Med-PRSIMD: Enhanced Complex Disease Risk Prediction through Integrative Analysis of Multi-Type Data and Medical History Records
Zeming Li, Yu Gong Xu, Debajyoti Chowdhury, Hip Fung Yip, Chonghao Wang, Lu Zhang · 2024
Predicting complex diseases using computational methods have rapidly evolved, which accelerates precision medicine, disease prevention, and so on. In past years, especially after emergence of genomics, major focus was inclined connecting genetic influence to complex diseases wherein many other essential factors such as environment, lifestyles, and so on were constantly neglected. In recent years, researchers have begun predicting disease risk scores by integrating genetic variants data and different lifestyle factors (alcohol intake, etc) and physical parameters (body mass index, age, etc). However, a potential missing link still exists there as most of those methods did not adequately address how to integrate the information from the medical history record that plays a crucial role in complex disease occurrence. In this paper, we have proposed Med-PRSIMD model that integrates genetic variants, lifestyle factors and medical history records to advance complex disease prediction. In this approach, we trained the Transformer model using causal language model pretraining task for extracting medical history records information. We have evaluated the prediction performance of our proposed Med-PRSIMD model on coronary artery disease, type 2 diabetes, and breast cancer patients' data obtained from the UK biobank. Med-PRSIMD achieved state-of-the-art performance compared to existing methods.