Predictive Analytics for Identification of Patients at Risk for QT Interval Prolongation: A Systematic Review

Prolongation of the heart rate–corrected QT ( QT c) interval increases the risk for torsade de pointes (TdP), a potentially fatal arrhythmia. The likelihood of TdP is higher in patients with risk factors that include female sex, older age, heart failure with reduced ejection fraction, hypokalemia, hypomagnesemia, concomitant administration of two or more QT c interval‐prolonging medications, among others. Assessment and quantification of risk factors may facilitate prediction of patients at highest risk for developing QT c interval prolongation and TdP. Investigators have utilized the field of predictive analytics, which generates predictions using techniques including data mining, modeling, machine learning, and others, to develop methods of risk quantification and prediction of QT c interval prolongation. Predictive analytics have also been incorporated into clinical decision support ( CDS ) tools to alert clinicians regarding patients at increased risk of developing QT c interval prolongation. The objectives of this article are to assess the effectiveness of predictive analytics for identification of patients at risk of drug‐induced QT c interval prolongation and to discuss the efficacy of incorporation of predictive analytics into CDS tools in clinical practice. A systematic review of English‐language articles (human subjects only) was performed, yielding 57 articles, with an additional 4 articles identified from other sources; a total of 10 articles were included in this review. Risk scores for QT c interval prolongation have been developed in various patient populations including those in cardiac intensive care units ( ICU s) and in broader populations of hospitalized or health system patients. One group developed a risk score that includes information regarding genetic polymorphisms; this score significantly predicted TdP. Development of QT c interval prolongation risk prediction models and incorporation of these models into CDS tools reduce the risk of QT c interval prolongation in cardiac ICU s and identify health system patients at increased risk for mortality. The impact of these QT c interval prolongation predictive analytics on overall patient safety outcomes, such as TdP and sudden cardiac death relative to the cost of development and implementation, requires further study.