Prediction of cognitive impairment among Medicare beneficiaries using a machine learning approach

Abstract

Objective

Developing machine learning (ML) models to predict cognitive impairment among Medicare beneficiaries in the United States.

Methods

This retrospective study used the 2016–2019 Medicare Current Beneficiary Survey Cost and Use and Survey Public Use Files. Medicare beneficiaries aged 65 and older (n=4,965) with at least two consecutive years’ data were included. Cognitive impairment was categorized into three stages: severe, moderate, and none based on self-reported data. Baseline year’s demographic, socioeconomic factors, self-reported functional limitations, health status and comorbidities, number of concurrent medications, level of social engagement, behavioral variables, and satisfaction of medical care’s quality were features assessed in ML algorithms to predict next years’ cognitive function. ML models in six major categories were developed, tested, and compared (accuracy, AUC, and F1 score) using Python version 3.11. The importance of features was evaluated using the total reduction of the Gini. A subgroup analysis was conducted among beneficiaries who were 80 years and older.

Results

Approximately 11.1% of beneficiaries aged ≥ 65 had moderate or severe cognitive function impairment. Baseline cognitive function was the most significant predictor for next year’s cognitive function impairment, followed by baseline IADL, level of social activities, ADL, general health status, income, age, education, region of residence, and body mass index. Beneficiaries 80 years and older had satisfaction of medical care’s quality among the top 10 most significant predictors.

Conclusions

Older adults’ baseline cognitive function and IADL were top two predictors of cognitive function impairment. Clinicians should regularly screen and monitor older adults’ cognitive and daily function.