A Risk Prediction Model Based on Machine Learning for Cognitive Impairment Among Chinese Community-Dwelling Elderly People With Normal Cognition: Development and Validation Study

Predicting rheumatoid arthritis in the middle-aged and older population using patient-reported outcomes: insights from the SHARE cohort

BACKGROUND

In light of global population aging and the increasing prevalence of Rheumatoid Arthritis (RA) with age, strategies are needed to address this public health challenge. Machine learning (ML) may play a vital role in early identification of RA, allowing an early start of treatment, thereby reducing costs. This study aims first to identify potential variables related to RA, and second to explore and evaluate the potential of ML to identify RA patients in people over 50 years.

METHOD

We developed ML predictive models (lightGBM, logistic regression, k nearest neighbor, naive Bayes, random forrest, and XGBoost) using patient-reported outcomes collected from the SHARE database (7th and 9th wave).

RESULTS

Difficulties in daily life such as stooping and pulling are risk factors for RA. Lifestyle activities participation is negatively associated with RA. ML models performed differently with the lightGBM model achieving the highest AUC (0.748, 95 % CI: 0.739-0.758), and logistic regression and lightGBM showing the highest accuracy at 0.902. The sensitivity of naive Bayes was highest at 0.442. Significant differences were observed in the Hosmer-Lemeshow test (P < 0.05).

CONCLUSION

The predictive models based on patient-reported outcome measures achieved fair performance with limited potential to early identify RA patients. Lifestyle activities and difficulties in daily life were associated with risk of RA and should be considered in anamnesis.

Development and validation of an interpretable machine learning model for predicting in-hospital mortality for ischemic stroke patients in ICU

BACKGROUND

Timely and accurate outcome prediction is essential for clinical decision-making for ischemic stroke patients in the intensive care unit (ICU). However, the interpretation and translation of predictive models into clinical applications are equally crucial. This study aims to develop an interpretable machine learning (IML) model that effectively predicts in-hospital mortality for ischemic stroke patients.

METHODS

In this study, an IML model was developed and validated using multicenter cohorts of 3225 ischemic stroke patients admitted to the ICU. Nine machine learning (ML) models, including logistic regression (LR), K-nearest neighbors (KNN), naive Bayes (NB), decision tree (DT), support vector machine (SVM), random forest (RF), XGBoost, LightGBM, and artificial neural network (ANN), were developed to predict in-hospital mortality using data from the MIMIC-IV and externally validated in Shanghai Changhai Hospital. Feature selection was conducted using three algorithms. Model's performance was assessed using area under the receiver operating characteristic (AUROC), accuracy, sensitivity, specificity and F1 score. Calibration curve and Brier score were used to evaluate the degree of calibration of the model, and decision curve analysis were generated to assess the net clinical benefit. Additionally, the SHapley Additive exPlanations (SHAP) method was employed to evaluate the risk of in-hospital mortality among ischemic stroke patients admitted to the ICU.

RESULTS

Mechanical ventilation, age, statins, white blood cell, blood urea nitrogen, hematocrit, warfarin, bicarbonate and systolic blood pressure were selected as the nine most influential variables. The RF model demonstrated the most robust predictive performance, achieving AUROC values of 0.908 and 0.858 in the testing set and external validation set, respectively. Calibration curves also revealed a high consistency between observations and predictions. Decision curve analysis showed that the model had the greatest net benefit rate when the prediction probability threshold is 0.10 ∼ 0.80. SHAP was employed to interpret the RF model. In addition, we have developed an online prediction calculator for ischemic stroke patients.

CONCLUSION

This study develops a machine learning-based calculator to predict the probability of in-hospital mortality among patients with ischemic stroke in ICU. The calculator has the potential to guide clinical decision-making and improve the care of patients with ischemic stroke by identifying patients at a higher risk of in-hospital mortality.

IADL for identifying cognitive impairment in Chinese older adults: insights from cross-lagged panel network analysis

BACKGROUND

As China has entered an aging society, the prevention of cognitive impairment is of great importance. The progression of cognitive impairment is usually a slow and continuous process, with Instrumental Activities of Daily Living (IADL) serving as a sensitive indicator for early prediction of cognitive decline. The objective of this study was to utilize longitudinal network analysis to pinpoint the most sensitive indicators of IADLs to identify cognitive impairment in different populations, and to offer practical recommendations for preventing cognitive impairment among older adults in China.

METHODS

A total of 2,781 participants were selected from the Chinese Longitudinal Healthy Longevity Survey (CLHLS 2014-2018). Cognitive function and IADLs were assessed by Mini-mental State Examination (MMSE) and Chinese modified Lawton scale, respectively. In this study, the cross-lagged panel network (CLPN) model was employed to construct three separate networks for all Chinese older adults, male Chinese older adults, and female Chinese older adults, respectively. Two centrality indices were used to quantify symptom centrality in directed CLPN: In-Expected-Influence (IEI) and Out-Expected-Influence (OEI).

RESULTS

In the IADLs and cognitive function networks, "Use public transit," "Make food" and "Walk 1 km" emerged as the most influential and important indicators. The edge "Use public transit → Attention and Calculation" was the strongest edge connection in all three networks. Among older adult males, "General ability" exhibited the most influence on other cognitive domains, followed by "Language," while "Attention and Calculation" had a weaker influence. Conversely, among older adult females, "Attention and Calculation" was the most influential factor, followed by "General ability" and "Language."

CONCLUSIONS

This study provides new insights into the associations between specific IADL activities and cognitive function domains among Chinese older adults. Concentrate on monitoring limitations related to "Use public transit," "Make food" and "Walk 1 km," and promoting broader life-space mobility may be beneficial to preventing the decline of cognitive function. The findings underscore the importance of targeting interventions not only by specific cognitive domains, but also potentially by gender.

CLINICAL TRIAL NUMBER

Not applicable.

Predicting cognitive function among Chinese community-dwelling older adults: A supervised machine learning approach

OBJECTIVE

Identifying cognitive impairment early enough could support timely intervention of cognitive impairment and facilitate successful cognitive aging. We aimed to build more precise prediction models for cognitive function using less variable input among Chinese community-dwelling older adults.

METHODS

We used data from a prospective cohort of 13,906 older adults aged 60 years and above from the nationally representative China Health and Retirement Longitudinal Study (CHARLS) 2011-2020. The Gradient Boosting Classifier (GBC) and gradient boosting regressor (GBR) models were used to predict an individual's current cognitive function. For future cognition prediction, we trained GBR models to analyze the prediction error over the years.

RESULTS

Among 68 features, ten features were finally selected to develop the model: education attainment, childhood friendship, age, instrumental activities of daily living (IADLs), hukou type, mobility, sleep duration, gender, residence, and social participation. Our model exhibited robust performance in predicting current and future cognitive function. When an individual's current cognitive function was assessed as a dichotomous classification of cognitive impairment presence, the GBC model achieved an area under the receiver operating characteristic (ROC) of 0.832. When the outcome was forecasted as a continuous variable, the model achieved a root mean square error (RMSE) loss of 3.356 in the test set. For predicting future cognition, models taking into account the current cognitive state demonstrated superior performance.

CONCLUSIONS

Our study offers a practical tool to aid in the early identification of cognitive impairment, thus supporting timely interventions in the community environment and potentially contributing to successful cognitive aging.

Predicting Progression to Dementia Using Auditory Verbal Learning Test in Community-Dwelling Older Adults Based On Machine Learning

BACKGROUND

Primary healthcare institutions find identifying individuals with dementia particularly challenging. This study aimed to develop machine learning models for identifying predictive features of older adults with normal cognition to develop dementia.

METHODS

We developed four machine learning models: logistic regression, decision tree, random forest, and gradient-boosted trees, predicting dementia of 1,162 older adults with normal cognition at baseline from the Hubei Memory and Aging Cohort Study. All relevant variables collected were included in the models. The Shanghai Aging Study was selected as a replication cohort (n = 1,370) to validate the performance of models including the key features after a wrapper feature selection technique. Both cohorts adopted comparable diagnostic criteria for dementia to most previous cohort studies.

RESULTS

The random forest model exhibited slightly better predictive power using a series of auditory verbal learning test, education, and follow-up time, as measured by overall accuracy (93%) and an area under the curve (AUC) (mean [standard error]: 088 [0.07]). When assessed in the external validation cohort, its performance was deemed acceptable with an AUC of 0.81 (0.15). Conversely, the logistic regression model showed better results in the external validation set, attaining an AUC of 0.88 (0.20).

CONCLUSION

Our machine learning framework offers a viable strategy for predicting dementia using only memory tests in primary healthcare settings. This model can track cognitive changes and provide valuable insights for early intervention.

Predictive value of biliverdin reductase-A and homeostasis model assessment of insulin resistance on mild cognitive impairment in patients with type 2 diabetes

AIMS/INTRODUCTION

To investigate the predictive value of the biliverdin reductase-A (BVR-A) and the homeostasis model assessment for insulin resistance (HOMA-IR) on mild cognitive impairment (MCI) in patients with type 2 diabetes mellitus, and to establish a nomogram model.

MATERIALS AND METHODS

This study included 140 patients with type 2 diabetes mellitus. Based on Montreal Cognitive Assessment (MoCA) scores, participants were categorized into the normal cognitive function (T2DM-NCF) group (65 cases) and the mild cognitive impairment (T2DM-MCI) group (75 cases). Multivariate logistic regression analysis was performed to identify the factors associated with MCI in patients with type 2 diabetes mellitus. A nomogram prediction model was developed using R software for the selected factors, and its predictability and accuracy were verified.

RESULTS

Compared with the T2DM-NCF group, subjects with MCI were older, had a longer duration of diabetes, higher HOMA-IR, lower BVR-A, lower cognitive scores, and lower education levels (all P < 0.05). Multivariate logistic regression analysis showed that duration of diabetes (OR = 1.407, 95% CI: 1.163-1.701), HOMA-IR (OR = 1.741, 95% CI: 1.197-2.53), and BVR-A (OR = 0.528, 95% CI: 0.392-0.712) were significantly associated with the development of MCI in patients with type 2 diabetes mellitus. The C-index of the nomogram was 0.863 (95% CI: 0.752-0.937).

CONCLUSIONS

Our findings suggest that BVR-A and HOMA-IR are significantly associated with the development of MCI in patients with type 2 diabetes mellitus. The nomogram incorporating BVR-A and HOMA-IR aids in predicting the risk of developing MCI in these patients.

Using Machine Learning to Predict Cognitive Decline in Older Adults From the Chinese Longitudinal Healthy Longevity Survey: Model Development and Validation Study

Background

Cognitive impairment, indicative of Alzheimer disease and other forms of dementia, significantly deteriorates the quality of life of older adult populations and imposes considerable burdens on families and health care systems worldwide. The early identification of individuals at risk for cognitive impairment through a convenient and rapid method is crucial for the timely implementation of interventions.

Objective

The objective of this study was to explore the application of machine learning (ML) to integrate blood biomarkers, life behaviors, and disease history to predict the decline in cognitive function.

Methods

This approach uses data from the Chinese Longitudinal Healthy Longevity Survey. A total of 2688 participants aged 65 years or older from the 2008-2009, 2011-2012, and 2014 Chinese Longitudinal Healthy Longevity Survey waves were included, with cognitive impairment defined as a Mini-Mental State Examination (MMSE) score below 18. The dataset was divided into a training set (n=1331), an internal test set (n=333), and a prospective validation set (n=1024). Participants with a baseline MMSE score of less than 18 were excluded from the cohort to ensure a more accurate assessment of cognitive function. We developed ML models that integrate demographic information, health behaviors, disease history, and blood biomarkers to predict cognitive function at the 3-year follow-up point, specifically identifying individuals who are at risk of experiencing significant declines in cognitive function by that time. Specifically, the models aimed to identify individuals who would experience a significant decline in their MMSE scores (less than 18) by the end of the follow-up period. The performance of these models was evaluated using metrics including accuracy, sensitivity, and the area under the receiver operating characteristic curve.

Results

All ML models outperformed the MMSE alone. The balanced random forest achieved the highest accuracy (88.5% in the internal test set and 88.7% in the prospective validation set), albeit with a lower sensitivity, while logistic regression recorded the highest sensitivity. SHAP (Shapley Additive Explanations) analysis identified instrumental activities of daily living, age, and baseline MMSE scores as the most influential predictors for cognitive impairment.

Conclusions

The incorporation of blood biomarkers, along with demographic, life behavior, and disease history into ML models offers a convenient, rapid, and accurate approach for the early identification of older adult individuals at risk of cognitive impairment. This method presents a valuable tool for health care professionals to facilitate timely interventions and underscores the importance of integrating diverse data types in predictive health models.

A point-based cognitive impairment scoring system for southeast Asian adults

BACKGROUND

Cognitive impairment is a growing concern in Southeast Asian populations, where the burden of cerebrovascular disease (CeVD) is high. Currently, there is no point-based scoring system for identifying cognitive impairment in these populations.

OBJECTIVE

To develop and validate a simple point-based Cognitive Impairment Scoring System (CISS) for identifying individuals with cognitive impairment no dementia (CIND) and concomitant CeVD in Southeast Asian populations.

DESIGN

A cross-sectional study using data from two population-based studies.

SETTING

Community-based setting in Southeast Asia.

PARTICIPANTS

1,511 Southeast Asian adults (664 with CIND, 44.0 %).

MEASURES

Two CISS measures were developed: a basic measure including 11 easily assessable risk factors, and an extended measure incorporating seven additional neuroimaging markers. Performance was evaluated using receiver operating characteristic analysis (AUC) and calibration plots.

RESULTS

The AUC for CISS-basic and CISS-extended were 0.81 (95 %CI, 0.76-0.86) and 0.85 (95 %CI, 0.81-0.89), respectively. Calibration plots indicated satisfactory fit for both the basic measure (p=0.82) and the extended measure (p=0.17). The basic measure included age, gender, ethnicity, education, systolic blood pressure, BMI, smoking history, diabetes, hyperlipidemia, stroke history, and mild/moderate depression. The extended measure added neuroimaging markers of CeVD and brain atrophy.

CONCLUSION

The CISS provides a quick, objective, and clinically relevant tool for assessing cognitive impairment risk in Southeast Asian populations. The basic measure is suitable for initial community-based screenings, while the extended measure offers higher specificity for probable diagnosis. This point-based system enables rapid estimation of cognitive status without requiring complex calculations, potentially improving early detection and management of cognitive impairment in clinical practice.

Using machine learning models to identify severe subjective cognitive decline and related factors in nurses during the menopause transition: a pilot study

OBJECTIVE

This study aims to develop and validate a machine learning model for identifying individuals within the nursing population experiencing severe subjective cognitive decline (SCD) during the menopause transition, along with their associated factors.

METHODS

A secondary analysis was performed using cross-sectional data from 1,264 nurses undergoing the menopause transition. The data set was randomly split into training (75%) and validation sets (25%), with the Bortua algorithm employed for feature selection. Seven machine learning models were constructed and optimized. Model performance was assessed using area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, and F1 score. Shapley Additive Explanations analysis was used to elucidate the weights and characteristics of various factors associated with severe SCD.

RESULTS

The average SCD score among nurses in the menopause transition was (5.38 ± 2.43). The Bortua algorithm identified 13 significant feature factors. Among the seven models, the support vector machine exhibited the best overall performance, achieving an area under the receiver operating characteristic curve of 0.846, accuracy of 0.789, sensitivity of 0.753, specificity of 0.802, and an F1 score of 0.658. The two variables most strongly associated with SCD were menopausal symptoms and the stage of menopause.

CONCLUSIONS

The machine learning models effectively identify individuals with severe SCD and the related factors associated with severe SCD in nurses during the menopause transition. These findings offer valuable insights for the management of cognitive health in women undergoing the menopause transition.

Trajectories of Cognitive Change and Their Association with All-Cause Mortality Among Chinese Older Adults: Results from the Chinese Longitudinal Healthy Longevity Survey

The analysis of cognitive trajectories is relatively underexplored in China. Furthermore, most previous studies examining the association between cognitive function and mortality have been limited to cross-sectional perspectives. This study aims to identify distinct cognitive trajectories and the corresponding influencing factors and investigate the impact of these trajectories on all-cause mortality in Chinese older adults. A total of 6232 subjects aged 65 years and above were drawn from the Chinese Longitudinal Healthy Longevity Survey. Growth mixture models were utilized to identify different cognitive trajectories, while Cox proportional hazards models were used to examine the association between the cognitive trajectories and all-cause mortality after adjusting for covariates. Four cognitive trajectories were identified: rapid decline group, slow decline group, low-level stable group, and high-level stable group. Some factors such as age, sex, and marital status were significantly associated with trajectories. Compared to the high-level stable group, adjusted hazard ratios and 95% confidence intervals (CIs) for the all-cause mortality were 3.87 (95% CI: 3.35-4.48), 1.41 (95% CI: 1.24-1.59), and 1.37 (95% CI: 1.18-1.58) for the rapid decline group, the slow decline group, and the low-level stable group, respectively, indicating that these three groups had a higher mortality risk. In summary, these findings facilitate the development of targeted health promotion measures, which have implications for reducing the social and economic burdens of cognitive decline.

Machine learning for the early prediction of long-term cognitive outcome in autoimmune encephalitis

BACKGROUND AND OBJECTIVE

Autoimmune encephalitis (AE) is an immune-mediated disease. Some patients experience persistent cognitive deficits despite receiving immunotherapy. We aimed to develop a prediction model for long-term cognitive outcomes in patients with AE.

METHOD

In this multicenter cohort study, a total of 341 patients with AE were enrolled from February 2014 to July 2023. Cognitive impairment was identified using the telephone Mini-Mental State Examination (t-MMSE). Six machine learning (ML) algorithms were used to assess the risk of developing cognitive impairment.

RESULTS

The median age of the patients with AE was 30.0 years (23.0-48.25), and 48.90 % (129/264) were female in the training cohort.77 (29.2 %) patients were identified with cognitive impairment after a median follow-up of 49 months. Among 16 features, the following six features were finally selected to develop the model: Cognitive Reserve Questionnaire (CRQ), Clinical Assessment Scale for Autoimmune Encephalitis (CASE), status epilepticus (SE), age, MRI abnormalities, and delayed immunotherapy. Compared to other ML models, the random forest (RF) model demonstrated superior performance with an AUC of 0.90. The accuracy, sensitivity, and specificity in the testing cohort were 0.87, 0.79, and 0.90, respectively.

CONCLUSION

The RF model based on CRQ, CASE scores, SE, age, MRI abnormalities and delayed immunotherapy demonstrates superior predictive performance and shows promise in predicting the risk of long-term cognitive outcomes in patients with AE in clinical settings.

Application of machine learning algorithms in an epidemiologic study of mortality

PURPOSE

Epidemiologic studies are important in assessing risk factors of mortality. Machine learning (ML) is efficient in analyzing multidimensional data to unravel dependencies between risk factors and health outcomes.

METHODS

Using a representative sample from the National Health and Nutrition Examination Survey data collected from 2009 to 2016 linked to the National Death Index public-use mortality data through December 31, 2019, we applied logistic, random forests, k-Nearest Neighbors, multivariate adaptive regression splines, support vector machines, extreme gradient boosting, and super learner ML algorithms to study risk factors of all-cause mortality. We evaluated the algorithms using area under the receiver operating curve (AUC-ROC), sensitivity, negative predictive value (NPV) among other metrics and interpreted the results using SHapley Additive exPlanation.

RESULTS

The AUC-ROC ranged from 0.80 ─ 0.87. The super learner had the highest AUC-ROC of 0.87 (95 % CI, 0.86 ─ 0.88), sensitivity of 0.86 (95 % CI, 0.84 ─ 0.88) and NPV of 0.98 (95 % CI, 0.98 ─ 0.99). Key risk factors of mortality included advanced age, larger waist circumference, male and systolic blood pressure. Being married, high annual household income, and high education level were linked with low risk of mortality.

CONCLUSIONS

Machine learning can be used to identify risk factors of mortality, which is critical for individualized targeted interventions in epidemiologic studies.

Effect of Intraoperative Midazolam on Postoperative Delirium in Older Surgical Patients: A Prospective, Multicenter Cohort Study

BACKGROUND

Midazolam is a short-acting benzodiazepine frequently used in the perioperative setting. This study aimed to investigate the potential impact of intraoperative midazolam on postoperative delirium in older patients undergoing noncardiac surgery.

METHODS

This study included patients aged 65 yr and older who received general anesthesia between April 2020 and April 2022 in multiple hospitals across China. Postoperative delirium occurring within 7 days was assessed using the 3-min Diagnostic Interview for Confusion Assessment Method. Univariable and multivariable logistic regression models based on the random effects were used to determine the association between midazolam administration and the occurrence of postoperative delirium, presented as the risk ratio and 95% CI. A Kaplan-Meier cumulative incidence curve was plotted to compare the distribution of time to postoperative delirium onset between patients who received midazolam and those who did not. Subgroup analyses based on specific populations were performed to explore the relationship between midazolam and postoperative delirium.

RESULTS

In all, 5,663 patients were included, of whom 723 (12.8%) developed postoperative delirium. Univariate and multivariable logistic regression analyses based on random effects of different hospitals showed no significant association between midazolam medication and postoperative delirium among older population (unadjusted risk ratio, 0.96; 95% CI, 0.90 to 1.30; P = 0.38; and adjusted risk ratio, 1.09; 95% CI, 0.91 to 1.33; P = 0.35). The Kaplan-Meier curve showed no difference in the distribution of time to postoperative delirium onset (hazard ratio, 1.02; 95% CI, 0.88 to 1.18; P = 0.82). The results of subgroup analyses found that intraoperative midazolam treatment was not associated with postoperative delirium in the specific subgroups of patients.

CONCLUSIONS

Intraoperative administration of midazolam may not be associated with an increased risk of postoperative delirium in older patients undergoing noncardiac surgery.

Predicting the decline of physical function among the older adults in China: A cohort study based on China longitudinal health and longevity survey (CLHLS)

BACKGROUND

As the arrival of healthy aging, maintaining physical function (PF) in older adults is crucial for their health, so it is necessary to detect the decline of PF among them and take intervention measures.

METHODS

We construct eight machine learning models to predict declines of PF in this study. The performance of the models was tested by Area Under Curve (AUC), sensitivity, specificity, accuracy, precision-recall (PR) curve and calibration degree. Decision Curve Analysis (DCA) curve was used to evaluate their discrimination ability and clinical practicability.

RESULTS

There were 2,017 participants in this study. We found that logistic regression models performed the best, with AUC, sensitivity, specificity and accuracy of 0.803, 0.698, 0.761 and 0.744 respectively, and its DCA curve, calibration degree and PR curve also performed well.

CONCLUSION

Logistic regression can be used as optimal model to identify the risk of PF decline among older adults in China.

The relationship between levels of physical activity, adherence to the MIND diet, and cognitive impairment in adults aged 65 years or older in Pakistan

Background

In contrast to existing evidence focusing on high-income countries, this study offers novel insights into the demographic and geographical context that have yet to be explored in the existing literature. Comparatively, in Pakistan, cognitive impairment is one of the neglected disorders that can develop into dementia and Alzheimer's disease. As no treatment is available, lifestyle modifications are a valid intervention for cognitive health.

Objective

This study aimed to assess the relationship between physical functionality, adherence to the Mediterranean-DASH diet Intervention for Neurological Delay (MIND), and cognitive impairment among elderly individuals in Pakistan.

Methods

From January to June 2023, this cross-sectional study recruited 462 participants aged 65 and above. We used proven tools in gerontological research, such as the MIND diet quiz and Quick Physical Activity Rating scale (QPAR), to evaluate diet and physical activity levels. Cognitive function was assessed using the Mini-Mental State Examination.

Results

Our analysis revealed that 26.40% of the participants had mild cognitive impairment, whereas 48.50% demonstrated low adherence to the MIND diet. The mean QPAR score was 20.51 ± 18.77. A significant association was found between lower physical activity levels and increased cognitive impairment (adjusted odds ratio 9.94, confidence interval (CI): 6.07-16.27). Additionally, higher adherence to the MIND diet correlated with reduced cognitive impairment (odds ratio 0.29, CI: 0.18-0.46).

Conclusions

These findings highlight the critical role of diet and physical activity in cognitive health among the elderly population. The study emphasizes the need for targeted public health interventions and further longitudinal research to explore the long-term effects of these factors on cognitive health.

Decoding machine learning in nursing research: A scoping review of effective algorithms

INTRODUCTION

The rapid evolution of artificial intelligence (AI) technology has revolutionized healthcare, particularly through the integration of AI into health information systems. This transformation has significantly impacted the roles of nurses and nurse practitioners, prompting extensive research to assess the effectiveness of AI-integrated systems. This scoping review focuses on machine learning (ML) used in nursing, specifically investigating ML algorithms, model evaluation methods, areas of focus related to nursing, and the most effective ML algorithms.

DESIGN

The scoping review followed the Preferred Reporting Items for Systematic Review and Meta-Analysis Extension for Scoping Reviews (PRISMA-ScR) guidelines.

METHODS

A structured search was performed across seven databases according to PRISMA-ScR: PubMed, EMBASE, CINAHL, Web of Science, OVID, PsycINFO, and ProQuest. The quality of the final reviewed studies was assessed using the Medical Education Research Study Quality Instrument (MERSQI).

RESULTS

Twenty-six articles published between 2019 and 2023 met the inclusion and exclusion criteria, and 46% of studies were conducted in the US. The average MERSQI score was 12.2, indicative of moderate- to high-quality studies. The most used ML algorithm was Random Forest. The four second-most used were logistic regression, least absolute shrinkage and selection operator, decision tree, and support vector machine. Most ML models were evaluated by calculating sensitivity (recall)/specificity, accuracy, receiver operating characteristic (ROC), area under the ROC (AUROC), and positive/negative prediction value (precision). Half of the studies focused on nursing staff or students and hospital readmission or emergency department visits. Only 11 articles reported the most effective ML algorithm(s).

CONCLUSION

The scoping review provides insights into the current status of ML research in nursing and recognition of its significance in nursing research, confirming the benefits of ML in healthcare. Recommendations include incorporating experimental designs in research studies to optimize the use of ML models across various nursing domains.

CLINICAL RELEVANCE

The scoping review demonstrates substantial clinical relevance of ML applications for nurses, nurse practitioners, administrators, and researchers. The integration of ML into healthcare systems and its impact on nursing practices have important implications for patient care, resource management, and the evolution of nursing research.

Bias in machine learning applications to address non-communicable diseases at a population-level: a scoping review

BACKGROUND

Machine learning (ML) is increasingly used in population and public health to support epidemiological studies, surveillance, and evaluation. Our objective was to conduct a scoping review to identify studies that use ML in population health, with a focus on its use in non-communicable diseases (NCDs). We also examine potential algorithmic biases in model design, training, and implementation, as well as efforts to mitigate these biases.

METHODS

We searched the peer-reviewed, indexed literature using Medline, Embase, Cochrane Central Register of Controlled Trials and Cochrane Database of Systematic Reviews, CINAHL, Scopus, ACM Digital Library, Inspec, Web of Science's Science Citation Index, Social Sciences Citation Index, and the Emerging Sources Citation Index, up to March 2022.

RESULTS

The search identified 27 310 studies and 65 were included. Study aims were separated into algorithm comparison (n = 13, 20%) or disease modelling for population-health-related outputs (n = 52, 80%). We extracted data on NCD type, data sources, technical approach, possible algorithmic bias, and jurisdiction. Type 2 diabetes was the most studied NCD. The most common use of ML was for risk modeling. Mitigating bias was not extensively addressed, with most methods focused on mitigating sex-related bias.

CONCLUSION

This review examines current applications of ML in NCDs, highlighting potential biases and strategies for mitigation. Future research should focus on communicable diseases and the transferability of ML models in low and middle-income settings. Our findings can guide the development of guidelines for the equitable use of ML to improve population health outcomes.

Development and Validation of a Predictive Model for Early Identification of Cognitive Impairment Risk in Community-Based Hypertensive Patients

Objective: To investigate the risk factors for the development of mild cognitive dysfunction in hypertensive patients in the community and to develop a risk prediction model. Method: The data used in this study were obtained from two sources: the China Health and Retirement Longitudinal Study (CHARLS) and the Chinese Longitudinal Healthy Longevity Survey (CLHLS). A total of 1121 participants from CHARLS were randomly allocated into a training set and a validation set, following a 70:30 ratio. Meanwhile, an additional 4016 participants from CLHLS were employed for external validation of the model. The patients in this study were divided into two groups: those with mild cognitive impairment and those without. General information, employment status, pension, health insurance, and presence of depressive symptoms were compared between the two groups. LASSO regression analysis was employed to identify the most predictive variables for the model, utilizing 14-fold cross-validation. The risk prediction model for cognitive impairment in hypertensive populations was developed using generalized linear models. The model's discriminatory power was evaluated through the area under the receiver operating characteristic (ROC) curve and calibration curves. Results: In the modeling group, eight variables such as gender, age, residence, education, alcohol use, depression, employment status, and health insurance were ultimately selected from an initial pool of 21 potential predictors to construct the risk prediction model. The area under the curve (AUC) values for the training, internal, and external validation sets were 0.777, 0.785, and 0.782, respectively. All exceeded the threshold of 0.7, suggesting that the model effectively predicts the incidence of mild cognitive dysfunction in community-based hypertensive patients. A risk prediction model was developed using a generalized linear model in conjunction with Lasso regression. The model's performance was evaluated using the area under the receiver operating characteristic (ROC) curve. Hosmer-Lemeshow test values yielded p = .346 and p = .626, both of which exceeded the 0.05 threshold. Calibration curves demonstrated a significant agreement between the nomogram model and observed outcomes, serving as an effective tool for evaluating the model's predictive performance. Discussion: The predictive model developed in this study serves as a promising and efficient tool for evaluating cognitive impairment in hypertensive patients, aiding community healthcare workers in identifying at-risk populations.

Predicting the Risk of Postoperative Delirium in Elderly Patients Undergoing Hip Arthroplasty: Development and Assessment of a Novel Nomogram

OBJECTIVE

To construct and internally validate a nomogram that predicts the likelihood of postoperative delirium in a cohort of elderly individuals undergoing hip arthroplasty.

METHODS

Data for a total of 681 elderly patients underwent hip arthroplasty were retrospectively collected and divided into a model (n = 477) and a validation cohort (n = 204) according to the principle of 7:3 distribution temporally. The assessment of postoperative cognitive function was conducted through the utilization of The Confusion Assessment Method (CAM). The nomogram model for postoperative cognitive impairments was established by a combination of Lasso regression and logistic regression. The receiver operating characteristic (ROC) curve, calibration plot, and decision curve analysis (DCA) were used to evaluate the performance.

RESULTS

The nomogram utilized various predictors, including age, body mass index (BMI), education, preoperative Barthel Index, preoperative hemoglobin level, history of diabetes, and history of cerebrovascular disease, to forecast the likelihood of postoperative delirium in patients. The area under the ROC curves (AUC) for the nomogram, incorporating the aforementioned predictors, was 0.836 (95% CI: 0.797-0.875) for the training set and 0.817 (95% CI: 0.755-0.880) for the validation set. The calibration curves for both sets indicated a good agreement between the nomogram's predictions and the actual probabilities.

CONCLUSION

The use of this novel nomogram can help clinicians predict the likelihood of delirium after hip arthroplasty in elderly patients and help prevent and manage it in advance.

Development and validation of machine learning models to predict frailty risk for elderly

AIMS

Early identification and intervention of the frailty of the elderly will help lighten the burden of social medical care and improve the quality of life of the elderly. Therefore, we used machine learning (ML) algorithm to develop models to predict frailty risk in the elderly.

DESIGN

A prospective cohort study.

METHODS

We collected data on 6997 elderly people from Chinese Longitudinal Healthy Longevity Study wave 6-7 surveys (2011-2012, 2014). After the baseline survey in 1998 (wave 1), the project conducted follow-up surveys (wave 2-8) in 2000-2018. The osteoporotic fractures index was used to assess frailty. Four ML algorithms (random forest [RF], support vector machine, XGBoost and logistic regression [LR]) were used to develop models to identify the risk factors of frailty and predict the risk of frailty. Different ML models were used for the prediction of frailty risk in the elderly and frailty risk was trained on a cohort of 4385 elderly people with frailty (split into a training cohort [75%] and internal validation cohort [25%]). The best-performing model for each study outcome was tested in an external validation cohort of 6997 elderly people with frailty pooled from the surveys (wave 6-7). Model performance was assessed by receiver operating curve and F2-score.

RESULTS

Among the four ML models, the F2-score values were similar (0.91 vs. 0.91 vs. 0.88 vs. 0.90), and the area under the curve (AUC) values of RF model was the highest (0.75), followed by LR model (0.74). In the final two models, the AUC values of RF and LR model were similar (0.77 vs. 0.76) and their accuracy was identical (87.4% vs. 87.4%).

CONCLUSION

Our study developed a preliminary prediction model based on two different ML approaches to help predict frailty risk in the elderly.

IMPACT

The presented models from this study can be used to inform healthcare providers to predict the frailty probability among older adults and maybe help guide the development of effective frailty risk management interventions.

IMPLICATIONS FOR THE PROFESSION AND/OR PATIENT CARE

Detecting frailty at an early stage and implementing timely targeted interventions may help to improve the allocation of health care resources and to reduce frailty-related burden. Identifying risk factors for frailty could be beneficial to provide tailored and personalized care intervention for older adults to more accurately prevent or improve their frail conditions so as to improve their quality of life.

REPORTING METHOD

The study has adhered to STROBE guidelines.

PATIENT OR PUBLIC CONTRIBUTION

No patient or public contribution.

Early Identification of Cognitive Impairment in Community Environments Through Modeling Subtle Inconsistencies in Questionnaire Responses: Machine Learning Model Development and Validation

BACKGROUND

The underdiagnosis of cognitive impairment hinders timely intervention of dementia. Health professionals working in the community play a critical role in the early detection of cognitive impairment, yet still face several challenges such as a lack of suitable tools, necessary training, and potential stigmatization.

OBJECTIVE

This study explored a novel application integrating psychometric methods with data science techniques to model subtle inconsistencies in questionnaire response data for early identification of cognitive impairment in community environments.

METHODS

This study analyzed questionnaire response data from participants aged 50 years and older in the Health and Retirement Study (waves 8-9, n=12,942). Predictors included low-quality response indices generated using the graded response model from four brief questionnaires (optimism, hopelessness, purpose in life, and life satisfaction) assessing aspects of overall well-being, a focus of health professionals in communities. The primary and supplemental predicted outcomes were current cognitive impairment derived from a validated criterion and dementia or mortality in the next ten years. Seven predictive models were trained, and the performance of these models was evaluated and compared.

RESULTS

The multilayer perceptron exhibited the best performance in predicting current cognitive impairment. In the selected four questionnaires, the area under curve values for identifying current cognitive impairment ranged from 0.63 to 0.66 and was improved to 0.71 to 0.74 when combining the low-quality response indices with age and gender for prediction. We set the threshold for assessing cognitive impairment risk in the tool based on the ratio of underdiagnosis costs to overdiagnosis costs, and a ratio of 4 was used as the default choice. Furthermore, the tool outperformed the efficiency of age or health-based screening strategies for identifying individuals at high risk for cognitive impairment, particularly in the 50- to 59-year and 60- to 69-year age groups. The tool is available on a portal website for the public to access freely.

CONCLUSIONS

We developed a novel prediction tool that integrates psychometric methods with data science to facilitate "passive or backend" cognitive impairment assessments in community settings, aiming to promote early cognitive impairment detection. This tool simplifies the cognitive impairment assessment process, making it more adaptable and reducing burdens. Our approach also presents a new perspective for using questionnaire data: leveraging, rather than dismissing, low-quality data.

Body mass index, waist circumference, hip circumference, abdominal volume index, and cognitive function in older Chinese people: a nationwide study

BACKGROUND

Numerous studies have indicated an obesity paradox in observational research on aging health, where being normal weight or underweight adversely affects cognitive function, while moderate obesity may offer protective benefits. This study aims to investigate the association between body mass index (BMI), waist circumference (WC), hip circumference (HC), waist-to-height ratio (WHtR), waist-to-hip ratio (WHR), abdominal volume index (AVI), and the joint effect of BMI and HC on cognitive impairment in older Chinese people.

METHODS

A total of 10,579 participants aged 65 years and older from the 2018 Chinese Longitudinal Healthy Longevity Survey (CLHLS) were included in this cross-sectional study. BMI, WC, HC, WHtR, WHR, and AVI were calculated from height, weight, WC, and HC measurements, where weight, WC, and HC were obtained by direct measurement. Mini-Mental State Examination was used to assess cognitive impairment. Odds ratios (ORs) and 95% confidence intervals (95% CIs) were estimated using binary logistic regression. Non-linear correlations were investigated using restricted cubic spline curves.

RESULTS

In multivariate logistic regression models fully adjusted for confounding variables, our analyses showed significant negative associations of WC [OR 0.93 (95%CI 0.88-0.98), P = .012], HC [OR 0.92 (95%CI 0.87-0.97), P = .004], lower WHR (Q2) [OR 0.85 (95%CI 0.72-1.00), P = .044], and AVI [OR 0.93 (95%CI 0.88-0.98), P = .011] with cognitive impairment. Nonlinear curve analysis showed that the risk of cognitive impairment was lowest when the BMI was about 25.5 kg/m², suggesting that the optimal BMI for older Chinese people to maintain good cognitive ability may be in the overweight range. In addition, there was a non-linear "N" shaped relationship between HC and cognitive impairment, with HC having the highest risk of cognitive impairment at about 82 cm and the lowest risk at about 101 cm. The joint effects analysis indicated that the lowest risk was observed among those with normal or higher BMI but higher HC compared with participants with normal BMI levels and lower HC levels.

CONCLUSION

In older Chinese people, a low-waisted and high-hip circumference body figure is favorable for cognitive function in older people. It also found a significant association between AVI and cognitive impairment. The joint analysis of BMI and HC suggests that maintaining a normal or higher BMI with a higher HC may be more conducive to maintaining good cognitive function.

Evidence of the Long-Term Protective Effect of Moderate-Intensity Physical Activity on Cognitive Function in Middle-Aged and Elderly Individuals: A Predictive Analysis of Longitudinal Studies

OBJECTIVE

To investigate the effects of different intensities of physical activity (PA) on cognitive function in middle-aged and elderly individuals, and to predict future trends in cognitive ability using longitudinal data to assess the long-term role of PA in cognitive preservation.

METHODS

Data from the China Health and Retirement Longitudinal Study (CHARLS) were utilized. Mixed-effects models were employed to analyze the impacts of low-intensity PA (LPA), moderate-intensity PA (MPA), and vigorous-intensity PA (VPA) on overall cognition, episodic memory, and mental intactness. Random forest and XGBoost machine learning methods were employed to further validate the effects of PA. ARIMA models predicted future cognitive trends under the influence of PA.

RESULTS

MPA demonstrated significant advantages in preserving cognitive function, particularly in overall cognition and episodic memory. While LPA had some protective effects, they were less significant than those of MPA, and VPA did not show advantages. Machine learning methods confirmed these findings. ARIMA model predictions indicated that the protective effects of MPA on cognitive function are likely to persist in the future.

CONCLUSIONS

Moderate-intensity physical activity is associated with the preservation of cognitive ability in middle-aged and elderly individuals and may continue to provide this benefit in the future; however, further in-depth research is needed for confirmation.

Exploration of Risk Factors for Cardiovascular Disease in Patients with Rheumatoid Arthritis: A Retrospective Study

OBJECTIVE

Patients with rheumatoid arthritis (RA) have increased mortality and morbidity rates owing to cardiovascular diseases (CVD). Timely detection of CVD in RA can greatly improve patient prognosis; however, this technique remains challenging. We aimed to investigate the risk factors for CVD incidence in patients with RA.

METHODS

This retrospective study included RA patients without CVD risk factors (n = 402), RA with CVD risk factors (n = 394), and RA with CVD (n = 201). Their data on routine examination indicators, vascular endothelial growth factor (VEGF), and immune cells were obtained from medical records. The characteristic variables between each group were screened using univariate analysis, least absolute shrinkage and selection operator (LASSO), random forest (RF), and logistic regression (LR) models, and individualized nomograms were further established to more conveniently observe the likelihood of CVD in RA.

RESULTS

Univariate analysis revealed significantly elevated levels of white blood cells (WBC), blood urea nitrogen (BUN), creatinine, creatine kinase (CK), lactate dehydrogenase (LDH), VEGF, serum total cholesterol (TC), triglycerides (TG), low-density lipoprotein (LDL), apolipoprotein B100 (ApoB100), and apolipoprotein E (ApoE) in RA patients with CVD, whereas apolipoprotein A1 (ApoA1) and high-density lipoprotein/cholesterol (HDL/TC) were decreased. Furthermore, the ratio of regulatory T (Treg) cells exhibiting excellent separation performance in RA patients with CVD was significantly lower than that in other groups, whereas the ratios of Th1/Th2/NK and Treg cells were significantly elevated. The LASSO, RF, and LR models were also used to identify the risk factors for CVD in patients with RA. Through the final selected indicators screened using the three machine learning models and univariate analysis, a convenient nomogram was established to observe the likelihood of CVD in patients with RA.

CONCLUSIONS

Serum lipids, lipoproteins, and reduction of Treg cells have been identified as risk factors for CVD in patients with RA. Three nomograms combining various risk factors were constructed to predict CVD occurring in patients with RA (RA with/without CVD risk factors).

