Combining systems pharmacology modeling with machine learning to identify groups at risk of drug-induced arrhythmia

  • Varshneya, Meera (PI)

Project Details


Episodes of Torsades de Pointes (TdP), a life threatening ventricular arrhythmia, are a common side effect of several antiarrhythmics. Although TdP only occurs in about 1-5% of the exposed population, it can lead to ventricular fibrillation and sudden cardiac death. Moreover, in recent years antibiotics, antipsychotics, antihistamines and other non-cardiovascular therapies have been reported to cause these extreme adverse events. What are the physiological and clinical traits that define this rare at-risk population? The inability to answer this question halts any considerable progress in preventing drug-induced TdP (diTdP). It highlights the idea of precision medicine and the importance of identifying relevant sub-groups of patients likely to benefit from a treatment versus those who are highly susceptible to a drug-induced adverse event. The current standards, a lengthened action potential (AP) duration of cells and a longer QT interval on an echocardiogram (ECG) have proven ineffective. Thus, there is a need to extract pertinent information from cell and tissue level simulations to detect patterns only apparent in the high-risk population. To analyze this concept, I plan to (1) explain at a mechanistic level the differences between the healthy and at-risk patients, (2) identify important AP and ECG markers that can predict risk early on, and (3) connect the physiological and clinical findings to improve the profile and description of the high-risk population. I will combine two complementary computational techniques: (1) simulations with mechanistic, quantitative systems pharmacology (QSP) models of heart cells and tissues; and (2) advanced machine learning approaches that can identify hidden patterns. (AHA Program: Predoctoral Fellowship)

Effective start/end date1/01/1930/11/19


  • American Heart Association: $54,000.00


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.