Latent trajectories of frailty and risk prediction models among geriatric community dwellers: an interpretable machine learning perspective

Explainable machine learning framework for biomarker discovery by combining biological age and frailty prediction

Biological age (BA) and frailty represent two distinct health measures that offer valuable insights into the aging process. Comparing and analyzing blood-based biomarkers from the machine learning (ML) predictors of BA and frailty helps deepen our understanding of aging. This study aimed to develop a novel framework to identify biomarkers of aging by combining BA and frailty ML predictors with eXplainable Artificial Intelligence (XAI) techniques. We utilized data from middle-aged and older Chinese adults (≥ 45 years) in the 2011/2012 wave (n = 9702) and the 2015/2016 wave (n = 9455, as test set validation) of the China Health and Retirement Longitudinal Study (CHARLS). Sixteen blood-based biomarkers were used to predict BA and frailty. Four tree-based ML algorithms were employed in the training and validation, and performance metrics were compared to select the best models. Then, SHapley Additive exPlanations (SHAP) analysis was conducted on the selected models. CatBoost performed the best in the BA predictor, and Gradient Boosting performed the best in the frailty predictor. Traditional ML feature importance identified cystatin C and glycated hemoglobin as the major contributors for their respective models. However, subsequent SHAP analysis demonstrated that only cystatin C was the primary contributor in both models. The proposed framework can easily incorporate additional biomarkers, providing a scalable and comprehensive toolset that offers a quantitative understanding of biomarkers of aging.

Determinants and risk prediction models for frailty among community-living older adults in eastern China

Objective

The purpose of this study is to develop predictive models for frailty risk among community-dwelling older adults in eastern China using machine learning techniques. This approach aims to facilitate early detection of high-risk individuals and inform the design of tailored interventions, with the ultimate goals of enhancing quality of life and mitigating frailty progression in the older adult population.

Methods

This study involved 1,263 participants aged 60 years or older, who were selected through stratified cluster sampling. Frailty was assessed using the Tilburg Frailty Indicator (TFI), which encompasses physical, psychological, and social dimensions. Predictive models were constructed using decision trees, random forests, and XGBoost algorithms, implemented in R software (version 4.4.2). The performance of these models was evaluated using metrics such as the area under the receiver operating characteristic curve (AUC), ROC curves, and confusion matrices.

Results

The results showed that 64.77% of the older adult were physically weak. Body mass index (BMI), living arrangements, frequency of visits and smoking status are the main factors contributing to frailty. When comparing predictive model metrics, random forest and extreme Gradient Lift (XGBoost) outperform decision tree models in terms of accuracy and applicability.

Conclusion

Older adults living in communities in eastern China showed slight frailty, and many factors influenced their frailty scores. Random forest and XGBoost models outperform decision tree models in predicting frailty in older adults, so identifying high-risk individuals early and developing personalized interventions can help slow the development of frailty and improve quality of life in older adults.

A two-year longitudinal study of the impact of cognitive status and depression on frailty status in older adults following hip fracture

OBJECTIVES

To examine if frailty is associated with cognitive status or depression in older adults following surgery for hip fracture.

DESIGN

A 2-year longitudinal correlational cohort study.

SETTING AND PARTICIPANTS

Older adults (≥ 60 years) who had hip-fracture surgery were recruited from a 3,000-bed medical center in Taiwan.

METHODS

Participants were recruited between September 2012; follow-up was completed in March 2021. Measures for frailty, cognitive status, and depression were assessed at six points. Frailty changes were analyzed using generalized estimating equations.

RESULTS

Mean age was 78.51 ± 9.0 years. Compared to those without cognitive impairment or without depression, pre-fracture basic activities of daily living (BADLs), baseline walking ability and frailty were worse for participants with cognitive impairment or depression (P < .001). Frailty increased over time for those with cognitive impairment and depression after controlling for covariates (P < .001).

CONCLUSIONS

Assessing cognitive status and depression in older adults following hip fracture could guide interventions to reduce frailty.

