Selecting the most important self-assessed features for predicting conversion to mild cognitive impairment with random forest and permutation-based methods

Development and interpretation of a pathomics-driven ensemble model for predicting the response to immunotherapy in gastric cancer

BACKGROUND

Only a subset of patients with gastric cancer experience long-term benefits from immune checkpoint inhibitors (ICIs). Currently, there is a deficiency in precise predictive biomarkers for ICI efficacy. The aim of this study was to develop and validate a pathomics-driven ensemble model for predicting the response to ICIs in gastric cancer, using H&E-stained whole slide images (WSI).

METHODS

This multicenter study retrospectively collected and analyzed H&E-stained WSIs and clinical data from 584 patients with gastric cancer. An ensemble model, integrating four classifiers: least absolute shrinkage and selection operator, k-nearest neighbors, decision trees, and random forests, was developed and validated using pathomics features, with the objective of predicting the therapeutic efficacy of immune checkpoint inhibition. Model performance was evaluated using metrics including the area under the curve (AUC), sensitivity, and specificity. Additionally, SHAP (SHapley Additive exPlanations) analysis was used to explain the model's predicted values as the sum of the attribution values for each input feature. Pathogenomics analysis was employed to explain the molecular mechanisms underlying the model's predictions.

RESULTS

Our pathomics-driven ensemble model effectively stratified the response to ICIs in training cohort (AUC 0.985 (95% CI 0.971 to 0.999)), which was further validated in internal validation cohort (AUC 0.921 (95% CI 0.839 to 0.999)), as well as in external validation cohort 1 (AUC 0.914 (95% CI 0.837 to 0.990)), and external validation cohort 2 (0.927 (95% CI 0.802 to 0.999)). The univariate Cox regression analysis revealed that the prediction signature of pathomics-driven ensemble model was a prognostic factor for progression-free survival in patients with gastric cancer who underwent immunotherapy (p<0.001, HR 0.35 (95% CI 0.24 to 0.50)), and remained an independent predictor after multivariable Cox regression adjusted for clinicopathological variables, (including sex, age, carcinoembryonic antigen, carbohydrate antigen 19-9, therapy regime, line of therapy, differentiation, location and programmed death ligand 1 (PD-L1) expression in all patients (p<0.001, HR 0.34 (95% CI 0.24 to 0.50)). Pathogenomics analysis suggested that the ensemble model is driven by molecular-level immune, cancer, metabolism-related pathways, and was correlated with the immune-related characteristics, including immune score, Estimation of STromal and Immune cells in MAlignant Tumor tissues using Expression data score, and tumor purity.

CONCLUSIONS

Our pathomics-driven ensemble model exhibited high accuracy and robustness in predicting the response to ICIs using WSIs. Therefore, it could serve as a novel and valuable tool to facilitate precision immunotherapy.

Different acupuncture and moxibustion therapies for mild cognitive impairment: a network meta-analysis

OBJECTIVE

To investigate the effectiveness of different acupuncture and moxibustion therapies in improving cognitive function in patients with mild cognitive impairment (MCI) to determine the optimal approach. This study aims to provide insights into the treatment of MCI patients for future randomized controlled trials (RCTs) and clinical decision-making.

MATERIALS AND METHODS

RCT studies were retrieved from databases including PubMed, Embase, Cochrane Library, Web of Science, CNKI, WANFANG, VIP, and SinoMed. The Cochrane risk of bias tool was used to assess the risk of bias for eligible trials. Bayesian network meta-analysis was conducted using R4.2.3 software.

RESULTS

A total of 46 RCTs with 3641 participants were included. The network meta-analysis showed that acupoint pressing + cognitive training + auricular point sticking, massage + western medicine treatment, and electroacupuncture + western medicine treatment ranked first, second, and third in improving MMSE score, respectively. Acupoint pressing + cognitive training, cognitive training + scalp acupuncture, and cognitive training + moxibustion ranked first, second, and third in improving MoCA score, respectively.

CONCLUSION

This study showed that acupoint pressing alone or acupoint pressing + auricular point sticking may improve cognitive function in MCI patients and possibly be the most effective acupuncture interventions for the treatment of MCI.

Comparison of the diagnostic accuracy of resting-state fMRI driven machine learning algorithms in the detection of mild cognitive impairment

Mild cognitive impairment (MCI) is a potential therapeutic window in the prevention of dementia; however, automated detection of early cognitive deterioration is an unresolved issue. The aim of our study was to compare various classification approaches to differentiate MCI patients from healthy controls, based on rs-fMRI data, using machine learning (ML) algorithms. Own dataset (from two centers) and ADNI database were used during the analysis. Three fMRI parameters were applied in five feature selection algorithms: local correlation, intrinsic connectivity, and fractional amplitude of low frequency fluctuations. Support vector machine (SVM) and random forest (RF) methods were applied for classification. We achieved a relatively wide range of 78-87% accuracy for the various feature selection methods with SVM combining the three rs-fMRI parameters. In the ADNI datasets case we can also see even 90% accuracy scores. RF provided a more harmonized result among the feature selection algorithms in both datasets with 80-84% accuracy for our local and 74-82% for the ADNI database. Despite some lower performance metrics of some algorithms, most of the results were positive and could be seen in two unrelated datasets which increase the validity of our methods. Our results highlight the potential of ML-based fMRI applications for automated diagnostic techniques to recognize MCI patients.

