Integrating Genomics into Multimodal EHR Foundation Models

TL;DR

This paper presents a novel multimodal EHR foundation model that incorporates Polygenic Risk Scores to improve disease prediction, interpretability, and personalized healthcare insights using extensive genetic and clinical data.

Contribution

It introduces an innovative framework integrating genetic data into EHR models, extending generative AI techniques to enhance predictive accuracy and interpretability in healthcare.

Findings

Model predicts onset of conditions like Type 2 Diabetes effectively.

Integration of PRS improves risk stratification and personalized predictions.

Transfer learning enables efficient adaptation to new classification tasks.

Abstract

This paper introduces an innovative Electronic Health Record (EHR) foundation model that integrates Polygenic Risk Scores (PRS) as a foundational data modality, moving beyond traditional EHR-only approaches to build more holistic health profiles. Leveraging the extensive and diverse data from the All of Us (AoU) Research Program, this multimodal framework aims to learn complex relationships between clinical data and genetic predispositions. The methodology extends advancements in generative AI to the EHR foundation model space, enhancing predictive capabilities and interpretability. Evaluation on AoU data demonstrates the model's predictive value for the onset of various conditions, particularly Type 2 Diabetes (T2D), and illustrates the interplay between PRS and EHR data. The work also explores transfer learning for custom classification tasks, showcasing the architecture's versatility and efficiency. This approach is pivotal for unlocking new insights into disease prediction, proactive health management, risk stratification, and personalized treatment strategies, laying the groundwork for more personalized, equitable, and actionable real-world evidence generation in healthcare.