Background-Cardiac resynchronization therapy (CRT) has significant non-response rates. We assessed whether machine learning could predict CRT response beyond current guidelines. Methods-We analyzed CRT patients from Cleveland Clinic and Johns Hopkins. A training cohort was created from all Johns Hopkins patients and an equal number of randomly sampled Cleveland Clinic patients. All remaining patients comprised the testing cohort. Response was defined as ≥10% increase in left ventricular (LV) ejection fraction. Machine learning models were developed to predict CRT response using different combinations of classification algorithms and clinical variable sets on the training cohort. The model with the highest area under curve (AUC) was evaluated on the testing cohort. Probability of response was used to predict survival free from a composite endpoint of death, heart transplant, or placement of LV assist device. Predictions were compared to current guidelines.
Background:
Cardiac resynchronization therapy (CRT) improves heart failure outcomes but has significant nonresponse rates, highlighting limitations in ECG selection criteria: QRS duration (QRSd) ≥150 ms and subjective labeling of left bundle branch block (LBBB). We explored unsupervised machine learning of ECG waveforms to identify CRT subgroups that may differentiate outcomes beyond QRSd and LBBB.
Methods:
We retrospectively analyzed 946 CRT patients with conduction delay. Principal component analysis (PCA) dimensionality reduction obtained a 2-dimensional representation of preCRT 12-lead QRS waveforms.
k
-means clustering of the 2-dimensional PCA representation of 12-lead QRS waveforms identified 2 patient subgroups (QRS PCA groups). Vectorcardiographic QRS area was also calculated. We examined following 2 primary outcomes: (1) composite end point of death, left ventricular assist device, or heart transplant, and (2) degree of echocardiographic left ventricular ejection fraction (LVEF) change after CRT.
Results:
Compared with QRS PCA Group 2 (
n
=425), Group 1 (
n
=521) had lower risk for reaching the composite end point (HR, 0.44 [95% CI, 0.38–0.53];
P
<0.001) and experienced greater mean LVEF improvement (11.1±11.7% versus 4.8±9.7%;
P
<0.001), even among patients with LBBB with QRSd ≥150 ms (HR, 0.42 [95% CI, 0.30–0.57];
P
<0.001; mean LVEF change 12.5±11.8% versus 7.3±8.1%;
P
=0.001). QRS area also stratified outcomes but had significant differences from QRS PCA groups. A stratification scheme combining QRS area and QRS PCA group identified patients with LBBB with similar outcomes to non-LBBB patients (HR, 1.32 [95% CI, 0.93–1.62]; difference in mean LVEF change: 0.8% [95% CI, −2.1% to 3.7%]). The stratification scheme also identified patients with LBBB with QRSd <150 ms with comparable outcomes to patients with LBBB with QRSd ≥150 ms (HR, 0.93 [95% CI, 0.67–1.29]; difference in mean LVEF change: −0.2% [95% CI, −2.7% to 3.0%]).
Conclusions:
Unsupervised machine learning of ECG waveforms identified CRT subgroups with relevance beyond LBBB and QRSd. This method may assist in objective classification of bundle branch block morphology in CRT.
ObjectiveDetermine the prognostic impact of scar quantification (scar %) by cardiac magnetic resonance (CMR) in predicting heart failure admission, death and left ventricular (LV) function improvement following cardiac resynchronisation therapy (CRT), after controlling for the presence of left bundle branch block (LBBB), QRS duration (QRSd) and LV lead tip location and polarity.MethodsConsecutive patients who underwent CMR between 2002 and 2014 followed by CRT were included. The primary endpoint was death or heart failure admission. The secondary endpoint was change in ejection fraction (EF) ≥3 months after CRT. Cox proportional hazards, linear regression models and change in the area under the receiver operating characteristic curve (AUC) were used.ResultsA total of 84 patients were included (63% male, 51% with ischaemic cardiomyopathy). After adjusting for clinical factors, presence of LBBB and QRSd and LV lead tip location and polarity, greater scar % remained associated with a higher risk for clinical events (HR=1.06; 95% CI 1.02 to 1.10; p<0.001) and a smaller improvement in EF (slope: −0.61%; 95% CI −0.93% to 0.29%; p<0.001). When adding scar % to QRSd and LBBB, there was significant improvement in predicting clinical events at 3 years (AUC increased to 0.831 from 0.638; p=0.027) and EF increase ≥10% (AUC 0.869 from 0.662; p=0.007).ConclusionScar quantification by CMR has an incremental value in predicting response to CRT, in terms of heart failure admission, death and EF improvement, independent of the presence of LBBB, QRSd, LV lead tip location and polarity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.