BiPETE: A Bi-Positional Embedding Transformer Encoder for Risk Assessment of Alcohol and Substance Use Disorder with Electronic Health Records

TL;DR

BiPETE is a novel transformer encoder that effectively models irregular temporal data in EHRs for predicting alcohol and substance use disorder risk, providing interpretable insights into clinical features.

Contribution

Introduces BiPETE, a transformer with dual positional embeddings for improved risk prediction from irregular EHR data without large-scale pretraining.

Findings

BiPETE improves AUPRC by 34% and 50% over baselines in two cohorts.

Dual positional encoding enhances model performance.

Model interpretability reveals key clinical risk factors.

Abstract

Transformer-based deep learning models have shown promise for disease risk prediction using electronic health records(EHRs), but modeling temporal dependencies remains a key challenge due to irregular visit intervals and lack of uniform structure. We propose a Bi-Positional Embedding Transformer Encoder or BiPETE for single-disease prediction, which integrates rotary positional embeddings to encode relative visit timing and sinusoidal embeddings to preserve visit order. Without relying on large-scale pretraining, BiPETE is trained on EHR data from two mental health cohorts-depressive disorder and post-traumatic stress disorder (PTSD)-to predict the risk of alcohol and substance use disorders (ASUD). BiPETE outperforms baseline models, improving the area under the precision-recall curve (AUPRC) by 34% and 50% in the depression and PTSD cohorts, respectively. An ablation study further confirms the effectiveness of the dual positional encoding strategy. We apply the Integrated Gradients method to interpret model predictions, identifying key clinical features associated with ASUD risk and protection, such as abnormal inflammatory, hematologic, and metabolic markers, as well as specific medications and comorbidities. Overall, these key clinical features identified by the attribution methods contribute to a deeper understanding of the risk assessment process and offer valuable clues for mitigating potential risks. In summary, our study presents a practical and interpretable framework for disease risk prediction using EHR data, which can achieve strong performance.