Advancing Precision Medicine: Treatment Regimen Recommendations via Siamese Neural Networks

The rapidly increasing adoption of Electronic Health Records (EHRs) has provided us with a comprehensive and reliable data repository, enabling the robust support for clinical decision making and the efficacious management of cardiovascular diseases. Patients may receive various treatment regimens due to the idiosyncratic dissimilarities in physical conditions. Hence, assigning specific category labels to treatment regimens for individual patients poses a challenge owing to the intricate nature of diverse medications and patient profiles. In this paper, we address this challenge by developing a novel model for Treatment Regimen Recommendations based on Siamese Neural Networks (TRRSNN). TRRSNN is harnessed to learn a global similarity metric from EHRs, facilitating the comparison and matching of target patients from unknown categories. The objective is to proffer recommendations of pre-existing treatments of patients that exhibit the highest semblance to those of target patients. Our proposed TRRSNN obviates the necessity for categorically labeling treatment regimens, and instead focuses on discerning the similarity among treatment regimens for pairwise patients. We conduct empirical evaluations on two real-world datasets, and the results demonstrate the superiority of our proposed TRRSNN over the baselines for treatment regimen recommendations.