Key result
A machine learning model integrating ECG, GMPS, and clinical variables predicted cardiac resynchronization therapy response with an AUC of 0.80 compared to 0.71 for guideline criteria (p=0.47).
Why the study?
Mechanical dyssynchrony may predict CRT responders, prompting the development and validation of machine learning models integrating ECG, gated SPECT MPI, and clinical variables to predict CRT response.
Do machine learning models integrating ECG, GMPS, and clinical variables improve the prediction of CRT response compared to standard guideline criteria in patients eligible for CRT?
Cohort (n=153)
Yes
Do machine learning models integrating ECG, GMPS, and clinical variables improve the prediction of CRT response compared to standard guideline criteria in patients eligible for CRT?
Answers are grounded in this paper and cite their sources.
Machine learning models integrating ECG and gated SPECT MPI trend towards improved prediction of CRT response and super-response compared to standard guideline criteria.
Cardiac resynchronization therapy (CRT) has been established as an important therapy for heart failure. Mechanical dyssynchrony has the potential to predict responders to CRT. The aim of this study was to report the development and the validation of machine learning (ML) models which integrates ECG, gated SPECT MPI (GMPS) and clinical variables to predict patients' response to CRT. This analysis included 153 patients who met criteria for CRT from a prospective cohort study. The variables were used to modeling predictive methods for CRT. Patients were classified as responders for an increase of LVEF>=5% at follow-up. In a second analysis, patients were classified super-responders for increase of LVEF>=15%. For ML, variable selection was applied, and Prediction Analysis of Microarrays (PAM) approach was used for response modeling while Naive Bayes (NB) was used for super-response. They were compared to models obtained with guideline variables. PAM had AUC of 0.80 against 0.71 of logistic regression with guideline variables (p = 0.47). The sensitivity (0.86) and specificity (0.75) were better than for guideline alone, sensitivity (0.72) and specificity (0.22). Neural network with guideline variables outperformed NB (AUC = 0.87 vs 0.86; p = 0.88). Its sensitivity and specificity (1.0 and 0.75, respectively) was better than guideline alone (0.40 and 0.06, respectively). Compared to guideline criteria, ML methods trended towards improved CRT response and super-response prediction. GMPS had a central role in the acquisition of most parameters. Further studies are needed to validate the models.
No takes yet. Share an insight, caveat, or question.
Fernandes et al. (2022) conducted a cohort in Heart failure meeting criteria for Cardiac Resynchronization Therapy (CRT) (n=153). Machine learning models (PAM) integrating ECG, GMPS, and clinical variables vs. Guideline criteria (QRSd, LVEF, LBBB, NYHA) was evaluated on Prediction of CRT response (LVEF increase ≥ 5%) measured by Area Under the Curve (AUC) (p=0.47). A machine learning model integrating ECG, GMPS, and clinical variables predicted cardiac resynchronization therapy response with an AUC of 0.80 compared to 0.71 for guideline criteria (p=0.47).
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: