Can machine learning improve patient selection for cardiac resynchronization therapy?

Abstract

RationaleMultiple clinical trials support the effectiveness of cardiac resynchronization therapy (CRT); however, optimal patient selection remains challenging due to substantial treatment heterogeneity among patients who meet the clinical practice guidelines.ObjectiveTo apply machine learning to create an algorithm that predicts CRT outcome using electronic health record (EHR) data avaible before the procedure.Methods and resultsWe applied machine learning and natural language processing to the EHR of 990 patients who received CRT at two academic hospitals between 2004–2015. The primary outcome was reduced CRT benefit, defined as <0% improvement in left ventricular ejection fraction (LVEF) 6–18 months post-procedure or death by 18 months. Data regarding demographics, laboratory values, medications, clinical characteristics, and past health services utilization were extracted from the EHR available before the CRT procedure. Bigrams (i.e., two-word sequences) were also extracted from the clinical notes using natural language processing. Patients accrued on average 75 clinical notes (SD, 29) before the procedure including data not captured anywhere else in the EHR. A machine learning model was built using 80% of the patient sample (training and validation dataset), and tested on a held-out 20% patient sample (test dataset). Among 990 patients receiving CRT the mean age was 71.6 (SD, 11.8), 78.1% were male, 87.2% non-Hispanic white, and the mean baseline LVEF was 24.8% (SD, 7.69). Out of 990 patients, 403 (40.7%) were identified as having a reduced benefit from the CRT device (<0% LVEF improvement in 25.2%, death by 18 months in 15.6%). The final model identified 26% of these patients at a positive predictive value of 79% (model performance: Fβ (β = 0.1): 77%; recall 0.26; precision 0.79; accuracy 0.65).ConclusionsA machine learning model that leveraged readily available EHR data and clinical notes identified a subset of CRT patients who may not benefit from CRT before the procedure.

Using Machine-Learning for Prediction of the Response to Cardiac Resynchronization Therapy: the SMART-AV Study

“…Kalscheur et al analyzed 595 COMPANION NYHA III/IV patients, 11 Cikes et al studied 1106 MADIT-CRT NYHA class ≤ II patients, 14 Feeny et al evaluated 470 NYHA I-IV patients from an observational cohort, and Hu et al retrospectively analyzed 990 predominately NYHA II-III patients from a single-center cohort. 32 Of note, all previous studies considered long-term CRT benefits, answering a question of CRT candidate selection. In contrast, our prediction model is focusing on a short-term CRT response and can help planning the CRT delivery strategy, in addition to selecting the most appropriate CRT candidate.…”

Artificial Intelligence–Aided Precision Medicine for COVID-19: Strategic Areas of Research and Development

“…Risk prediction models are not new to the AI-aided health care approach. They have already been successfully utilized for tasks such as predicting the risk of developing cancer [ 41 , 42 ] and identifying which patients are likely to benefit from heart-related procedures [ 43 ]. However, the COVID-19 crisis has accelerated the utilization of such models.…”

Clinical Utility of Body Surface Potential Mapping in CRT Patients

“…[ 41 ] Hu et al successfully applied machine learning techniques with natural language processing to identify a subgroup of patients who were unlikely to benefit from CRT. [ 42 ] Machine learning models that relied on pre-implantation clinical, echocardiographic, and ECG characteristics produced understandably better predictions of CRT benefit than those that relied on ECG parameters. [ 41 , 42 ] This integration approach based on analysis of many clinical parameters may provide a new opportunity for personalised management of patients with HF.…”