Significance of plasma p-tau217 in predicting long-term dementia risk in older community residents: Insights from machine learning approaches

INTRODUCTION

Whether plasma biomarkers play roles in predicting incident dementia among the general population is worth exploring.

METHODS

A total of 1857 baseline dementia-free older adults with follow-ups up to 13.5 years were included from a community-based cohort. The Recursive Feature Elimination (RFE) algorithm aided in feature selection from 90 candidate predictors to construct logistic regression, naive Bayes, bagged trees, and random forest models. Area under the curve (AUC) was used to assess the model performance for predicting incident dementia.

RESULTS

During the follow-up of 12,716 person-years, 207 participants developed dementia. Four predictive models, incorporated plasma p-tau217, age, and scores of MMSE, STICK, and AVLT, exhibited AUCs ranging from 0.79 to 0.96 in testing datasets. These models maintained robustness across various subgroups and sensitivity analyses.

DISCUSSION

Plasma p-tau217 outperforms most traditional variables and may be used to preliminarily screen older individuals at high risk of dementia.

HIGHLIGHTS

Plasma p-tau217 showed comparable importance with age and cognitive tests in predicting incident dementia among community older adults. Machine learning models combining plasma p-tau217, age, and cognitive tests exhibited excellent performance in predicting incident dementia. The training models demonstrated robustness in subgroup and sensitivity analysis.

Development and Validation of a Nocturnal Hypoglycaemia Risk Model for Patients With Type 2 Diabetes Mellitus

AIM

To develop and test different machine learning algorithms for predicting nocturnal hypoglycaemia in patients with type 2 diabetes mellitus.

DESIGN

A retrospective study.

METHODS

We collected data from dynamic blood glucose monitoring of patients with T2DM admitted to the Department of Endocrinology and Metabolism at a hospital in Shanghai, China, from November 2020 to January 2022. Patients undergone the continuous glucose monitoring (CGM) for ≥ 24 h were included in this study. Logistic regression, random forest and light gradient boosting machine algorithms were employed, and the models were validated and compared using AUC, accuracy, specificity, recall rate, precision, F1 score and the Kolmogorov-Smirnov test.

RESULTS

A total of 4015 continuous glucose-monitoring data points from 440 patients were included, and 28 variables were selected to build the risk prediction model. The 440 patients had an average age of 62.7 years. Approximately 48.2% of the patients were female and 51.8% were male. Nocturnal hypoglycaemia appeared in 573 (14.30%) of 4015 continuous glucose monitoring data. The light gradient boosting machine model demonstrated the highest predictive performances: AUC (0.869), specificity (0.802), accuracy (0.801), precision (0.409), recall rate (0.797), F1 score (0.255) and Kolmogorov (0.603). The selected predictive factors included time below the target glucose range, duration of diabetes, insulin use before bed and dynamic blood glucose monitoring parameters from the previous day.

PATIENT OR PUBLIC CONTRIBUTION

No Patient or Public Contribution.

Association of Tai Chi and Square Dance with Cognitive Function in Chinese Older Adults

OBJECTIVE

This study explores the association of Tai Chi and square dance with cognitive function and compares the effects of the two fitness programs on cognitive function in Chinese older adults.

METHODS

A total of 1732 older people (aged 60 years and over) met the inclusion criteria from the 2018 Chinese Longitudinal Healthy Longevity Survey. Based on the frequency of participating in Tai Chi and square dance, older adults were divided into three groups: a Tai Chi group (n = 234), a square dance group (n = 345), and a control group (n = 1153). Cognitive function was measured using a modified Mini-Mental State Examination (MMSE). Participation in Tai Chi or square dance was investigated by asking the subjects to report how often they participated in the fitness programs.

RESULTS

Older adults in both the Tai Chi group and the square dance group had higher scores in all MMSE items, including orientation, registration, attention and calculation, recall, and language, compared to those in the control group. But there were no significant differences in any MMSE items between the Tai Chi group and the square dance group. Multiple regression analysis showed that participating in Tai Chi or square dance, age, educational level, and sex can predict cognitive function in older people.

CONCLUSION

Our findings suggest that participating in Tai Chi and square dance are associated with better cognitive function, and Tai Chi and square dance have similar effects on cognitive function in the Chinese older population.

Establishment of a mild cognitive impairment risk model in middle-aged and older adults: a longitudinal study

BACKGROUND

Early identification individuals at high risk of mild cognitive impairment (MCI) is essential for prevention and intervention strategies of dementia, such as Alzheimer's disease. MCI prediction considering the interdependence of predictors in longitudinal data needs to be further explored. We aimed to employ machine learning (ML) to develop and verify a prediction model of MCI.

METHODS

In a longitudinal population-based cohort of China Health and Retirement Longitudinal Study (CHARLS), 8390 non-MCI participants were enrolled. The diagnosis of MCI was based on the aging-associated cognitive decline (AACD), and 13 factors (gender, education, marital status, residence, diabetes, hypertension, depression, hearing impairment, social isolation, physical activity, drinking status, body mass index and expenditure) were finally selected as predictors. We implemented a long short-term memory (LSTM) to predict the MCI risks in middle-aged and older adults within 7 years. The Receiver Operating Characteristic curve (ROC) and calibration curve were used to evaluate the performance of the model.

RESULTS

Through 7 years of follow-up, 1925 participants developed MCI. The model for all incident MCI achieved an AUC of 0.774, and its deployment to the participants followed 2, 4, and 7 years achieved results of 0.739, 0.747, and 0.750, respectively. The model was well-calibrated with predicted probabilities plotted against the observed proportions of cognitive impairment. Education level, gender, marital status, and depression contributed most to the prediction of MCI.

CONCLUSIONS

This model could be widely applied to medical institutions, even in the community, to identify middle-aged and older adults at high risk of MCI.

Development of Automated Triggers in Ambulatory Settings in Brazil: Protocol for a Machine Learning-Based Design Thinking Study

BACKGROUND

The use of technologies has had a significant impact on patient safety and the quality of care and has increased globally. In the literature, it has been reported that people die annually due to adverse events (AEs), and various methods exist for investigating and measuring AEs. However, some methods have a limited scope, data extraction, and the need for data standardization. In Brazil, there are few studies on the application of trigger tools, and this study is the first to create automated triggers in ambulatory care.

OBJECTIVE

This study aims to develop a machine learning (ML)-based automated trigger for outpatient health care settings in Brazil.

METHODS

A mixed methods research will be conducted within a design thinking framework and the principles will be applied in creating the automated triggers, following the stages of (1) empathize and define the problem, involving observations and inquiries to comprehend both the user and the challenge at hand; (2) ideation, where various solutions to the problem are generated; (3) prototyping, involving the construction of a minimal representation of the best solutions; (4) testing, where user feedback is obtained to refine the solution; and (5) implementation, where the refined solution is tested, changes are assessed, and scaling is considered. Furthermore, ML methods will be adopted to develop automated triggers, tailored to the local context in collaboration with an expert in the field.

RESULTS

This protocol describes a research study in its preliminary stages, prior to any data gathering and analysis. The study was approved by the members of the organizations within the institution in January 2024 and by the ethics board of the University of São Paulo and the institution where the study will take place. in May 2024. As of June 2024, stage 1 commenced with data gathering for qualitative research. A separate paper focused on explaining the method of ML will be considered after the outcomes of stages 1 and 2 in this study.

CONCLUSIONS

After the development of automated triggers in the outpatient setting, it will be possible to prevent and identify potential risks of AEs more promptly, providing valuable information. This technological innovation not only promotes advances in clinical practice but also contributes to the dissemination of techniques and knowledge related to patient safety. Additionally, health care professionals can adopt evidence-based preventive measures, reducing costs associated with AEs and hospital readmissions, enhancing productivity in outpatient care, and contributing to the safety, quality, and effectiveness of care provided. Additionally, in the future, if the outcome is successful, there is the potential to apply it in all units, as planned by the institutional organization.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/55466.

A glimpse into the future: revealing the key factors for survival in cognitively impaired patients

Background

Drawing on prospective data from the National Health and Nutrition Examination Survey (NHANES), our goal was to construct and validate a 5-year survival prediction model for individuals with cognitive impairment (CI).

Methods

This study entailed a prospective cohort design utilizing information from the 2011-2014 NHANES dataset, encompassing individuals aged 40 years or older, with updated mortality status as of December 31, 2019. Predictive models within the derivation and validation cohorts were assessed using logistic proportional risk regression, column-line plots, and least absolute shrinkage and selection operator (LASSO) binomial regression models.

Results

The study enrolled a total of 1,439 participants (677 men, mean age 69.75 ± 6.71 years), with the derivation and validation cohorts consisting of 1,007 (538 men) and 432 (239 men) individuals, respectively. The 5-year mortality rate stood at 16.12% (n = 232). We devised a 5-item column-line graphical model incorporating age, race, stroke, cardiovascular disease (CVD), and blood urea nitrogen (BUN). The model exhibited an area under the curve (AUC) of 0.772 with satisfactory calibration. Internal validation demonstrated that the column-line graph model displayed strong discrimination, yielding an AUC of 0.733, and exhibited good calibration.

Conclusion

To sum up, our study successfully developed and internally validated a 5-item nomogram integrating age, race, stroke, cardiovascular disease, and blood urea nitrogen. This nomogram exhibited robust predictive performance for 5-year mortality in individuals with CI, offering a valuable tool for prognostic evaluation and personalized care planning.

Development and validation of a risk prediction model for mild cognitive impairment in elderly patients with type 2 diabetes mellitus

BACKGROUND

The prevalence of mild cognitive impairment (MCI) is steadily increasing among elderly people with type 2 diabetes (T2DM). This study aimed to create and validate a predictive model based on a nomogram.

METHODS

This cross-sectional study collected sociodemographic characteristics, T2DM-related factors, depression, and levels of social support from 530 older adults with T2DM. We used LASSO regression and multifactorial logistic regression to determine the predictors of the model. The performance of the nomogram was evaluated using calibration curves, receiver operating characteristics (ROC), and decision curve analysis (DCA).

RESULTS

The nomogram comprised age, smoking, physical activity, social support, depression, living alone, and glycosylated hemoglobin. The AUC for the training and validation sets were 0.914 and 0.859. The DCA showed good clinical applicability.

CONCLUSIONS

This predictive nomogram has satisfactory accuracy and discrimination. Therefore, the nomogram can be intuitively and easily used to detect MCI in elderly adults with T2DM.

