A next-generation electronic frailty index leveraging deep learning on unstructured health records extends risk prediction across the full frailty spectrum

Background: Existing electronic frailty indices (eFI) are typically based on structured data and designed for older adults. We developed an eFI that integrates structured and unstructured electronic health records (EHRs) across adulthood and assessed its longitudinal trajectories and associations with adverse outcomes. Methods: We used longitudinal EHR data from 193629 individuals aged 35-103 in the Wellbeing Services County of Central Finland (2010-2023) and constructed a 53-item eFI including diagnosis codes, laboratory tests and items extracted from free-text clinical notes using deep-learning-based natural language processing. Associations with all-cause mortality, severe infections, fractures, and healthcare utilization were assessed using Cox and count models. Predictive performance was compared with Hospital Frailty Risk Score (HFRS) and Charlson Comorbidity Index (CCI). Findings: eFI trajectories accelerated notably from age 65 onwards. Using the eFI as a categorical variable, severe frailty was associated with higher risks of mortality (hazard ratio [HR] 7.31, 95% confidence interval [CI] 6.83-7.83), severe infections (HR 9.22, 95%CI 8.52-9.98), fractures (HR 2.75, 95%CI 2.52-3.01) and increased healthcare utilization (odds ratio [OR] 3.15, 95%CI 2.96-3.35) compared with non-frail. The risks were relatively greater in younger age groups and persisted when using the continuous eFI restricted to non-frail individuals. Across all outcomes, the eFI showed greater model discrimination than HFRS and CCI. Interpretation: An eFI using structured and unstructured EHR data improves risk stratification even in younger adults and at very low levels of frailty. Funding: Research Council of Finland, Instrumentarium Science Foundation, Sigrid Juselius Foundation and Samfundet Folkhalsan.