Abstract 12872: Machine Learning on Dual-isotope Myocardial Semiconductor SPECT Can Predict Cardiac Prognosis in Patients With Congestive Heart Failure

• Published in: Circulation (New York, N.Y.) N.Y.), 2020-11, Vol.142 (Suppl_3 Suppl 3), p.A12872-A12872
• Main Authors: Shimizu, Masato, cho, shummo, Misu, Yoshiki, Ohmori, Mari, Tateishi, Ryo, Kaneda, Toshio, Yamakami, Yosuke, Shimada, Hiroshi, Manno, Tomoko, Isshiki, Ami, Kimura, Shigeki, Fujii, Hiroyuki, Suzuki, Makoto, Nishizaki, Mitsuhiro, Sasano, Tetsuo
• Format: Article
• Language: English
• ISSN: 0009-7322; 1524-4539
• DOI: 10.1161/circ.142.suppl_3.12872

IntroductionDual-isotope (201TlCl and 123I-β-methyl-P-iodophenyl-pentadecanoic acid (BMIPP) ) single photon emission computed tomography (SPECT) is utilized to estimate not only in patients with ischemic heart disease but with congestive heart failure (CHF). We tried to construct predictive model for cardiac prognosis on the SPECT for cardiac death by machine learning. HypothesisMachine learning is a powerful tool to predict cardiac prognosis in patients with CHF MethodsConsecutive 310 patients who admitted with CHF (77.1±3.1 years, 164 males) were enrolled. After initial treatment, they underwent electrocardiography gated SPECT and observed in median 507 days [IQR165, 1032]. Multivariate Cox regression analysis for cardiac death was performed, and predictive model was constructed by ROC curve analysis and machine learning (Random Forest and Deep Learning). The accuracies (= [True positive + True negative] / Total) of the prediction models were compared with ROC curve model. ResultsThirty-six patients fell into cardiac death. Cox analysis showed Age, left ventricular ejection fraction (LVEF), summed rest score (SRS) of BMIPP, and mismatch score were significant predictors (Hazard ratio1.068, 0.970, 1.032, 1.092, P value