EURO 2025 Leeds
Abstract Submission

207. Identifying Combination Therapies for Diabetes and its Comorbidities

Invited abstract in session MC-13: Medical applications, stream OR in Healthcare (ORAHS).

Monday, 12:30-14:00
Room: Clarendon SR 1.01

Authors (first author is the speaker)

1. Hyungsuk Lim
Industrial Engineering, Yonsei University
2. Yucheol Kim
Industrial Engineering, Yonsei University
3. Geon Hyeok Chun
Industrial Engineering (Industrial Statistics Lab), Yonsei University
4. So Young Sohn
Industrial Engineering, Yonsei university

Abstract

Type 2 diabetes mellitus is one of the most serious health conditions globally recognized for the diversity in related comorbidities. Since each patient is exposed to different diabetic comorbidities with varying level of risk, personalized combination therapies are necessary for managing both diabetes and its related comorbidities. However, current diabetic treatment guidelines fail to comprehensively address the unique susceptibility of individuals to various diabetic comorbidities, thereby facing challenges in identifying personalized combination therapy. Furthermore, previous studies on diabetic treatments are mostly focused on the impact of antidiabetic drugs on diabetic comorbidities, without considering the drug-drug interactions among antidiabetic drugs and other drugs for diabetic comorbidities. In this study, we suggest a novel framework that identifies combination therapies for the treatment of both diabetes and diabetic comorbidities in terms of not only maximizing synergism but also minimizing antagonism among drugs. We first utilize the link prediction based on multiplex disease network and community detection to identify different sets of diabetic comorbidities while incorporating diverse aspects of diseases. Afterward, we apply integer programming to drug-disease associations in each identified combination of diabetic comorbidities. Our framework is expected to contribute to the establishment of personalized combination therapy with optimal treatment effect.

Keywords

Status: accepted

Back to the list of papers