Machine learning analyses identify multi-modal frailty factors that selectively discriminate four cohorts in the Alzheimer's disease spectrum: a COMPASS-ND study

BACKGROUND

Frailty indicators can operate in dynamic amalgamations of disease conditions, clinical symptoms, biomarkers, medical signals, cognitive characteristics, and even health beliefs and practices. This study is the first to evaluate which, among these multiple frailty-related indicators, are important and differential predictors of clinical cohorts that represent progression along an Alzheimer's disease (AD) spectrum. We applied machine-learning technology to such indicators in order to identify the leading predictors of three AD spectrum cohorts; viz., subjective cognitive impairment (SCI), mild cognitive impairment (MCI), and AD. The common benchmark was a cohort of cognitively unimpaired (CU) older adults.

METHODS

The four cohorts were from the cross-sectional Comprehensive Assessment of Neurodegeneration and Dementia dataset. We used random forest analysis (Python 3.7) to simultaneously test the relative importance of 83 multi-modal frailty indicators in discriminating the cohorts. We performed an explainable artificial intelligence method (Tree Shapley Additive exPlanation values) for deep interpretation of prediction effects.

RESULTS

We observed strong concurrent prediction results, with clusters varying across cohorts. The SCI model demonstrated excellent prediction accuracy (AUC = 0.89). Three leading predictors were poorer quality of life ([QoL]; memory), abnormal lymphocyte count, and abnormal neutrophil count. The MCI model demonstrated a similarly high AUC (0.88). Five leading predictors were poorer QoL (memory, leisure), male sex, abnormal lymphocyte count, and poorer self-rated eyesight. The AD model demonstrated outstanding prediction accuracy (AUC = 0.98). Ten leading predictors were poorer QoL (memory), reduced olfaction, male sex, increased dependence in activities of daily living (n = 6), and poorer visual contrast.

CONCLUSIONS

Both convergent and cohort-specific frailty factors discriminated the AD spectrum cohorts. Convergence was observed as all cohorts were marked by lower quality of life (memory), supporting recent research and clinical attention to subjective experiences of memory aging and their potentially broad ramifications. Diversity was displayed in that, of the 14 leading predictors extracted across models, 11 were selectively sensitive to one cohort. A morbidity intensity trend was indicated by an increasing number and diversity of predictors corresponding to clinical severity, especially in AD. Knowledge of differential deficit predictors across AD clinical cohorts may promote precision interventions.

Artificial intelligence for dementia research methods optimization

Artificial intelligence (AI) and machine learning (ML) approaches are increasingly being used in dementia research. However, several methodological challenges exist that may limit the insights we can obtain from high-dimensional data and our ability to translate these findings into improved patient outcomes. To improve reproducibility and replicability, researchers should make their well-documented code and modeling pipelines openly available. Data should also be shared where appropriate. To enhance the acceptability of models and AI-enabled systems to users, researchers should prioritize interpretable methods that provide insights into how decisions are generated. Models should be developed using multiple, diverse datasets to improve robustness, generalizability, and reduce potentially harmful bias. To improve clarity and reproducibility, researchers should adhere to reporting guidelines that are co-produced with multiple stakeholders. If these methodological challenges are overcome, AI and ML hold enormous promise for changing the landscape of dementia research and care. HIGHLIGHTS: Machine learning (ML) can improve diagnosis, prevention, and management of dementia. Inadequate reporting of ML procedures affects reproduction/replication of results. ML models built on unrepresentative datasets do not generalize to new datasets. Obligatory metrics for certain model structures and use cases have not been defined. Interpretability and trust in ML predictions are barriers to clinical translation.

Dementia prediction in the general population using clinically accessible variables: a proof-of-concept study using machine learning. The AGES-Reykjavik study

BACKGROUND

Early identification of dementia is crucial for prompt intervention for high-risk individuals in the general population. External validation studies on prognostic models for dementia have highlighted the need for updated models. The use of machine learning in dementia prediction is in its infancy and may improve predictive performance. The current study aimed to explore the difference in performance of machine learning algorithms compared to traditional statistical techniques, such as logistic and Cox regression, for prediction of all-cause dementia. Our secondary aim was to assess the feasibility of only using clinically accessible predictors rather than MRI predictors.

METHODS

Data are from 4,793 participants in the population-based AGES-Reykjavik Study without dementia or mild cognitive impairment at baseline (mean age: 76 years, % female: 59%). Cognitive, biometric, and MRI assessments (total: 59 variables) were collected at baseline, with follow-up of incident dementia diagnoses for a maximum of 12 years. Machine learning algorithms included elastic net regression, random forest, support vector machine, and elastic net Cox regression. Traditional statistical methods for comparison were logistic and Cox regression. Model 1 was fit using all variables and model 2 was after feature selection using the Boruta package. A third model explored performance when leaving out neuroimaging markers (clinically accessible model). Ten-fold cross-validation, repeated ten times, was implemented during training. Upsampling was used to account for imbalanced data. Tuning parameters were optimized for recalibration automatically using the caret package in R.

RESULTS

19% of participants developed all-cause dementia. Machine learning algorithms were comparable in performance to logistic regression in all three models. However, a slight added performance was observed in the elastic net Cox regression in the third model (c = 0.78, 95% CI: 0.78-0.78) compared to the traditional Cox regression (c = 0.75, 95% CI: 0.74-0.77).