Effect of leisure activity on frailty trajectories among Chinese older adults: a 16-year longitudinal study

BACKGROUND

While the significant association between leisure activities and frailty risk among older adults is well-established, the impact of integrated leisure activity scores and different categories of them on frailty trajectories over time remains unclear.

METHODS

This study utilized longitudinal data from the Chinese Longitudinal Healthy Longevity Survey (CLHLS), which enrolled participants aged 65 years and older between 2002 and 2018. Frailty trajectories were derived using group-based trajectory modelling, and based on these trajectories, subjects were classified into various categories. Leisure activity was measured by integrated scores as well as three distinct categories: physically, cognitively, and socially stimulating activity. The effect of leisure activity on frailty trajectories was examined using multinomial logistic regression.

RESULTS

By analysing data from 2,299 older adults, three frailty trajectories were identified: non-frail, moderate progressive, and high progressive. The results indicated that an increase in the score of integrated leisure activity was associated with 11% (odds ratio [OR] 0.89; 95% Confidence Interval [CI] 0.85-0.93) and 14% (OR 0.86; 95% CI 0.80-0.91) decrease in the likelihood of being in the moderate and high progressive frailty trajectories, respectively. Engaging in physically stimulating activity lowered the odds of belonging to the moderate and high progressive trajectory by 43% (OR 0.57; 95% CI 0.40-0.81; OR 0.57; 95% CI 0.36-0.92, respectively). Participation in socially stimulating activity showed a lower odd of being in the moderate progressive trajectory (OR 0.68; 95% CI 0.49-0.93) and the high progressive trajectory (OR, 0.61; 95% CI, 0.39-0.95). The effects of leisure activities on frailty trajectories were observed not to vary by age, education level and retirement status.

CONCLUSIONS

This study suggests that older adults should be encouraged to increase both the amount and variety of their leisure activities. Physically stimulating activities should be considered the primary choice, followed by socially and cognitively stimulating activities.

Latent Trajectories of Cerebral Perfusion Pressure and Risk Prediction Models Among Patients with Traumatic Brain Injury: Based on an Interpretable Artificial Neural Network

OBJECTIVE

This study aimed to characterize long-term cerebral perfusion pressure (CPP) trajectory in traumatic brain injury (TBI) patients and construct an interpretable prediction model to assess the risk of unfavorable CPP evolution patterns.

METHODS

TBI patients with CPP records were identified from the Medical Information Mart for Intensive Care (MIMIC)-IV 2.1, eICU Collaborative Research Database (eICU-CRD) 2.0, and HiRID dataset 1.1.1. The research process consisted of 2 stages. First, group-based trajectory modeling (GBTM) was used to identify different CPP trajectories. Second, different artificial neural network (ANN) algorithms were used to predict the trajectories of CPP.

RESULTS

A total of 331 eligible patients' records from MIMIC-IV 2.1 and eICU-CRD 2.0 were used for trajectory analysis and model development. Additionally, 310 patients' data from HiRID were used for external validation. The GBTM identified 5 CPP trajectory groups, group 1 and group 5 were merged into class 1 based on unfavorable in-hospital mortality. The best 6 predictors were invasive systolic blood pressure coefficient of variation, venous blood chloride ion concentration, PaCO2, prothrombin time, CPP coefficient of variation, and mean CPP. Compared with other algorithms, Scaled Conjugate Gradient performed relatively better in identifying class 1.

CONCLUSIONS

This study identified 2 CPP trajectory groups associated with elevated risk and 3 with reduced risk. PaCO2 might be a strong predictor for the unfavorable CPP class. The ANN model achieved the primary goal of risk stratification, which is conducive to early intervention and individualized treatment.

