Predicting Patient Mortality for Earlier Palliative Care Identification in Medicare Advantage Plans: Features of a Machine Learning Model (Preprint)

Abstract

BACKGROUND Machine learning (ML) offers greater precision and sensitivity in predicting Medicare patient end of life (EOL) and potential need for palliative services. However, earlier ML research on older community-dwelling Medicare beneficiaries has provided insufficient exploration of key model feature impacts and the role of the social determinants of health. OBJECTIVE This study describes the development of a binary classification ML model predicting 1-year mortality among Medicare Advantage plan members aged 65+ (N=318,774), and further examines the top features of the predictive model. METHODS A light gradient boosted trees model configuration was selected based on 5 fold cross-validation. The model was trained with 80% of cases (n=255,020) using randomized feature generation periods, with 20% (n=63,754) reserved as a holdout for validation. The final algorithm used 907 feature inputs extracted primarily from claims and administrative data capturing patient diagnoses, service utilization, demographics, and census tract-based social determinants index measures. RESULTS The total sample had an actual mortality prevalence of 3.9% in the 2018 outcome period. The final model positively predicted 41.5% of patient expirations among the top 1% of highest risk members (AUC=0.84; 95% CI: 0.83-0.85), versus 22.2% predicted by the model iteration based on age, gender, and select high-risk utilization features alone (AUC=0.73; 95% CI: 0.72-0.75). The most important algorithm features included patient demographics, diagnoses, pharmacy utilization, mean costs, and certain social determinants of health. CONCLUSIONS The final ML model better predicts Medicare Advantage members approaching EOL using a variety of routinely-collected data and can support earlier patient identification for palliative care.