CONCLUSIONS

Supervised machine learning only showed added benefit when using survival techniques. Removing MRI markers did not significantly worsen our model's performance. Further, we presented the use of a nomogram using machine learning methods, showing transportability for the use of machine learning models in clinical practice. External validation is needed to assess the use of this model in other populations. Identifying high-risk individuals will amplify prevention efforts and selection for clinical trials.

Using machine learning to identify patient characteristics to predict mortality of in-patients with COVID-19 in south Florida

Introduction

The SARS-CoV-2 (COVID-19) pandemic has created substantial health and economic burdens in the US and worldwide. As new variants continuously emerge, predicting critical clinical events in the context of relevant individual risks is a promising option for reducing the overall burden of COVID-19. This study aims to train an AI-driven decision support system that helps build a model to understand the most important features that predict the "mortality" of patients hospitalized with COVID-19.

Methods

We conducted a retrospective analysis of "5,371" patients hospitalized for COVID-19-related symptoms from the South Florida Memorial Health Care System between March 14th, 2020, and January 16th, 2021. A data set comprising patients' sociodemographic characteristics, pre-existing health information, and medication was analyzed. We trained Random Forest classifier to predict "mortality" for patients hospitalized with COVID-19.

Results

Based on the interpretability of the model, age emerged as the primary predictor of "mortality", followed by diarrhea, diabetes, hypertension, BMI, early stages of kidney disease, smoking status, sex, pneumonia, and race in descending order of importance. Notably, individuals aged over 65 years (referred to as "older adults"), males, Whites, Hispanics, and current smokers were identified as being at higher risk of death. Additionally, BMI, specifically in the overweight and obese categories, significantly predicted "mortality". These findings indicated that the model effectively learned from various categories, such as patients' sociodemographic characteristics, pre-hospital comorbidities, and medications, with a predominant focus on characterizing pre-hospital comorbidities. Consequently, the model demonstrated the ability to predict "mortality" with transparency and reliability.

Conclusion

AI can potentially provide healthcare workers with the ability to stratify patients and streamline optimal care solutions when time is of the essence and resources are limited. This work sets the platform for future work that forecasts patient responses to treatments at various levels of disease severity and assesses health disparities and patient conditions that promote improved health care in a broader context. This study contributed to one of the first predictive analyses applying AI/ML techniques to COVID-19 data using a vast sample from South Florida.

Machine learning-based identification and related features of depression in patients with diabetes mellitus based on the Korea National Health and Nutrition Examination Survey: A cross-sectional study

Patients with diabetes mellitus (DM) are twice as likely as nondiabetic individuals to develop depression, which is a prevalent but often undiagnosed psychiatric comorbidity. Patients with DM who are depressed have poor glycemic control, worse quality of life, increased risk of diabetic complications, and higher mortality rate. The present study aimed to develop machine learning (ML) models that identify depression in patients with DM, determine the best performing model by evaluating multiple ML algorithms, and investigate features related to depression. We developed six ML models, including random forest, K-nearest neighbor, support vector machine (SVM), Adaptive Boosting, light gradient-boosting machine, and Extreme Gradient Boosting, based on the Korea National Health and Nutrition Examination Survey. The results showed that the SVM model performed well, with a cross-validated area under the receiver operating characteristic curve of 0.835 (95% confidence interval [CI] = 0.730-0.901). Thirteen features were related to depression in patients with DM. Permutation feature importance showed that the most important feature was subjective health status, followed by level of general stress awareness; stress recognition rate; average monthly income; triglyceride (mg/dL) level; activity restriction status; European quality of life (EuroQoL): usual activity and lying in a sickbed in the past 1 month; EuroQoL: pain / discomfort, self-care, and physical discomfort in the last 2 weeks; and EuroQoL: mobility and chewing problems. The current findings may offer clinicians a better understanding of the relationship between DM and depression using ML approaches and may be an initial step toward developing a more predictive model for the early detection of depressive symptoms in patients with DM.

Artificial Intelligence for Dementia Research Methods Optimization

INTRODUCTION

Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater.

METHODS

We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research.

RESULTS

We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future.

DISCUSSION

ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.

Association of nonpharmacological interventions for cognitive function in older adults with mild cognitive impairment: a systematic review and network meta-analysis

BACKGROUND

Understanding the effectiveness of nonpharmacological interventions to improve cognitive function in older adults with MCI and identifying the best intervention may help inform ideas for future RCT studies and clinical decision-making.

AIM

The main focus of this study was to assess the comparative effectiveness of nonpharmacological interventions on cognitive function in older adults with MCI and to rank the interventions.

METHODS

RCT studies until September 2022 were searched from six databases, including PubMed, the Cochrane Library, Embase, Web of Science, PsycINFO and CINAHL. The risk of bias in eligible trials was evaluated using the Cochrane Risk of Bias tool. Both pairwise and network meta-analyses were used, and pooled effect sizes were reported using SMD and the corresponding 95% confidence intervals.

