Empowering Health in Aging Populations: A Multimodal Vulnerability Tool for Frail Patients

Joanna G. Kondylis, Houman Javedan, Dimitris Bertsimas, Bharti Khurana

Keywords: Multimodal Machine Learning, Prognostic Classifiers, Optimal Policy Trees, Interpretability, Aging, Frailty

TL;DR: We built the first multimodal ML tool combining EHR data, clinical notes, and CT imaging to automatically assess vulnerability in frail adults, predicting six geriatric outcomes and stratifying patients into risk categories.

Track: Proceedings

Abstract: Frailty is a powerful predictor of adverse outcomes in older adults, yet its routine assessment remains limited in acute care settings due to the labor-intensive nature of the clinical Frailty Index (FI) scoring, requiring geriatric specialists and meticulous clinical assessment. We developed and externally validated the first automated multimodal vulnerability tool that provides a real-time risk assessment, integrating structured EHR data, clinical narratives, and CT imaging. Using data from two major Boston hospitals in the Mass General Brigham system, we trained models to predict six outcomes: 3- and 6-month all-cause mortality, 3- and 6-month hospital readmission, 6-month fall risk, and 1-year recurrent fall risk. Our multimodal approach achieved AUCs of $0.74$-$0.86$, with improvements of up to $4.3$% over single-modality models and $8$-$49$% over FI's predictive power. Beyond outcome prediction, we also sought to mirror clinical practice, where discrete frailty levels guide care planning. To this end, we developed a four-tier stratification system using k-means clustering and Optimal Policy Trees. This produces interpretable decision rules that assign patients to Non-, Pre-, Moderately-, and Severely- Vulnerable categories, actionable classifications that directly inform interventions, from fall prevention to advance care planning, while significantly outperforming traditional frailty scoring.

General Area: Applications and Practice

Specific Subject Areas: Supervised Learning, Unsupervised Learning, Public & Social Health

Data And Code Availability: No

Ethics Board Approval: Yes

Entered Conflicts: I confirm the above

Anonymity: I confirm the above

Submission Number: 51