What If the Clinical and Older Adults' Perspectives about Frailty Converge? A Call for a Mixed Conceptual Model of Frailty: A Traditional Literature Review

Existing frailty models have enhanced research and practice; however, none of the models accounts for the perspective of older adults upon defining and operationalizing frailty. We aim to propose a mixed conceptual model that builds on the integral model while accounting for older adults' perceptions and lived experiences of frailty. We conducted a traditional literature review to address frailty attributes, risk factors, consequences, perceptions, and lived experiences of older adults with frailty. Frailty attributes are vulnerability/susceptibility, aging, dynamic, complex, physical, psychological, and social. Frailty perceptions and lived experience themes/subthemes are refusing frailty labeling, being labeled "by others" as compared to "self-labeling", from the perception of being frail towards acting as being frail, positive self-image, skepticism about frailty screening, communicating the term "frail", and negative and positive impacts and experiences of frailty. Frailty risk factors are classified into socio-demographic, biological, physical, psychological/cognitive, behavioral, and situational/environmental factors. The consequences of frailty affect the individual, the caregiver/family, the healthcare sector, and society. The mixed conceptual model of frailty consists of interacting risk factors, interacting attributes surrounded by the older adult's perception and lived experience, and interacting consequences at multiple levels. The mixed conceptual model provides a lens to qualify frailty in addition to quantifying it.

Machine learning approaches for frailty detection, prediction and classification in elderly people: A systematic review

BACKGROUND

Frailty in older people is a syndrome related to aging that is becoming increasingly common and problematic as the average age of the world population increases. Detecting frailty in its early stages or, even better, predicting its appearance can greatly benefit health in later years of life and save the healthcare system from high costs. Machine Learning models fit the need to develop a tool for supporting medical decision-making in detecting or predicting frailty.

METHODS

In this review, we followed the PRISMA methodology to conduct a systematic search of the most relevant Machine Learning models that have been developed so far in the context of frailty. We selected 41 publications and compared them according to their purpose, the type of dataset used, the target variables, and the results they obtained, highlighting their shortcomings and strengths.

RESULTS

The variety of frailty definitions allows many problems to fall into this field, and it is often challenging to compare results due to the differences in target variables. The data types can be divided into gait data, usually collected with sensors, and medical records, often in the context of aging studies. The most common algorithms are well-known models available from every Machine Learning library. Only one study developed a new framework for frailty classification, and only two considered Explainability.

CONCLUSIONS

This review highlights some gaps in the field of Machine Learning applied to the assessment and prediction of frailty, such as the need for a universal quantitative definition. It emphasizes the need for close collaboration between medical professionals and data scientists to unlock the potential of data collected in hospital and clinical settings. As a suggestion for future work, the area of Explainability, which is crucial for models in medicine and health care, was considered in very few studies.

Digital health technology combining wearable gait sensors and machine learning improve the accuracy in prediction of frailty

Background

Frailty is a dynamic and complex geriatric condition characterized by multi-domain declines in physiological, gait and cognitive function. This study examined whether digital health technology can facilitate frailty identification and improve the efficiency of diagnosis by optimizing analytical and machine learning approaches using select factors from comprehensive geriatric assessment and gait characteristics.

Methods

As part of an ongoing study on observational study of Aging, we prospectively recruited 214 individuals living independently in the community of Southern China. Clinical information and fragility were assessed using comprehensive geriatric assessment (CGA). Digital tool box consisted of wearable sensor-enabled 6-min walk test (6MWT) and five machine learning algorithms allowing feature selections and frailty classifications.

Results

It was found that a model combining CGA and gait parameters was successful in predicting frailty. The combination of these features in a machine learning model performed better than using either CGA or gait parameters alone, with an area under the curve of 0.93. The performance of the machine learning models improved by 4.3-11.4% after further feature selection using a smaller subset of 16 variables. SHapley Additive exPlanation (SHAP) dependence plot analysis revealed that the most important features for predicting frailty were large-step walking speed, average step size, age, total step walking distance, and Mini Mental State Examination score.

Conclusion

This study provides evidence that digital health technology can be used for predicting frailty and identifying the key gait parameters in targeted health assessments.