RESULTS

A total of 28 RCT studies were included in this study, pooling 18 categories of nonpharmacological interventions. MBE (mind-body exercise) (SMD (standard mean difference): 0.24, 95% CI: 0.08-0.41, P = 0.004), DTE (dual-task exercise) (SMD: 0.61, 95% CI: 0.09-1.13, P = 0.02), PE (physical exercise) (SMD: 0.58, 95% CI: 0.04-1.12, P = 0.03) may be effective in improving cognitive function in older adults with MCI. Acupressure + CT (cognitive training) was the top-ranked intervention among all interventions. No greater benefits of MA (mindful awareness) on cognitive function were found.

CONCLUSIONS

Overall, nonpharmacological interventions significantly improved cognitive function in older adults with MCI. Acupressure + CT(cognitive training) was the most effective intervention for managing cognitive impairment. Future studies with high quality and large sample size RCT studies are needed to confirm our results.

Dimensionality reduction and ensemble of LSTMs for antimicrobial resistance prediction

Bacterial resistance to antibiotics has been rapidly increasing, resulting in low antibiotic effectiveness even treating common infections. The presence of resistant pathogens in environments such as a hospital Intensive Care Unit (ICU) exacerbates the critical admission-acquired infections. This work focuses on the prediction of antibiotic resistance in Pseudomonas aeruginosa nosocomial infections at the ICU, using Long Short-Term Memory (LSTM) artificial neural networks as the predictive method. The analyzed data were extracted from the Electronic Health Records (EHR) of patients admitted to the University Hospital of Fuenlabrada from 2004 to 2019 and were modeled as Multivariate Time Series. A data-driven dimensionality reduction method is built by adapting three feature importance techniques from the literature to the considered data and proposing an algorithm for selecting the most appropriate number of features. This is done using LSTM sequential capabilities so that the temporal aspect of features is taken into account. Furthermore, an ensemble of LSTMs is used to reduce the variance in performance. Our results indicate that the patient's admission information, the antibiotics administered during the ICU stay, and the previous antimicrobial resistance are the most important risk factors. Compared to other conventional dimensionality reduction schemes, our approach is able to improve performance while reducing the number of features for most of the experiments. In essence, the proposed framework achieve, in a computationally cost-efficient manner, promising results for supporting decisions in this clinical task, characterized by high dimensionality, data scarcity, and concept drift.

Using Machine Learning to Predict Cognitive Impairment Among Middle-Aged and Older Chinese: A Longitudinal Study

Objective: To explore the predictive value of machine learning in cognitive impairment, and identify important factors for cognitive impairment. Methods: A total of 2,326 middle-aged and elderly people completed questionnaire, and physical examination evaluation at baseline, Year 2, and Year 4 follow-ups. A random forest machine learning (ML) model was used to predict the cognitive impairment at Year 2 and Year 4 longitudinally. Based on Year 4 cross-sectional data, the same method was applied to establish a prediction model and verify its longitudinal prediction accuracy for cognitive impairment. Meanwhile, the ability of random forest and traditional logistic regression model to longitudinally predict 2-year and 4-year cognitive impairment was compared. Results: Random forest models showed high accuracy for all outcomes at Year 2, Year 4, and cross-sectional Year 4 [AUC = 0.81, 0.79, 0.80] compared with logistic regression [AUC = 0.61, 0.62, 0.70]. Baseline physical examination (e.g., BMI, Blood pressure), biomarkers (e.g., cholesterol), functioning (e.g., functional limitations), demography (e.g., age), and emotional status (e.g., depression) characteristics were identified as the top ten important predictors of cognitive impairment. Conclusion: ML algorithms could enhance the prediction of cognitive impairment among the middle-aged and older Chinese for 4 years and identify essential risk markers.

A Machine Learning Approach for Early Diagnosis of Cognitive Impairment Using Population-Based Data

BACKGROUND

The major mechanisms of dementia and cognitive impairment are vascular and neurodegenerative processes. Early diagnosis of cognitive impairment can facilitate timely interventions to mitigate progression.

OBJECTIVE

This study aims to develop a reliable machine learning (ML) model using socio-demographics, vascular risk factors, and structural neuroimaging markers for early diagnosis of cognitive impairment in a multi-ethnic Asian population.

METHODS

The study consisted of 911 participants from the Epidemiology of Dementia in Singapore study (aged 60- 88 years, 49.6% male). Three ML classifiers, logistic regression, support vector machine, and gradient boosting machine, were developed. Prediction results of independent classifiers were combined in a final ensemble model. Model performances were evaluated on test data using F1 score and area under the receiver operating curve (AUC) methods. Post modelling, SHapely Additive exPlanation (SHAP) was applied on the prediction results to identify the predictors that contribute most to the cognitive impairment prediction.

FINDINGS

The final ensemble model achieved a F1 score and AUC of 0.87 and 0.80 respectively. Accuracy (0.83), sensitivity (0.86), specificity (0.74) and predictive values (positive 0.88 negative 0.72) of the ensemble model were higher compared to the independent classifiers. Age, ethnicity, highest education attainment and neuroimaging markers were identified as important predictors of cognitive impairment.

CONCLUSION

This study demonstrates the feasibility of using ML tools to integrate multiple domains of data for reliable diagnosis of early cognitive impairment. The ML model uses easy-to-obtain variables and is scalable for screening individuals with a high risk of developing dementia in a population-based setting.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 2-Data From Nonwearables

OBJECTIVES

Despite the increasing interest in applying machine learning (ML) methods in health economics and outcomes research (HEOR), stakeholders face uncertainties in when and how ML can be used. We reviewed the recent applications of ML in HEOR.

