P-Transformer: A Prompt-based Multimodal Transformer Architecture For Medical Tabular Data

Medical tabular data, abundant in Electronic Health Records (EHRs), is a valuable resource for diverse medical tasks such as risk prediction. While deep learning approaches, particularly transformer-based models, have shown remarkable performance in tabular data prediction, there are still problems remained for existing work to be effectively adapted into medical domain, such as under-utilization of unstructured free-texts, limited exploration of textual information in structured data, and data corruption. To address these issues, we propose P-Transformer, a Prompt-based multimodal Transformer architecture designed specifically for medical tabular data. This framework consists two critical components: a tabular cell embedding generator and a tabular transformer. The former efficiently encodes diverse modalities from both structured and unstructured tabular data into a harmonized language semantic space with the help of pre-trained sentence encoder and medical prompts. The latter integrates cell representations to generate patient embeddings for various medical tasks. In comprehensive experiments on two real-world datasets for three medical tasks, P-Transformer demonstrated the improvements with 10.9%/11.0% on RMSE/MAE, 0.5%/2.2% on RMSE/MAE, and 1.6%/0.8% on BACC/AUROC compared to state-of-the-art (SOTA) baselines in predictability. Notably, the model exhibited strong resilience to data corruption in the structured data, particularly when the corruption rates are high.