Develop and validate a prognostic index with laboratory tests to predict mortality in middle-aged and older adults using machine learning models: a prospective cohort study.

BACKGROUND: Prognostic indices can enhance personalized predictions of health burdens. However, a simple, practical and reproducible tool is lacking for clinical use. This study aimed to develop a machine learning-based prognostic index for predicting all-cause mortality in community-dwelling elderly individuals.

METHODS: We utilized the Healthy Aging Longitudinal Study in Taiwan (HALST) cohort, encompassing data from 5,663 participants. Over the 5-year follow-up, 447 deaths were confirmed. A machine learning-based routine blood examination prognostic index (MARBE-PI) was developed using common laboratory tests based on machine learning techniques. Participants were grouped into multiple risk categories by stratum-specific likelihood ratios analysis based on their MARBE-PI scores. The MARBE-PI was subsequently externally validated with an independent population-based cohort from Japan.

RESULTS: Beyond age, sex, education level and BMI, six laboratory tests (LDL, albumin, AST, lymphocyte count, hsCRP, and creatinine) emerged as pivotal predictors via stepwise logistic regression for 5-year mortality. The AUCs of MARBE-PI constructed by logistic regression were 0.799 (95% CI: 0.778-0.819) and 0.756 (95% CI: 0.694-0.814) for the internal and external validation datasets, and were 0.801 (95% CI: 0.790-0.811) and 0.809 (95% CI: 0.774-0.845) for the extended 10-year mortality in both datasets, respectively. Risk categories stratified by MARBE-PI showed a consistent dose-response association with mortality. The MARBE-PI also performed comparably with indices constructed with clinical health deficits and/or laboratory results.

CONCLUSIONS: The MARBE-PI is considered the most applicable measure for risk stratification in busy clinical settings. It holds potential to pinpoint elderly individuals at elevated mortality risk, thereby aiding clinical decision-making.