High‐Throughput Algorithm for Discovering New Drug Indications by Utilizing Large‐Scale Electronic Medical Record Data

Abstract

Drug repositioning is an effective way to mitigate the production problem in the pharmaceutical industry. Electronic medical record (EMR) databases harbor a large amount of data on drug prescriptions and laboratory test results and may thus be useful for finding new indications for existing drugs. Here, we present a novel high-throughput data-driven algorithm that identifies and prioritizes drug candidates that show significant effects on specific clinical indicators by utilizing large-scale EMR data. We chose four laboratory tests as clinical indicators: hemoglobin A1c (HbA1c), low-density lipoprotein (LDL) cholesterol, triglycerides (TGs), and high-density lipoprotein (HDL) cholesterol. From a 5-year EMR database, we generated datasets consisting of paired data with averaged measurement values during on and off each drug in each patient, adjusted for co-administered drug effects at each timepoint, and applied one sample t-test with the Bonferroni correction for statistical analysis. Among 1,774 drugs, 45 were associated with increases in HDL cholesterol, and 41, 146, and 65 were associated with reductions in HbA1c, LDL cholesterol, and TGs, respectively. We compared the list of candidate drugs with that of drugs indicated for relevant clinical conditions and found that the algorithm had high values for both sensitivity (range 0.95-1.00) and negative predictive value (range 0.95-1.00). Our algorithm was able to rediscover well-known drugs that are used for diabetes and dyslipidemia while revealing potential candidates without current indications but have shown promising results in the literature. Our algorithm may facilitate the repositioning of drugs with proven safety profiles. The pharmaceutical industry faces a productivity problem in delivering new drugs to the market. Current operations on de novo drug discovery and development are costly, time-consuming, and risky. 1 Therefore, pharmaceutical companies and public-sector researchers are seeking creative methods for drug discovery. 2 In this era of big data, abundant data sources that harbor rich amounts of drug-related information are emerging. As such, effective mining of large-scale heterogeneous drug-related data sources has become an active research area for drug repositioning, which is gaining a great deal of attention. 1 Drug

Computational drug repurposing based on electronic health records: a scoping review

“…Of the surveyed studies, five studies utilized NLP to process their data, seven used standardization, and four dealt with temporal data. We note that three studies implemented more than one data processing method (e.g., MedEx and RxNorm CUI were used to extract and standardize medication information 19 , and the Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) was used for both drug prescription and laboratory tests 26 ).

Fig.

…”

“…Figure 5 shows the disease targeted. The most common repurposing target was diabetes-related, consisting of 10 out of the 33 publications 17 , 26 , 29 , 32 , 37 – 42 , including type 2 diabetes 37 , 41 , 42 , gestational diabetes 17 , diabetes (unspecified) 26 , 29 , diabetes-related tests including glycated hemoglobin 32 and Fasting Blood Glucose 38 – 40 . Six publications did not focus on any specific diseases 21 , 22 , 27 , 28 , 43 , 44 .…”

“…Cardiovascular-related diseases are also focused on in seven publications. Specifically, Jang et al 41 targeted congestive heart failure, myocardial ischemia, and stroke, Ghalwash et al 32 targeted low-density lipoprotein, which is a risk factor for cardiovascular and vascular diseases, Kim et al 26 targeted dyslipidemia, Cai et al 34 targeted cardiovascular disease, Liu et al 33 targeted coronary artery disease, Nordon et al 29 targeted hypertension, and 366 targeted coronary heart disease, congestive heart failure, heart attack, and stroke. In addition, there are four publications targeting at cancer 18 , 19 , 35 , 45 , three targeting at COVID 36 , 46 , 47 , two targeting at asthma 41 , 42 .…”

A Study on Methodologies of Drug Repositioning Using Biomedical Big Data: A Focus on Diabetes Mellitus

“…Recently, an algorithm was developed to identify drug candidates effective for DM and dyslipidemia by analyzing large amounts of EMR data and clinical trial results [ 86 ]. This algorithm can be used to monitor the post-marketing safety of drugs and re-evaluate their effectiveness in clinical trials to ultimately discover new indications [ 86 ]. Metformin has been suggested as a repositioning candidate for cancer treatment because it reduces cancer incidence and mortality [ 41 ].…”

Information Sharing and Privacy Protection of Electronic Nursing Record Management System

“…Responding to the classification and protection requirements of privacy-sensitive information in EMRs, Blondon and Ehrler [14] proposed a recognition and classification algorithm for medical terms that represent patient health-sensitive information in EMR texts and performed selective encryption and confidential search of the recognized words. Kim et al [15] constructed an EMR management system based on the browser/server (B/S) architecture.…”