AI Insight
Researchers developed a next-generation electronic frailty index (eFI) that combines structured medical data with information extracted from clinical notes using deep learning natural language processing, analyzing records from nearly 194,000 adults aged 35-103 in Finland over 13 years. The new eFI, comprising 53 health indicators, demonstrated superior ability to predict mortality, severe infections, fractures, and healthcare utilization compared to existing tools, with particularly strong predictive value in younger adults and even among individuals classified as non-frail. Frailty trajectories accelerated notably after age 65, and severe frailty was associated with a 7-fold increased mortality risk and 9-fold increased risk of severe infections.
Why it matters
This tool could enable earlier identification of at-risk individuals across all adult age groups, not just the elderly, potentially allowing for preventive interventions before severe frailty develops. By incorporating unstructured clinical notes through artificial intelligence, the system captures health information that traditional risk assessment tools miss, offering more accurate patient risk stratification for clinical decision-making and healthcare resource allocation.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
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.