HARBOR: Holistic Adaptive Risk assessment model for BehaviORal healthcare

TL;DR

HARBOR is a novel language model tailored for behavioral healthcare risk assessment, effectively predicting mood and risk scores from multimodal, longitudinal patient data, outperforming traditional models and generic LLMs.

Contribution

The paper introduces HARBOR, a specialized language model for behavioral health risk scoring, and releases PEARL, a new longitudinal dataset for this domain.

Findings

HARBOR achieves 69% accuracy in risk prediction.

HARBOR outperforms classical models and proprietary LLMs.

PEARL dataset enables comprehensive benchmarking.

Abstract

Behavioral healthcare risk assessment remains a challenging problem due to the highly multimodal nature of patient data and the temporal dynamics of mood and affective disorders. While large language models (LLMs) have demonstrated strong reasoning capabilities, their effectiveness in structured clinical risk scoring remains unclear. In this work, we introduce HARBOR, a behavioral health aware language model designed to predict a discrete mood and risk score, termed the Harbor Risk Score (HRS), on an integer scale from -3 (severe depression) to +3 (mania). We also release PEARL, a longitudinal behavioral healthcare dataset spanning four years of monthly observations from three patients, containing physiological, behavioral, and self reported mental health signals. We benchmark traditional machine learning models, proprietary LLMs, and HARBOR across multiple evaluation settings and ablations. Our results show that HARBOR outperforms classical baselines and off the shelf LLMs, achieving 69 percent accuracy compared to 54 percent for logistic regression and 29 percent for the strongest proprietary LLM baseline.