Computational Drug Repositioning Using Continuous Self-Controlled Case Series.

Area of Science:

• Pharmacology
• Biomedical Informatics
• Health Informatics

Background:

• Drug repositioning accelerates the discovery of new therapeutic indications for existing drugs.
• Electronic Health Records (EHRs) contain rich, longitudinal patient data valuable for drug discovery.
• Computational approaches are essential for analyzing large-scale, heterogeneous biomedical data.

Purpose of the Study:

• To develop and evaluate a novel computational method for drug repositioning using EHR data.
• To identify existing drugs that may effectively control Fasting Blood Glucose (FBG) levels.
• To leverage temporal patient data for discovering new drug indications.

Main Methods:

• A Continuous Self-controlled Case Series (CSCCS) model was developed for computational drug repositioning (CDR).
• The CSCCS model utilizes patient-level temporal information from EHRs, including physiological measurements and drug prescriptions.
• The model was applied to the Marshfield Clinic EHR dataset for evaluating its efficacy in identifying glucose-lowering drugs.

Main Results:

• The CSCCS model successfully rediscovered known drugs indicated for blood glucose control.
• The model identified additional drugs with emerging literature support for FBG level management.
• This demonstrates the potential of the CSCCS model in uncovering novel therapeutic applications.

Conclusions:

• The Continuous Self-controlled Case Series (CSCCS) model is a viable computational approach for drug repositioning.
• EHR data, when analyzed with appropriate temporal models, can effectively identify drug-indication relationships.
• This methodology holds promise for accelerating the discovery of new uses for existing medications, particularly for metabolic conditions.