Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: May 15, 2020
Date Accepted: Jan 18, 2021

The final, peer-reviewed published version of this preprint can be found here:

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

Hu M, Wu X, Shu X, Zhao Y, Feng H

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

J Med Internet Res 2021;23(2):e20298

DOI: 10.2196/20298

PMID: 33625369

PMCID: 7946590

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Development and validation of risk prediction model for cognitive impairment in Chinese community dwellers with normal cognition: using machine learning approach

  • Mingyue Hu; 
  • Xinyin Wu; 
  • Xinhui Shu; 
  • Yinan Zhao; 
  • Hui Feng

ABSTRACT

Background:

Dementia causes huge pressure on families and goverments worldwide. Early detection of individuals at risk of cognitive impairment is critical to reduce the mortality rate.

Objective:

We aimed to build a prediction model based on machine learning for cognitive impairment (CI) in Chinese elderly community dwellers with normal cognition.

Methods:

A prospective cohort of 6,718 older people from the Chinese Longitudinal Healthy Longevity Survey (CLHLS), followed from 2008-2011, was used to develop and validate the prediction model. CI was identified using Chinese version of the Mini-Mental State Examination (CMMSE). Several machine learning algorithms (Random Forest, XGBoost, Naïve Bayes and logistic regression) were used to model 3-year risk of CI. We explored optimal cutoffs and adjusted parameters in validation data and evaluated the model in test data. Nomogram was established to vividly present the prediction model.

Results:

Mean age was 80.4 ± 10.3 years and 50.8% were female. During 3-year follow-up, 991 (14.8%) participants were identified as CI. Four features were finally selected to develop model, including age, IADL, marital status and baseline cognitive function. The Concordance index of the model constructed by logistic regression were 0.814 (95%CI 0.781 - 0.846). Older people with normal cognitive function who had a nomogram score of less than 170 or 170 or greater were considered to have low or high 3-year risks of CI, respectively.

Conclusions:

The simple and feasible CI prediction model could identify Chinese elderly community dwellers at greatest risk for CI. This practical model presented by nomogram could be used to screen Chinese elderly community dwellers for CI and to target intervention strategies.


 Citation

Please cite as:

Hu M, Wu X, Shu X, Zhao Y, Feng H

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

J Med Internet Res 2021;23(2):e20298

DOI: 10.2196/20298

PMID: 33625369

PMCID: 7946590

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.