A machine learning method integrating ECG and gated SPECT for cardiac resynchronization therapy decision support

• Published in: European journal of nuclear medicine and molecular imaging Vol. 50; no. 10; pp. 3022 - 3033
• Main Authors: de A. Fernandes, Fernando, Larsen, Kristoffer, He, Zhuo, Nascimento, Erivelton, Peix, Amalia, Sha, Qiuying, Paez, Diana, Garcia, Ernest V., Zhou, Weihua, Mesquita, Claudio T.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.08.2023; Springer Nature B.V
• Subjects: Bayes Theorem; Cardiac Resynchronization Therapy - methods; Cardiology; Congestive heart failure; Criteria; Discriminant analysis; EKG; Electrocardiography; Heart Failure - diagnostic imaging; Heart Failure - therapy; Humans; Imaging; Learning algorithms; Machine Learning; Medicine; Medicine & Public Health; Neural networks; Nuclear Medicine; Oncology; Original Article; Orthopedics; Prospective Studies; Radiology; Therapy; Tomography, Emission-Computed, Single-Photon - methods; Treatment Outcome; Variables; Heart failure; CRT; SPECT; Machine learning
• ISSN: 1619-7070; 1619-7089
• DOI: 10.1007/s00259-023-06259-4

Purpose 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 models which integrate ECG, gated SPECT MPI (GMPS), and clinical variables to predict patients’ response to CRT. Methods This analysis included 153 patients who met criteria for CRT from a prospective cohort study. The variables were used to model 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 as “super-responders” for an increase of LVEF ≥ 15%. For ML, variable selection was applied, and Prediction Analysis of Microarrays (PAM) approach was used to model response while Naïve Bayes (NB) was used to model super-response. These ML models were compared to models obtained with guideline variables. Results PAM had AUC of 0.80 against 0.72 of partial least squares-discriminant analysis with guideline variables ( p  = 0.52). The sensitivity (0.86) and specificity (0.75) were better than for guideline alone, sensitivity (0.75) and specificity (0.24). Neural network with guideline variables was better than NB (AUC = 0.93 vs. 0.87) however without statistical significance ( p  = 0.48). Its sensitivity and specificity (1.0 and 0.75, respectively) were better than guideline alone (0.78 and 0.25, respectively). Conclusions Compared to guideline criteria, ML methods trended toward improved CRT response and super-response prediction. GMPS was central in the acquisition of most parameters. Further studies are needed to validate the models.