METHODS

We searched PubMed for studies published between January 2020 and March 2021 and randomly chose 20% of the identified studies for the sake of manageability. Studies that were in HEOR and applied an ML technique were included. Studies related to wearable devices were excluded. We abstracted information on the ML applications, data types, and ML methods and analyzed it using descriptive statistics.

RESULTS

We retrieved 805 articles, of which 161 (20%) were randomly chosen. Ninety-two of the random sample met the eligibility criteria. We found that ML was primarily used for predicting future events (86%) rather than current events (14%). The most common response variables were clinical events or disease incidence (42%) and treatment outcomes (22%). ML was less used to predict economic outcomes such as health resource utilization (16%) or costs (3%). Although electronic medical records (35%) were frequently used for model development, claims data were used less frequently (9%). Tree-based methods (eg, random forests and boosting) were the most commonly used ML methods (31%).

CONCLUSIONS

The use of ML techniques in HEOR is growing rapidly, but there remain opportunities to apply them to predict economic outcomes, especially using claims databases, which could inform the development of cost-effectiveness models.

Machine learning modelling of a membrane capacitive deionization (MCDI) system for prediction of long-term system performance and optimization of process control parameters in remote brackish water desalination

Membrane Capacitive Deionization (MCDI) is a promising electrochemical technique for water desalination. Previous studies have confirrmed the effectiveness of MCDI in removing contaminants from brackish groundwaters, especially in remote areas where electricity is scarce. However, as with other water treatment technologies, performance deterioration of the MCDI system still occurs, hindering the stability of long-term operation. Herein, a machine learning (ML) modelling framework and various ML models were developed to (i) investigate the performance deterioration due particularly to insufficient charging/discharging of the electrode caused by accumulation of ions and electrode scaling and (ii) optimise MCDI operating parameters such that the impacts of these deleterious effects on unit performance were minimized. The ML models developed in this work exhibited a prediction accuracy of cycle time with average mean absolute percentage error (MAPE) values of 16.82% and 16.09% after 30-fold cross validation for Random Forest (RF) and Multilayer Perceptron (MLP) models respectively. The pre-trained ML model predicted different declining trends of water production for two different operating conditions and provided corresponding recommendations on frequencies of chemical cleaning. A case study on the adjustment of operating parameters using the results suggested by the optimization ML model was conducted. The model validation results showed that the overall water production and water recovery of the system using the cycle-based optimized process control parameters (SCN 1) exceeds the MCDI system performance under three fixed parameter settings that were used at each stage of SCN 1 by 1.78% to 4.48% and 2.95% to 9.46%, respectively. Permutation-based and Shapley additive explanation (SHAP) coefficients were also employed for variable importance (VIMP) analysis to uncover the "black-box" nature of the ML models and to better understand the various features' contributions to overall MCDI system performance.

Different item characteristics of a mild cognitive impairment screening tool in the community-based Yilan Study: application of the item response theory

BACKGROUND

This study aimed to use item response theory (IRT) to explore the item-by-item characteristics of a mild cognitive impairment (MCI) screening tool using community-based data.

METHODS

The Yilan Study is a community-based study that has been conducted since 2012. Until March 2020, 2230 older adults were interviewed according to the household registration data. IRT was applied to determine the item-by-item distinctive characteristics of the Eight-item Interview to Differentiate Aging and Dementia (AD8).

RESULTS

The MCI characteristics in the AD8 items have varying degrees of item response threshold. In all circumstances, item AD8-8, which is related to self-rated memory ability, had a low item response threshold. AD8-5 and AD8-7, which are related to the comparisons of time-oriented functional status, had slightly lower thresholds, especially for those aged 65-79 years or without activity limitations. Conversely, AD8-1, AD8-2, AD8-3, AD8-4, and AD8-6 had similar item response thresholds and discriminative power; these items have more detailed functional descriptions or examples for illustration.

CONCLUSIONS

Concise and understandable elements are often expected in community-based screening tools. For community-based health screening and population empowerment in the early detection of MCI, assessment tool items with detailed functional descriptions and examples for illustration have similar validities in most of the population. Items related to self-rated memory ability might be less valid. More examples may be needed for items constructed for comparing time-oriented functional status, especially in extremely old adults and individuals with activity limitations.

Discriminating Aging Cognitive Decline Spectrum Using PET and Magnetic Resonance Image Features

Background: The population aging increased the prevalence of brain diseases, like Alzheimer’s disease (AD), and early identification of individuals with higher odds of cognitive decline is essential to maintain quality of life. Imaging evaluation of individuals at risk of cognitive decline includes biomarkers extracted from brain positron emission tomography (PET) and structural magnetic resonance imaging (MRI). Objective: We propose investigating ensemble models to classify groups in the aging cognitive decline spectrum by combining features extracted from single imaging modalities and combinations of imaging modalities (FDG+AMY+MRI, and a PET ensemble). Methods: We group imaging data of 131 individuals into four classes related to the individuals’ cognitive assessment in baseline and follow-up: stable cognitive non-impaired; individuals converting to mild cognitive impairment (MCI) syndrome; stable MCI; and Alzheimer’s clinical syndrome. We assess the performance of four algorithms using leave-one-out cross-validation: decision tree classifier, random forest (RF), light gradient boosting machine (LGBM), and categorical boosting (CAT). The performance analysis of models is evaluated using balanced accuracy before and after using Shapley Additive exPlanations with recursive feature elimination (SHAP-RFECV) method. Results: Our results show that feature selection with CAT or RF algorithms have the best overall performance in discriminating early cognitive decline spectrum mainly using MRI imaging features. Conclusion: Use of CAT or RF algorithms with SHAP-RFECV shows good discrimination of early stages of aging cognitive decline, mainly using MRI image features. Further work is required to analyze the impact of selected brain regions and their correlation with cognitive decline spectrum.

