Developing a social vulnerability index from real-world electronic health records using natural language processing

Background: Social vulnerability is associated with adverse health outcomes, but existing social vulnerability indices often rely on cohort-based and self-reported data, potentially limiting their population-level applicability. Therefore, this study aimed to develop an SVI from routinely collected electronic health records (EHRs) using natural language processing (NLP) and examine its association with mortality and healthcare utilization. Method: EHR data from 193,629 individuals aged 35 to102 from the Wellbeing Services County of Central Finland between years 2010 and 2023 were used in this study. A 6 item SVI (total score 0 to 6) was developed from free-text clinical notes using deep-learning-based NLP. SVI scores were calculated at baseline and annually for individuals. Associations between baseline SVI and all cause mortality and healthcare utilization were assessed over 12-year follow-up using Cox and count models. Results: The mean baseline SVI among all participants was 0.35 (range 0 to 6). Women had higher SVI (0.39) than men (0.32, p<0.001). SVI increased with age. One unit increase in SVI was associated with a higher risk of mortality (Hazard Ratio (HR) 1.23; 95% Confidence Interval (CI) (1.21 to 1.24), a higher odds of using healthcare services (Odds Ratio (OR) = 1.20; 95% CI): 1.19 to 1.21) and a greater healthcare service use (Incidence Rate Ratio (IRR) = 1.07; 95% CI: 1.06 to 1.07). Discussion: An index capturing multiple domains of social vulnerability can be derived from EHRs using NLP. Higher SVI was associated with increased mortality and healthcare utilization. These findings support the potential of EHR data for assessing social vulnerability and related health risks.