Bio-Inspired AI Multimorbidity Score for Human-Machine Clinical Risk Stratification

Multimorbidity is strongly associated with mortality, but existing comorbidity indices often
generalize poorly across populations because they depend on fixed disease lists and contextspecific weights. We developed LLM-MMS, a prompt-based large language model–derived
multimorbidity phenotype score, as a bio-inspired AI score for human–machine clinical risk
stratification, and evaluated it for all-cause mortality prediction in 770,439 adults from nine
international longitudinal cohorts. Harmonized participant-level data were converted into
standardized health narratives and processed without model fine-tuning. In UK Biobank, LLMMMS achieved strong discrimination, calibration and prediction accuracy. Across eight external
cohorts, it maintained consistent performance, with C-indices of 0.67–0.86 and observed-toexpected ratios close to 1.00. This outperformed recalibrated conventional comorbidity indices in
every cohort with absolute C-index gains of 0.12–0.21. Performance remained stable across sex
and age subgroups, including adults younger than 60 years, and decision curve analysis showed
greater or comparable clinical net benefit in most cohorts. Proteomic and interpretability analyses
supported the biological plausibility of LLM-MMS, linking high multimorbidity burden to
inflammatory, metabolic and tissue-damage pathways and identifying clinically coherent drivers
of risk. These findings suggest that LLM-MMS offers a transportable and interpretable bioinspired framework that integrates clinician-like multimodal reasoning with population-level
validation for multimorbidity risk stratification across diverse populations.