A Study of Dementia Prediction Models Based on Machine Learning with Survey Data of Community-Dwelling Elderly People in China

BACKGROUND

For community-dwelling elderly individuals without enough clinical data, it is important to develop a method to predict their dementia risk and identify risk factors for the formulation of reasonable public health policies to prevent dementia.

OBJECTIVE

A community elderly survey data was used to establish machine learning prediction models for dementia and analyze the risk factors.

METHODS

In a cluster-sample community survey of 9,387 elderly people in 5 subdistricts of Wuxi City, data on sociodemographics and neuropsychological self-rating scales for depression, anxiety, and cognition evaluation were collected. Machine learning models were developed to predict their dementia risk and identify risk factors.

RESULTS

The random forest model (AUC = 0.686) had slightly better dementia prediction performance than logistic regression model (AUC = 0.677) and neural network model (AUC = 0.664). The sociodemographic data and psychological evaluation revealed that depression (OR = 3.933, 95% CI = 2.995-5.166); anxiety (OR = 2.352, 95% CI = 1.577-3.509); multiple physical diseases (OR = 2.486, 95% CI = 1.882-3.284 for three or above); "disability, poverty or no family member" (OR = 1.859, 95% CI = 1.337-2.585) and "empty nester" (OR = 1.339, 95% CI = 1.125-1.595) in special family status; "no spouse now" (OR = 1.567, 95% CI = 1.118-2.197); age older than 80 years (OR = 1.645, 95% CI = 1.335-2.026); and female (OR = 1.214, 95% CI = 1.048-1.405) were risk factors for suspected dementia, while a higher education level (OR = 0.365, 95% CI = 0.245-0.546 for college or above) was a protective factor.

CONCLUSION

The machine learning models using sociodemographic and psychological evaluation data from community surveys can be used as references for the prevention and control of dementia in large-scale community populations and the formulation of public health policies.

Influence of Selected Environmental Factors on Diatom β Diversity (Bacillariophyta) and the Value of Diatom Indices and Sampling Issues

Human impacts and environmental climate changes have led to a progressive decline in the diversity of diatoms in lakes in the recent past. The components of β diversity (e.g., species turnover and nestedness) and underlying factors are still poorly understood. Here, we report an investigation of two alternative approaches—beta diversity (β diversity) partitioning and local contribution to β diversity (LCBD)—including their responses to selected environmental factors and representativeness of samples in estimating the ecological fitness of a lake. The β diversity of diatoms and their local contributions could be explained by the effects of environmental variables (p < 0.01). The random forest method showed the most contribution to the variance for NO3−, Cl−, and SO42−. PERMANOVA as well as a network analysis in JASP (Jeffrey’s Amazing Statistics Program) showed significant differences between the seasons in diatom assemblages and in the diatom index for Polish lakes (IOJ). Our findings provide insights into the mechanisms responsible for community organizations along environmental gradients from the perspective of β diversity components, and mechanisms of the indication value of diatoms for lakes; the results could be used especially by countries implementing ecological assessments.

Channels and Features Identification: A Review and a Machine-Learning Based Model With Large Scale Feature Extraction for Emotions and ASD Classification

Autism Spectrum Disorder (ASD) is characterized by impairments in social and cognitive skills, emotional disorders, anxiety, and depression. The prolonged conventional ASD diagnosis raises the sheer need for early meaningful intervention. Recently different works have proposed potential for ASD diagnosis and intervention through emotions prediction using deep neural networks (DNN) and machine learning algorithms. However, these systems lack an extensive large-scale feature extraction (LSFE) analysis through multiple benchmark data sets. LSFE analysis is required to identify and utilize the most relevant features and channels for emotion recognition and ASD prediction. Considering these challenges, for the first time, we have analyzed and evaluated an extensive feature set to select the optimal features using LSFE and feature selection algorithms (FSA). A set of up to eight most suitable channels was identified using different best-case FSA. The subject-wise importance of channels and features is also identified. The proposed method provides the best-case accuracies, precision, and recall of 95, 92, and 90%, respectively, for emotions prediction using a linear support vector machine (LSVM) classifier. It also provides the best-case accuracy, precision, and recall of 100% for ASD classification. This work utilized the largest number of benchmark data sets (5) and subjects (99) for validation reported till now in the literature. The LSVM classification algorithm proposed and utilized in this work has significantly lower complexity than the DNN, convolutional neural network (CNN), Naïve Bayes, and dynamic graph CNN used in recent ASD and emotion prediction systems.