Assessment of the Daily Living Activities of Older People (2004-2023): A Bibliometric and Visual Analysis

With a rapidly aging global population, comprehending the risks associated with older people's activities of daily living is increasingly important; yet, interdisciplinary analyses remain rare. By providing a bibliometric overview of the capability risks associated with older people's activities of daily living, in order to identify prevailing trends and future directions in the field, the study aims to fill this gap. Using CiteSpace software to analyze data from 928 articles published between 2004 and 2023, the study results demonstrate the growing interest in the capability risks of older people's activities of daily living, with the United States leading in the number of publications, and geriatrics emerging as the dominant discipline. Notably, Institut National de la Sante et de la Recherche Medicale (Inserm) in France emerges as a pivotal contributor in the field. Key research topics encompass risk factors associated with a decline in daily activities and disease-related studies, with emerging trends in cognitive function and instrumental activity research. Future research should prioritize the development of predictive mechanisms for daily living trends, exploration of caregiving solutions, and promotion of interdisciplinary collaboration. This study highlights promising avenues for further research, emphasizing the importance of predictive modeling, innovative caregiving strategies, and interdisciplinary cooperation in addressing capability risks in the activities of daily living of older people.

Correlation between hearing loss and mild cognitive impairment in the elderly population: Mendelian randomization and cross-sectional study

Background

Hearing loss and tinnitus have been linked to mild cognitive impairment (MCI); however, the evidence is constrained by ethical and temporal constraints, and few prospective studies have definitively established causation. This study aims to utilize Mendelian randomization (MR) and cross-sectional studies to validate and analyze this association.

Methods

This study employs a two-step approach. Initially, the genetic data of the European population from the Genome-wide association studies (GWAS) database is utilized to establish the causal relationship between hearing loss and cognitive impairment through Mendelian randomization using the inverse variance weighted (IVW) method. This is achieved by identifying strongly correlated single nucleotide polymorphisms (SNPs), eliminating linkage disequilibrium, and excluding weak instrumental variables. In the second step, 363 elderly individuals from 10 communities in Qingdao, China are assessed and examined using methods questionnaire survey and pure tone audiology (PTA). Logistic regression and multiple linear regression were used to analyze the risk factors of MCI in the elderly and to calculate the cutoff values.

Results

Mendelian randomization studies have shown that hearing loss is a risk factor for MCI in European populations, with a risk ratio of hearing loss to MCI loss of 1. 23. The findings of this cross-sectional study indicate that age, tinnitus, and hearing loss emerged as significant risk factors for MCI in univariate logistic regression analysis. Furthermore, multivariate logistic regression analysis identified hearing loss and tinnitus as potential risk factors for MCI. Consistent results were observed in multiple linear regression analysis, revealing that hearing loss and age significantly influenced the development of MCI. Additionally, a notable finding was that the likelihood of MCI occurrence increased by 9% when the hearing threshold exceeded 20 decibels.

Conclusion

This study provides evidence from genomic and epidemiological investigations indicating that hearing loss may serve as a risk factor for cognitive impairment. While our epidemiological study has found both hearing loss and tinnitus as potential risk factors for cognitive decline, additional research is required to establish a causal relationship, particularly given that tinnitus can manifest as a symptom of various underlying medical conditions.

Predictors and consequences of visual trajectories in Chinese older population: A growth mixture model

Background

Given the relatively high prevalence of vision impairment and the heterogeneity of visual changes among the elderly population, we aimed to identify the visual trajectories and to examine the predictors and consequences associated with each trajectory class.

Methods

We analysed data from 2235 participants involved in the 5th, 6th, 7th, and 8th waves of the Chinese Longitudinal Healthy Longevity Survey (CLHLS), where vision impairment was evaluated using an adapted Landolt-C chart during each wave. We employed a growth mixture model (GMM) to identify distinct visual trajectories and logistic regression analysis to examine the predictors associated with each trajectory class. Furthermore, we investigated the effect of visual trajectories on distal consequences, including cognitive function, activities of daily living (ADL), instrumental activities of daily living (IADL), depression, anxiety, and fall risk. Within the CLHLS study, cognitive function was assessed using the Chinese version of the Mini-Mental State Examination (CMMSE), ADL via the Katz index, and IADL through a modified version of Lawton's scale. Lastly, depression was assessed using the 10-item version of the Centre for Epidemiologic Studies (CES-D-10), while anxiety was measured using the Generalized Anxiety Disorder scale (GAD-7). Fall risk was determined by asking the question: 'Have you experienced any falls within the past year?'

Results

We identified two distinct visual trajectories in our analysis. Most older adults (n = 1830, 81.9%) initially had a good vision level that diminished ('high-baseline decline' group). Conversely, the remaining participants (n = 405, 18.1%) initially had a lower vision level that improved over time ('low-baseline improvement' group). The 'high-baseline decline' group was more likely to include older adults with relatively higher body mass index (BMI) (odds ratio (OR) = 1.086; 95% confidence interval (CI) = 1.046, 1.127), individuals with higher formal educational qualifications (OR = 1.411; 95% CI = 1.068, 1.864), those current engaging in exercise (OR = 1.376; 95% CI = 1.046, 1.811), and individuals reporting more frequent consumption of fruit (OR = 1.357; 95% CI = 1.053, 1.749). Conversely, the 'low-baseline improvement' group had a higher likelihood of including older individuals (OR = 0.947; 95% CI = 0.934, 0.961), residents of nursing homes (OR = 0.340; 95% CI = 0.116, 0.993) and those self-reporting cataracts (OR = 0.268; 95% CI = 0.183, 0.391) and glaucoma (OR = 0.157; 95% CI = 0.079, 0.315). Furthermore, the 'high-baseline decline' group showed a positive impact on distal consequences, adjusting for sex, birthplace, residence, main occupation, education, economic status, and marital status. This impact included cognitive function (correlation coefficient (β) = 2.092; 95% CI = 1.272, 2.912), ADL (β  = -0.362; 95% CI = -0.615, -0.108), IADL (β  = -1.712; 95% CI = -2.304, -1.121), and reported lower levels of depression (β  = 0.649; 95% CI = 0.013, 1.285). We observed no significant influence on fall risk and anxiety within the identified visual trajectories in the adjusted model.

Conclusions

Vision in older adults with ocular disease could potentially be improved. Having formal education, maintaining an appropriate BMI, engaging in exercise, and consuming fruit more frequently appear to be beneficial for the visual health of the elderly. Considering the negative impact of visual impairment experience on distal cognition, self-care ability, and depression symptoms, stakeholder should prioritise long-term monitoring and management of vision impairment among older adults.

Prediction of Cognitive Impairment Risk among Older Adults: A Machine Learning-Based Comparative Study and Model Development

INTRODUCTION

The prevalence of cognitive impairment and dementia in the older population is increasing, and thereby, early detection of cognitive decline is essential for effective intervention.

METHODS

This study included 2,288 participants with normal cognitive function from the Ma'anshan Healthy Aging Cohort Study. Forty-two potential predictors, including demographic characteristics, chronic diseases, lifestyle factors, anthropometric indices, physical function, and baseline cognitive function, were selected based on clinical importance and previous research. The dataset was partitioned into training, validation, and test sets in a proportion of 60% for training, 20% for validation, and 20% for testing, respectively. Recursive feature elimination was used for feature selection, followed by six machine learning algorithms that were employed for model development. The performance of the models was evaluated using area under the curve (AUC), specificity, sensitivity, and accuracy. Moreover, SHapley Additive exPlanations (SHAP) was conducted to access the interpretability of the final selected model and to gain insights into the impact of features on the prediction outcomes. SHAP force plots were established to vividly show the application of the prediction model at the individual level.

RESULTS

The final predictive model based on the Naive Bayes algorithm achieved an AUC of 0.820 (95% CI, 0.773-0.887) on the test set, outperforming other algorithms. The top ten influential features in the model included baseline Mini-Mental State Examination (MMSE), education, self-reported economic status, collective or social activities, Pittsburgh sleep quality index (PSQI), body mass index, systolic blood pressure, diastolic blood pressure, instrumental activities of daily living, and age. The model demonstrated the potential to identify individuals at a higher risk of cognitive impairment within 3 years from older adults.

CONCLUSION

The predictive model developed in this study contributes to the early detection of cognitive impairment in older adults by primary healthcare staff in community settings.

Investigating the association between inflammation mediated by mushroom consumption and mild cognitive impairment in Chinese older adults

Background: Chronic inflammatory stimulation is a major risk factor for mild cognitive impairment. Mushroom consumption and inflammatory factors may play an important role in the pathogenesis of mild cognitive impairment. Additionally, consuming mushrooms can reduce the levels of inflammatory cytokines and preserve cognitive function. Therefore, this study aimed to investigate the relationship between mushroom consumption and serum inflammatory cytokines and mild cognitive impairment (MCI). Methods: Binary logistic regression was used to determine the relationship between mushroom consumption and MCI in 550 participants. Subsequently, mediation analysis was used to analyze the relationship between mushroom consumption, inflammatory factors, and the Montreal Cognitive assessment (MoCA) score in 248 participants. Results: Mushroom consumption was associated with MCI (odds ratio = 0.623, 95% confidence interval = 0.542-0.715, P < 0.001). The association between mushroom intake and MCI was mediated by interleukin-6 (IL-6) and hypersensitive C-reactive protein (hs-CRP), and the MoCA score was 12.76% and 47.59%, respectively. Conclusion: A high intake of mushrooms was associated with a low risk of MCI. Serum inflammatory factors including IL-6 and hs-CRP play a partial mediating role between mushroom intake and the MoCA score, and the underlying mechanism needs to be further explored.

Prediction Model for Cognitive Impairment among Disabled Older Adults: A Development and Validation Study

Disabled older adults exhibited a higher risk for cognitive impairment. Early identification is crucial in alleviating the disease burden. This study aims to develop and validate a prediction model for identifying cognitive impairment among disabled older adults. A total of 2138, 501, and 746 participants were included in the development set and two external validation sets. Logistic regression, support vector machine, random forest, and XGBoost were introduced to develop the prediction model. A nomogram was further established to demonstrate the prediction model directly and vividly. Logistic regression exhibited better predictive performance on the test set with an area under the curve of 0.875. It maintained a high level of precision (0.808), specification (0.788), sensitivity (0.770), and F1-score (0.788) compared with the machine learning models. We further simplified and established a nomogram based on the logistic regression, comprising five variables: age, daily living activities, instrumental activity of daily living, hearing impairment, and visual impairment. The areas under the curve of the nomogram were 0.871, 0.825, and 0.863 in the internal and two external validation sets, respectively. This nomogram effectively identifies the risk of cognitive impairment in disabled older adults.

