Explainable machine learning model for pre‐frailty risk assessment in community‐dwelling older adults

Abstract Background Frailty in older adults is linked to increased risks and lower quality of life. Pre‐frailty, a condition preceding frailty, is intervenable, but its determinants and assessment are challenging. This study aims to develop and validate an explainable machine learning model for pre‐...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenlin Du, Zeyu Zhang, Baoqin Liu, Zijian Cao, Nan Jiang, Zongjiu Zhang
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:Health Care Science
Subjects:
Online Access:https://doi.org/10.1002/hcs2.120
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846107032725225472
author Chenlin Du
Zeyu Zhang
Baoqin Liu
Zijian Cao
Nan Jiang
Zongjiu Zhang
author_facet Chenlin Du
Zeyu Zhang
Baoqin Liu
Zijian Cao
Nan Jiang
Zongjiu Zhang
author_sort Chenlin Du
collection DOAJ
description Abstract Background Frailty in older adults is linked to increased risks and lower quality of life. Pre‐frailty, a condition preceding frailty, is intervenable, but its determinants and assessment are challenging. This study aims to develop and validate an explainable machine learning model for pre‐frailty risk assessment among community‐dwelling older adults. Methods The study included 3141 adults aged 60 or above from the China Health and Retirement Longitudinal Study. Pre‐frailty was characterized by one or two criteria from the physical frailty phenotype scale. We extracted 80 distinct features across seven dimensions to evaluate pre‐frailty risk. A model was constructed using recursive feature elimination and a stacking‐CatBoost distillation module on 80% of the sample and validated on a separate 20% holdout data set. Results The study used data from 2508 community‐dwelling older adults (mean age, 67.24 years [range, 60–96]; 1215 [48.44%] females) to develop a pre‐frailty risk assessment model. We selected 57 predictive features and built a distilled CatBoost model, which achieved the highest discrimination (AUROC: 0.7560 [95% CI: 0.7169, 0.7928]) on the 20% holdout data set. The living city, BMI, and peak expiratory flow (PEF) were the three most significant contributors to pre‐frailty risk. Physical and environmental factors were the top 2 impactful feature dimensions. Conclusions An accurate and interpretable pre‐frailty risk assessment framework using state‐of‐the‐art machine learning techniques and explanation methods has been developed. Our framework incorporates a wide range of features and determinants, allowing for a comprehensive and nuanced understanding of pre‐frailty risk.
format Article
id doaj-art-f3c26c83d5004c8e9c70546dce02d878
institution Kabale University
issn 2771-1757
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series Health Care Science
spelling doaj-art-f3c26c83d5004c8e9c70546dce02d8782024-12-27T01:50:03ZengWileyHealth Care Science2771-17572024-12-013642643710.1002/hcs2.120Explainable machine learning model for pre‐frailty risk assessment in community‐dwelling older adultsChenlin Du0Zeyu Zhang1Baoqin Liu2Zijian Cao3Nan Jiang4Zongjiu Zhang5School of Biomedical Engineering Tsinghua University Beijing ChinaTsinghua Medicine, Tsinghua University Beijing ChinaInstitute for Hospital Management Tsinghua University Beijing ChinaSchool of Biomedical Engineering Tsinghua University Beijing ChinaSchool of Biomedical Engineering Tsinghua University Beijing ChinaSchool of Biomedical Engineering Tsinghua University Beijing ChinaAbstract Background Frailty in older adults is linked to increased risks and lower quality of life. Pre‐frailty, a condition preceding frailty, is intervenable, but its determinants and assessment are challenging. This study aims to develop and validate an explainable machine learning model for pre‐frailty risk assessment among community‐dwelling older adults. Methods The study included 3141 adults aged 60 or above from the China Health and Retirement Longitudinal Study. Pre‐frailty was characterized by one or two criteria from the physical frailty phenotype scale. We extracted 80 distinct features across seven dimensions to evaluate pre‐frailty risk. A model was constructed using recursive feature elimination and a stacking‐CatBoost distillation module on 80% of the sample and validated on a separate 20% holdout data set. Results The study used data from 2508 community‐dwelling older adults (mean age, 67.24 years [range, 60–96]; 1215 [48.44%] females) to develop a pre‐frailty risk assessment model. We selected 57 predictive features and built a distilled CatBoost model, which achieved the highest discrimination (AUROC: 0.7560 [95% CI: 0.7169, 0.7928]) on the 20% holdout data set. The living city, BMI, and peak expiratory flow (PEF) were the three most significant contributors to pre‐frailty risk. Physical and environmental factors were the top 2 impactful feature dimensions. Conclusions An accurate and interpretable pre‐frailty risk assessment framework using state‐of‐the‐art machine learning techniques and explanation methods has been developed. Our framework incorporates a wide range of features and determinants, allowing for a comprehensive and nuanced understanding of pre‐frailty risk.https://doi.org/10.1002/hcs2.120China Health and Retirement Longitudinal StudyChinese community‐dwelling older adultsexplainable machine learningpre‐frailtyrisk assessment
spellingShingle Chenlin Du
Zeyu Zhang
Baoqin Liu
Zijian Cao
Nan Jiang
Zongjiu Zhang
Explainable machine learning model for pre‐frailty risk assessment in community‐dwelling older adults
Health Care Science
China Health and Retirement Longitudinal Study
Chinese community‐dwelling older adults
explainable machine learning
pre‐frailty
risk assessment
title Explainable machine learning model for pre‐frailty risk assessment in community‐dwelling older adults
title_full Explainable machine learning model for pre‐frailty risk assessment in community‐dwelling older adults
title_fullStr Explainable machine learning model for pre‐frailty risk assessment in community‐dwelling older adults
title_full_unstemmed Explainable machine learning model for pre‐frailty risk assessment in community‐dwelling older adults
title_short Explainable machine learning model for pre‐frailty risk assessment in community‐dwelling older adults
title_sort explainable machine learning model for pre frailty risk assessment in community dwelling older adults
topic China Health and Retirement Longitudinal Study
Chinese community‐dwelling older adults
explainable machine learning
pre‐frailty
risk assessment
url https://doi.org/10.1002/hcs2.120
work_keys_str_mv AT chenlindu explainablemachinelearningmodelforprefrailtyriskassessmentincommunitydwellingolderadults
AT zeyuzhang explainablemachinelearningmodelforprefrailtyriskassessmentincommunitydwellingolderadults
AT baoqinliu explainablemachinelearningmodelforprefrailtyriskassessmentincommunitydwellingolderadults
AT zijiancao explainablemachinelearningmodelforprefrailtyriskassessmentincommunitydwellingolderadults
AT nanjiang explainablemachinelearningmodelforprefrailtyriskassessmentincommunitydwellingolderadults
AT zongjiuzhang explainablemachinelearningmodelforprefrailtyriskassessmentincommunitydwellingolderadults