Dynamic ensemble prediction of cognitive performance in spaceflight

During spaceflight, astronauts face a unique set of stressors, including microgravity, isolation, and confinement, as well as environmental and operational hazards. These factors can negatively impact sleep, alertness, and neurobehavioral performance, all of which are critical to mission success. In this paper, we predict neurobehavioral performance over the course of a 6-month mission aboard the International Space Station (ISS), using ISS environmental data as well as self-reported and cognitive data collected longitudinally from 24 astronauts. Neurobehavioral performance was repeatedly assessed via a 3-min Psychomotor Vigilance Test (PVT-B) that is highly sensitive to the effects of sleep deprivation. To relate PVT-B performance to time-varying and discordantly-measured environmental, operational, and psychological covariates, we propose an ensemble prediction model comprising of linear mixed effects, random forest, and functional concurrent models. An extensive cross-validation procedure reveals that this ensemble outperforms any one of its components alone. We also identify the most important predictors of PVT-B performance, which include an individual's previous PVT-B performance, reported fatigue and stress, and temperature and radiation dose. This method is broadly applicable to settings where the main goal is accurate, individualized prediction of human behavior involving a mixture of person-level traits and irregularly measured time series.

Prediction of Chronological Age in Healthy Elderly Subjects with Machine Learning from MRI Brain Segmentation and Cortical Parcellation

Normal aging is associated with changes in volumetric indices of brain atrophy. A quantitative understanding of age-related brain changes can shed light on successful aging. To investigate the effect of age on global and regional brain volumes and cortical thickness, 3514 magnetic resonance imaging scans were analyzed using automated brain segmentation and parcellation methods in elderly healthy individuals (69–88 years of age). The machine learning algorithm extreme gradient boosting (XGBoost) achieved a mean absolute error of 2 years in predicting the age of new subjects. Feature importance analysis showed that the brain-to-intracranial-volume ratio is the most important feature in predicting age, followed by the hippocampi volumes. The cortical thickness in temporal and parietal lobes showed a superior predictive value than frontal and occipital lobes. Insights from this approach that integrate model prediction and interpretation may help to shorten the current explanatory gap between chronological age and biological brain age.

Neuropsychology of posteromedial parietal cortex and conversion factors from Mild Cognitive Impairment to Alzheimer's disease: systematic search and state-of-the-art review

In the present review, we discuss the rationale and the clinical implications of assessing visuospatial working memory (VSWM), awareness of memory deficits, and visuomotor control in patients with mild cognitive impairment (MCI). These three domains are related to neural activity in the posteromedial parietal cortex (PMC) whose hypoactivation seems to be a significant predictor of conversion from MCI to Alzheimer’s disease (AD) as indicated by recent neuroimaging evidence. A systematic literature search was performed up to May 2021. Forty-eight studies were included: 42 studies provided analytical cross-sectional data and 6 studies longitudinal data on conversion rates. Overall, these studies showed that patients with MCI performed worse than healthy controls in tasks assessing VSWM, awareness of memory deficits, and visuomotor control; in some cases, MCI patients’ performance was comparable to that of patients with overt dementia. Deficits in VSWM and metamemory appear to be significant predictors of conversion. No study explored the relationship between visuomotor control and conversion. Nevertheless, it has been speculated that the assessment of visuomotor abilities in subjects at high AD risk might be useful to discriminate patients who are likely to convert from those who are not. Being able to indirectly estimate PMC functioning through quick and easy neuropsychological tasks in outpatient settings may improve diagnostic and prognostic accuracy, and therefore, the quality of the MCI patient’s management.

A Comparative Analysis of MRI Automated Segmentation of Subcortical Brain Volumes in a Large Dataset of Elderly Subjects

In this study, we perform a comparative analysis of automated image segmentation of subcortical structures in the elderly brain. Manual segmentation is very time-consuming and automated methods are gaining importance as a clinical tool for diagnosis. The two most commonly used software libraries for brain segmentation -FreeSurfer and FSL- are put to work in a large dataset of 4,028 magnetic resonance imaging (MRI) scans collected for this study. We find a lack of linear correlation between the segmentation volume estimates obtained from FreeSurfer and FSL. On the other hand, FreeSurfer volume estimates tend to be larger thanFSL estimates of the areas putamen, thalamus, amygdala, caudate, pallidum, hippocampus, and accumbens. The characterization of the performance of brain segmentation algorithms in large datasets as the one presented here is a necessary step towards partially or fully automated end-to-end neuroimaging workflow both in clinical and research settings.

Modeling household online shopping demand in the U.S.: a machine learning approach and comparative investigation between 2009 and 2017

Despite the rapid growth of online shopping and research interest in the relationship between online and in-store shopping, national-level modeling and investigation of the demand for online shopping with a prediction focus remain limited in the literature. This paper differs from prior work and leverages two recent releases of the U.S. National Household Travel Survey (NHTS) data for 2009 and 2017 to develop machine learning (ML) models, specifically gradient boosting machine (GBM), for predicting household-level online shopping purchases. The NHTS data allow for not only conducting nationwide investigation but also at the level of households, which is more appropriate than at the individual level given the connected consumption and shopping needs of members in a household. We follow a systematic procedure for model development including employing Recursive Feature Elimination algorithm to select input variables (features) in order to reduce the risk of model overfitting and increase model explainability. Among several ML models, GBM is found to yield the best prediction accuracy. Extensive post-modeling investigation is conducted in a comparative manner between 2009 and 2017, including quantifying the importance of each input variable in predicting online shopping demand, and characterizing value-dependent relationships between demand and the input variables. In doing so, two latest advances in machine learning techniques, namely Shapley value-based feature importance and Accumulated Local Effects plots, are adopted to overcome inherent drawbacks of the popular techniques in current ML modeling. The modeling and investigation are performed at the national level, with a number of findings obtained. The models developed and insights gained can be used for online shopping-related freight demand generation and may also be considered for evaluating the potential impact of relevant policies on online shopping demand.