Optimizing the physical activity intervention for older adults with mild cognitive impairment: a factorial randomized trial

Background

Physical activity (PA) intervention is one of the most effective interventions to promote cognitive function of older adults with mild cognitive impairment (MCI). However, the level of PA remains low. Based on the two core interventions (X-CircuiT and health education), this study aimed to examine the effect of three implementation strategies (viz., role modeling, goal-setting, and reminding) on the PA level among older adults with MCI using the multiphase optimization strategy (MOST).

Methods

Participants were randomized into one of eight conditions in a factorial design involving three factors with two levels: (i) role modeling (on vs. off); (ii) goal-setting (on vs. off); and (iii) reminding (on vs. off). The primary outcome was PA level at 12 weeks. The secondary outcomes were cognitive function, self-efficacy, and cost-effectiveness at 12 weeks. The intention-to-treat (ITT) analysis was performed as the main analysis and the per-protocol (PP) analysis as the sensitivity analysis.

Results

A total of 107 participants were included and randomly assigned into three groups, each receiving different implementation strategies. The results of the multivariate regression analysis showed that the three implementation strategies, namely, reminding (B = 0.31, p < 0.01), role modeling (B = 0.21, p < 0.01), and goal-setting (B = 0.19, p < 0.01), could significantly improve PA level. Specifically, it was found that role modeling (B = 0.68, p = 0.03) could significantly improve cognitive function. There were no significant interactions among the three implementation strategies. Role modeling was the most cost-effective strategy, costing 93.41 RMB for one unit of PA.

Conclusions

Role modeling was likely to be the best implementation strategy. The value-based and cost-effective PA intervention package could include the core intervention (X-CircuiT and health education) and implementation strategy (role modeling).

Clinical Trial Registration

https://www.chictr.org.cn, The study was retrospectively registered on 30 June 2022 (ChiCTR2200061693).

Community screening for dementia among older adults in China: a machine learning-based strategy

BACKGROUND

Dementia is a leading cause of disability in people older than 65 years worldwide. However, diagnosing dementia in its earliest symptomatic stages remains challenging. This study combined specific questions from the AD8 scale with comprehensive health-related characteristics, and used machine learning (ML) to construct diagnostic models of cognitive impairment (CI).

METHODS

The study was based on the Shenzhen Healthy Ageing Research (SHARE) project, and we recruited 823 participants aged 65 years and older, who completed a comprehensive health assessment and cognitive function assessments. Permutation importance was used to select features. Five ML models using BalanceCascade were applied to predict CI: a support vector machine (SVM), multilayer perceptron (MLP), AdaBoost, gradient boosting decision tree (GBDT), and logistic regression (LR). An AD8 score ≥ 2 was used to define CI as a baseline. SHapley Additive exPlanations (SHAP) values were used to interpret the results of ML models.

RESULTS

The first and sixth items of AD8, platelets, waist circumference, body mass index, carcinoembryonic antigens, age, serum uric acid, white blood cells, abnormal electrocardiogram, heart rate, and sex were selected as predictive features. Compared to the baseline (AUC = 0.65), the MLP showed the highest performance (AUC: 0.83 ± 0.04), followed by AdaBoost (AUC: 0.80 ± 0.04), SVM (AUC: 0.78 ± 0.04), GBDT (0.76 ± 0.04). Furthermore, the accuracy, sensitivity and specificity of four ML models were higher than the baseline. SHAP summary plots based on MLP showed the most influential feature on model decision for positive CI prediction was female sex, followed by older age and lower waist circumference.

CONCLUSIONS

The diagnostic models of CI applying ML, especially the MLP, were substantially more effective than the traditional AD8 scale with a score of ≥ 2 points. Our findings may provide new ideas for community dementia screening and to promote such screening while minimizing medical and health resources.

Anti-Inflammatory Diet and Protein-Enriched Diet Can Reduce the Risk of Cognitive Impairment among Older Adults: A Nationwide Cross-Sectional Research

BACKGROUND

Cognitive impairment (CI) is a common mental health disorder among older adults, and dietary patterns have an impact on cognitive function. However, no systematic researches have constructed anti-inflammatory diet (AID) and protein-enriched diet (PED) to explore their association with CI among older adults in China.

METHODS

The data used in this study were obtained from the 2018 waves of the China Longitudinal Health and Longevity Survey (CLHLS). We construct AID, PED, and calculate scores for CI. We use binary logistic regression to explore the relationship between them, and use restrictive cubic splines to determine whether the relationships are non-linear. Subgroup analysis and sensitivity analysis were used to demonstrate the robustness of the results.

RESULTS

A total of 8692 participants (mean age is 83.53 years) were included in the analysis. We found that participants with a higher AID (OR = 0.789, 95% confidence interval: 0.740-0.842, p < 0.001) and PED (OR = 0.910, 95% confidence interval: 0.866-0.956, p < 0.001) score showed lower odds of suffering from CI. Besides, the relationship between the two dietary patterns and CI is linear, and the results of subgroup analysis and sensitivity analysis are also significant.

CONCLUSION

Higher intakes of AID and PED are associated with a lower risk of CI among older adults, which has important implications for future prevention and control of CI from a dietary and nutritional perspective.

Data-driven clustering approach to identify novel clusters of high cognitive impairment risk among Chinese community-dwelling elderly people with normal cognition: A national cohort study

Background

Cognitive impairment is a highly heterogeneous disorder that necessitates further investigation into the distinct characteristics of populations at varying risk levels of cognitive impairment. Using a large-scale registry cohort of elderly individuals, we applied a data-driven approach to identify novel clusters based on diverse sociodemographic features.

Methods

A prospective cohort of 6398 elderly people from the Chinese Longitudinal Healthy Longevity Survey, followed between 2008-14, was used to develop and validate the model. Participants were aged ≥60 years, community-dwelling, and the Chinese version of the Mini-Mental State Examination (MMSE) score ≥18 were included. Sixty-nine sociodemographic features were included in the analysis. The total population was divided into two-thirds for the derivation cohort (n = 4265) and one-third for the validation cohort (n = 2133). In the derivation cohort, an unsupervised Gaussian mixture model was applied to categorise participants into distinct clusters. A classifier was developed based on the most important 10 factors and was applied to categorise participants into their corresponding clusters in a validation cohort. The difference in the three-year risk of cognitive impairment was compared across the clusters.

Results

We identified four clusters with distinct features in the derivation cohort. Cluster 1 was associated with the worst life independence, longest sleep duration, and the oldest age. Cluster 2 demonstrated the highest loneliness, characterised by non-marital status and living alone. Cluster 3 was characterised by the lowest sense of loneliness and the highest proportions in marital status and family co-residence. Cluster 4 demonstrated heightened engagement in exercise and leisure activity, along with independent decision-making, hygiene, and a diverse diet. In comparison to Cluster 4, Cluster 1 exhibited the highest three-year cognitive impairment risk (adjusted odds ratio (aOR) = 3.31; 95% confidence interval (CI) = 1.81-6.05), followed by Cluster 2 and Cluster 3 after adjustment for baseline MMSE, residence, sex, age, years of education, drinking, smoking, hypertension, diabetes, heart disease and stroke or cardiovascular diseases.

Conclusions

A data-driven approach can be instrumental in identifying individuals at high risk of cognitive impairment among cognitively normal elderly populations. Based on various sociodemographic features, these clusters can suggest individualised intervention plans.

Identifying and predicting physical limitation and cognitive decline trajectory group of older adults in China: A data-driven machine learning analysis

OBJECTIVE

This study aimed to utilize data-driven machine learning methods to identify and predict potential physical and cognitive function trajectory groups of older adults and determine their crucial factors for promoting active ageing in China.

METHODS

Longitudinal data on 3026 older adults from the Chinese Longitudinal Healthy Longevity and Happy Family Survey was used to identify potential physical and cognitive function trajectory groups using a group-based multi-trajectory model (GBMTM). Predictors were selected from sociodemographic characteristics, lifestyle factors, and physical and mental conditions. The trajectory groups were predicted using data-driven machine learning models and dynamic nomogram. Model performance was evaluated by area under the receiver operating characteristics curve (AUROC), area under the precision-recall curve (PRAUC), and confusion matrix.

RESULTS

Two physical and cognitive function trajectory groups were determined, including a trajectory group with physical limitation and cognitive decline (14.18 %) and a normal trajectory group (85.82 %). Logistic regression performed well in predicting trajectory groups (AUROC = 0.881, PRAUC = 0.649). Older adults with lower baseline score of activities of daily living, older age, less frequent housework, and fewer actual teeth were more likely to experience physical limitation and cognitive decline trajectory group.

LIMITATION

This study didn't carry out external validation.

CONCLUSIONS

This study shows that GBMTM and machine learning models effectively identify and predict physical limitation and cognitive decline trajectory group. The identified predictors might be essential for developing targeted interventions to promote healthy ageing.

Identifying Predictive Risk Factors for Future Cognitive Impairment Among Chinese Older Adults: Longitudinal Prediction Study

Background

The societal burden of cognitive impairment in China has prompted researchers to develop clinical prediction models aimed at making risk assessments that enable preventative interventions. However, it is unclear what types of risk factors best predict future cognitive impairment, if known risk factors make equally accurate predictions across different socioeconomic groups, and if existing prediction models are equally accurate across different subpopulations.

Objective

This paper aimed to identify which domain of health information best predicts future cognitive impairment among Chinese older adults and to examine if discrepancies exist in predictive ability across different population subsets.

Methods

Using data from the Chinese Longitudinal Healthy Longevity Survey, we quantified the ability of demographics, instrumental activities of daily living, activities of daily living, cognitive tests, social factors and hobbies, psychological factors, diet, exercise and sleep, chronic diseases, and 3 recently published logistic regression-based prediction models to predict 3-year risk of cognitive impairment in the general Chinese population and among male, female, rural-dwelling, urban-dwelling, educated, and not formally educated older adults. Predictive ability was quantified using the area under the receiver operating characteristic curve (AUC) and sensitivity-specificity curves through 20 repeats of 10-fold cross-validation.

Results

A total of 4047 participants were included in the study, of which 337 (8.3%) developed cognitive impairment 3 years after baseline data collection. The risk factor groups with the best predictive ability in the general population were demographics (AUC 0.78, 95% CI 0.77-0.78), cognitive tests (AUC 0.72, 95% CI 0.72-0.73), and instrumental activities of daily living (AUC 0.71, 95% CI 0.70-0.71). Demographics, cognitive tests, instrumental activities of daily living, and all 3 recreated prediction models had significantly higher AUCs when making predictions among female older adults compared to male older adults and among older adults with no formal education compared to those with some education.

