# Proactive HIV Care: AI-Based Comorbidity Prediction from Routine EHR Data

## TL;DR

This study demonstrates that AI models using routine EHR data, including demographic information, can effectively predict multiple comorbidities in HIV patients, highlighting both predictive benefits and fairness concerns.

## Contribution

It introduces demographic-aware AI models for multi-label comorbidity prediction in HIV care, showing improved accuracy over demographic-unaware models.

## Key findings

- Demographic-aware models outperform unaware models in comorbidity prediction.
- Gender and age can be accurately inferred from laboratory data.
- Using demographic data raises important fairness and bias considerations.

## Abstract

People living with HIV face a high burden of comorbidities, yet early detection is often limited by symptom-driven screening. We evaluate the potential of AI to predict multiple comorbidities from routinely collected Electronic Health Records. Using data from 2,200 HIV-positive patients in South East London, comprising 30 laboratory markers and 7 demographic/social attributes, we compare demographic-aware models (which use both laboratory/social variables and demographic information as input) against demographic-unaware models (which exclude all demographic information). Across all methods, demographic-aware models consistently outperformed unaware counterparts. Demographic recoverability experiments revealed that gender and age can be accurately inferred from laboratory data, underscoring both the predictive value and fairness considerations of demographic features. These findings show that combining demographic and laboratory data can improve automated, multi-label comorbidity prediction in HIV care, while raising important questions about bias and interpretability in clinical AI.