Self-reported subjective cognitive decline is associated with global cognition in a community sample of Latinos/as/x living in the United States

INTRODUCTION

Although subjective cognitive decline (SCD) may be an early risk marker of Alzheimer's Disease (AD), research on SCD among Hispanics/Latinos/as/x (henceforth Latinos/as) living in the U.S. is lacking. We investigated if the cross-sectional relationship of self-reported SCD with objective cognition varies as a function of ethnic background (Latinos/as versus Non-Hispanic Whites [NHWs]). Secondary analyses conducted solely within the Latino/a group investigated if informant reported SCD is associated with objective cognition and whether self-reported SCD is related to markers of brain health in a sub-sample of Latinos/as with available MRI data.

METHODS

Eighty-three participants (≥60 years of age) without dementia (35 Latinos/as; 48 NHWs) completed the Mattis Dementia Rating Scale (MDRS) and the Subjective Cognitive Decline-Questionnaire (SCD-Q). Additionally, 22 Latino/a informants completed the informant-version of the SCD-Q. Hierarchical regression models investigated if ethnicity moderates the association of MDRS and SCD-Q scores after adjusting for demographics and depressive symptoms. Correlational analyses within the Latino/a group investigated self- and informant-reported associations of SCD-Q scores with objective cognition, and associations of self-reported SCD-Q scores with medial temporal lobe volume and thickness.

RESULTS

Latinos/as had lower education and MDRS scores than NHWs. Higher SCD-Q scores were associated with lower MDRS scores only in Latinos/as. Within the Latino/a group, self, but not informant reported SCD was related to objective cognition. Medium to large effect sizes were found whereby higher self-reported SCD was associated with lower entorhinal cortex thickness and left hippocampal volume in Latinos/as.

CONCLUSIONS

The association of SCD and concurrent objectively measured global cognition varied by ethnic background and was only significant in Latinos/as. Self-reported SCD may be an indicator of cognitive and brain health in Latinos/as without dementia, prompting clinicians to monitor cognition. Future studies should explore if SCD predicts objective cognitive decline in diverse groups of Latinos/as living in the U.S.

XGBoost Algorithm Prediction of Critical Care Outcome for Adult Patients Presenting to Emergency Department Using Initial Triage Information

Background

The emergency department (ED) triage system to classify and prioritize patients from high risk to less urgent continues to be a challenge.

Objective

This study, comprising 80,433 patients, aims to develop a machine learning algorithm prediction model of critical care outcomes for adult patients using information collected during ED triage and compare the performance with that of the baseline model using the Korean Triage and Acuity Scale (KTAS).

Methods

To predict the need for critical care, we used 13 predictors from triage information: age, gender, mode of ED arrival, the time interval between onset and ED arrival, reason of ED visit, chief complaints, systolic blood pressure, diastolic blood pressure, pulse rate, respiratory rate, body temperature, oxygen saturation, and level of consciousness. The baseline model with KTAS was developed using logistic regression, and the machine learning model with 13 variables was generated using extreme gradient boosting (XGB) and deep neural network (DNN) algorithms. The discrimination was measured by the area under the receiver operating characteristic (AUROC) curve. The ability of calibration with Hosmer–Lemeshow test and reclassification with net reclassification index were evaluated. The calibration plot and partial dependence plot were used in the analysis.

Results

The AUROC of the model with the full set of variables (0.833-0.861) was better than that of the baseline model (0.796). The XGB model of AUROC 0.861 (95% CI 0.848-0.874) showed a higher discriminative performance than the DNN model of 0.833 (95% CI 0.819-0.848). The XGB and DNN models proved better reclassification than the baseline model with a positive net reclassification index. The XGB models were well-calibrated (Hosmer-Lemeshow test; P>.05); however, the DNN showed poor calibration power (Hosmer-Lemeshow test; P<.001). We further interpreted the nonlinear association between variables and critical care prediction.

Conclusions

Our study demonstrated that the performance of the XGB model using initial information at ED triage for predicting patients in need of critical care outperformed the conventional model with KTAS.

Intra- and interhemispheric symmetry of subcortical brain structures: a volumetric analysis in the aging human brain

Here, we address the hemispheric interdependency of subcortical structures in the aging human brain. In particular, we investigated whether subcortical volume variations can be explained by the adjacency of structures in the same hemisphere or are due to the interhemispheric development of mirror subcortical structures in the brain. Seven subcortical structures in each hemisphere were automatically segmented in a large sample of 3312 magnetic resonance imaging (MRI) studies of elderly individuals in their 70s and 80s. We performed Eigenvalue analysis, and found that anatomic volumes in the limbic system and basal ganglia show similar statistical dependency whether considered in the same hemisphere (intrahemispherically) or different hemispheres (interhemispherically). Our results indicate that anatomic bilaterality of subcortical volumes is preserved in the aging human brain, supporting the hypothesis that coupling between non-adjacent subcortical structures might act as a mechanism to compensate for the deleterious effects of aging.