Conclusions

This study suggests that demographics, cognitive tests, and instrumental activities of daily living are the most useful risk factors for predicting future cognitive impairment among Chinese older adults. However, the most predictive risk factors and existing models have lower predictive power among male, urban-dwelling, and educated older adults. More efforts are needed to ensure that equally accurate risk assessments can be conducted across different socioeconomic groups in China.

A deep learning model for Alzheimer's disease diagnosis based on patient clinical records

BACKGROUND

Dementia, with Alzheimer's disease (AD) being the most common type of this neurodegenerative disease, is an under-diagnosed health problem in older people. The creation of classification models based on AD risk factors using Deep Learning is a promising tool to minimize the impact of under-diagnosis.

OBJECTIVE

To develop a Deep Learning model that uses clinical data from patients with dementia to classify whether they have AD.

METHODS

A Deep Learning model to identify AD in clinical records is proposed. In addition, several rebalancing methods have been used to preprocess the dataset and several studies have been carried out to tune up the model.

RESULTS

Model has been tested against other well-established machine learning techniques, having better results than these in terms of AUC with alpha less than 0.05.

CONCLUSIONS

The developed Neural Network Model has a good performance and can be an accurate assisting tool for AD diagnosis.

Development and validation of prediction model for older adults with cognitive frailty

OBJECTIVE

This study sought to develop and validate a 6-year risk prediction model in older adults with cognitive frailty (CF).

METHODS

In the secondary analysis of Chinese Longitudinal Healthy Longevity Survey (CLHLS), participants from the 2011-2018 cohort were included to develop the prediction model. The CF was assessed by the Chinese version of Mini-Mental State Exam (CMMSE) and the modified Fried criteria. The stepwise regression was used to select predictors, and the logistic regression analysis was conducted to construct the model. The model was externally validated using the temporal validation method via the 2005-2011 cohort. The discrimination was measured by the area under the curve (AUC), and the calibration was measured by the calibration plot. A nomogram was conducted to vividly present the prediction model.

RESULTS

The development dataset included 2420 participants aged 60 years or above, and 243 participants suffered from CF during a median follow-up period of 6.91 years (interquartile range 5.47-7.10 years). Six predictors, namely, age, sex, residence, body mass index (BMI), exercise, and physical disability, were finally used to develop the model. The model performed well with the AUC of 0.830 and 0.840 in the development and external validation datasets, respectively.

CONCLUSION

The study could provide a practical tool to identify older adults with a high risk of CF early. Furthermore, targeting modifiable factors could prevent about half of the new-onset CF during a 6-year follow-up.

Applications of Artificial Intelligence in the Neuropsychological Assessment of Dementia: A Systematic Review

In the context of advancing healthcare, the diagnosis and treatment of cognitive disorders, particularly Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD), pose significant challenges. This review explores Artificial Intelligence (AI) and Machine Learning (ML) in neuropsychological assessment for the early detection and personalized treatment of MCI and AD. The review includes 37 articles that demonstrate that AI could be an useful instrument for optimizing diagnostic procedures, predicting cognitive decline, and outperforming traditional tests. Three main categories of applications are identified: (1) combining neuropsychological assessment with clinical data, (2) optimizing existing test batteries using ML techniques, and (3) employing virtual reality and games to overcome the limitations of traditional tests. Despite advancements, the review highlights a gap in developing tools that simplify the clinician's workflow and underscores the need for explainable AI in healthcare decision making. Future studies should bridge the gap between technical performance measures and practical clinical utility to yield accurate results and facilitate clinicians' roles. The successful integration of AI/ML in predicting dementia onset could reduce global healthcare costs and benefit aging societies.

Clinical study of different prediction models in predicting diabetic nephropathy in patients with type 2 diabetes mellitus

BACKGROUND

Among older adults, type 2 diabetes mellitus (T2DM) is widely recognized as one of the most prevalent diseases. Diabetic nephropathy (DN) is a frequent complication of DM, mainly characterized by renal microvascular damage. Early detection, aggressive prevention, and cure of DN are key to improving prognosis. Establishing a diagnostic and predictive model for DN is crucial in auxiliary diagnosis.

AIM

To investigate the factors that impact T2DM complicated with DN and utilize this information to develop a predictive model.

METHODS

The clinical data of 210 patients diagnosed with T2DM and admitted to the First People's Hospital of Wenling between August 2019 and August 2022 were retrospectively analyzed. According to whether the patients had DN, they were divided into the DN group (complicated with DN) and the non-DN group (without DN). Multivariate logistic regression analysis was used to explore factors affecting DN in patients with T2DM. The data were randomly split into a training set (n = 147) and a test set (n = 63) in a 7:3 ratio using a random function. The training set was used to construct the nomogram, decision tree, and random forest models, and the test set was used to evaluate the prediction performance of the model by comparing the sensitivity, specificity, accuracy, recall, precision, and area under the receiver operating characteristic curve.

RESULTS

Among the 210 patients with T2DM, 74 (35.34%) had DN. The validation dataset showed that the accuracies of the nomogram, decision tree, and random forest models in predicting DN in patients with T2DM were 0.746, 0.714, and 0.730, respectively. The sensitivities were 0.710, 0.710, and 0.806, respectively; the specificities were 0.844, 0.875, and 0.844, respectively; the area under the receiver operating characteristic curve (AUC) of the patients were 0.811, 0.735, and 0.850, respectively. The Delong test results revealed that the AUC values of the decision tree model were lower than those of the random forest and nomogram models (P < 0.05), whereas the difference in AUC values of the random forest and column-line graph models was not statistically significant (P > 0.05).

CONCLUSION

Among the three prediction models, random forest performs best and can help identify patients with T2DM at high risk of DN.

Quality of life and socio-demographic factors associated with nutritional risk in Brazilian community-dwelling individuals aged 80 and over: cluster analysis and ensemble methods

Introduction

The aim of the present study was to use cluster analysis and ensemble methods to evaluate the association between quality of life, socio-demographic factors to predict nutritional risk in community-dwelling Brazilians aged 80 and over.

Methods

This cross-sectional study included 104 individuals, both sexes, from different community locations. Firstly, the participants answered the sociodemographic questionnaire, and were sampled for anthropometric data. Subsequently, the Mini-Mental State Examination (MMSE) was applied, and Mini Nutritional Assessment Questionnaire (MAN) was used to evaluate their nutritional status. Finally, quality of life (QoL) was assessed by a brief version of World Health Organizations' Quality of Life (WHOQOL-BREF) questionnaire and its older adults' version (WHOQOL-OLD).

Results

The K-means algorithm was used to identify clusters of individuals regarding quality-of-life characteristics. In addition, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) algorithms were used to predict nutritional risk. Four major clusters were derived. Although there was a higher proportion of individuals aged 80 and over with nutritional risk in cluster 2 and a lower proportion in cluster 3, there was no statistically significant association. Cluster 1 showed the highest scores for psychological, social, and environmental domains, while cluster 4 exhibited the worst scores for the social and environmental domains of WHOQOL-BREF and for autonomy, past, present, and future activities, and intimacy of WHOQOL-OLD.

Conclusion

Handgrip, household income, and MMSE were the most important predictors of nutritional. On the other hand, sex, self-reported health, and number of teeth showed the lowest levels of influence in the construction of models to evaluate nutritional risk. Taken together, there was no association between clusters based on quality-of-life domains and nutritional risk, however, predictive models can be used as a complementary tool to evaluate nutritional risk in individuals aged 80 and over.

What's New in Dementia Risk Prediction Modelling? An Updated Systematic Review

Introduction

Identifying individuals at high risk of dementia is critical to optimized clinical care, formulating effective preventative strategies, and determining eligibility for clinical trials. Since our previous systematic reviews in 2010 and 2015, there has been a surge in dementia risk prediction modelling. The aim of this study was to update our previous reviews to explore, and critically review, new developments in dementia risk modelling.

Methods

MEDLINE, Embase, Scopus, and Web of Science were searched from March 2014 to June 2022. Studies were included if they were population- or community-based cohorts (including electronic health record data), had developed a model for predicting late-life incident dementia, and included model performance indices such as discrimination, calibration, or external validation.

Results

In total, 9,209 articles were identified from the electronic search, of which 74 met the inclusion criteria. We found a substantial increase in the number of new models published from 2014 (>50 new models), including an increase in the number of models developed using machine learning. Over 450 unique predictor (component) variables have been tested. Nineteen studies (26%) undertook external validation of newly developed or existing models, with mixed results. For the first time, models have also been developed in low- and middle-income countries (LMICs) and others validated in racial and ethnic minority groups.

Conclusion

The literature on dementia risk prediction modelling is rapidly evolving with new analytical developments and testing in LMICs. However, it is still challenging to make recommendations about which one model is the most suitable for routine use in a clinical setting. There is an urgent need to develop a suitable, robust, validated risk prediction model in the general population that can be widely implemented in clinical practice to improve dementia prevention.

Online interpretable dynamic prediction models for postoperative delirium after cardiac surgery under cardiopulmonary bypass developed based on machine learning algorithms: A retrospective cohort study

OBJECTIVE

Postoperative delirium (POD) is strongly associated with poor early and long-term prognosis in cardiac surgery patients with cardiopulmonary bypass (CPB). This study aimed to develop dynamic prediction models for POD after cardiac surgery under CPB using machine learning (ML) algorithms.

METHODS

From July 2021 to June 2022, clinical data were collected from patients undergoing cardiac surgery under CPB at Nanjing First Hospital. A dataset from the same center (October 2022 to November 2022) was also used for temporal external validation. We used ML and deep learning to build models in the training set, optimized parameters in the test set, and finally validated the best model in the validation set. The SHapley Additive exPlanations (SHAP) method was introduced to explain the best models.

RESULTS

Of the 885 patients enrolled, 221 (25.0%) developed POD. 22 (22.0%) of 100 validation cohort patients developed POD. The preoperative and postoperative artificial neural network (ANN) models exhibited optimal performance. The validation results demonstrated satisfactory predictive performance of the ANN model, with area under the receiver operator characteristic curve (AUROC) values of 0.776 and 0.684 for the preoperative and postoperative models, respectively. Based on the ANN algorithm, we constructed dynamic, highly accurate, and interpretable web risk calculators for POD.

CONCLUSIONS

We successfully developed online interpretable dynamic ANN models as clinical decision aids to identify patients at high risk of POD before and after cardiac surgery to facilitate early intervention or care.