{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:56:18Z","timestamp":1781535378126,"version":"3.54.5"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We aimed to develop machine learning-based predictive models for identifying inappropriate implantable cardioverter-defibrillator (ICD) therapy. Our study included 182 consecutive cases (average age 62.2\u2009\u00b1\u20094.5\u00a0years, 169 men) and employed 14 non-deep learning models for prediction (hold-out method). These models utilized selected electrocardiogram parameters and clinical features collected after ICD implantation. From the feature importance analysis of the best ML model, we established easily calculable scores. Among the patients, 25 (13.7%) experienced inappropriate therapy, and we identified 16 significant predictors. Using recursive feature elimination with cross-validation, we reduced the features to six with high feature importance: history of atrial arrhythmia (Atr-arrhythm), ischemic cardiomyopathy (ICM), absence of diabetes mellitus (DM), lack of cardiac resynchronization therapy (CRT), V3 ST level at J point (V3 STJ), and V5 R-wave amplitudes (V5R amp). The extra-trees classifier yielded the highest area under receiver operating characteristics curve (AUROC; 0.869 on test data). Thus, the Cardi35 score was defined as [+\u20095.5*Atr-arrhythm \u2212 1.5*CRT\u2009+\u20091.0*V3STJ\u2009+\u20091.0*V5R \u2212 1.0*ICM \u2212 0.5*DM], which demonstrated a hazard ratio of 1.62 (P\u2009&lt;\u20090.001). A cut-off value of the score\u2009+\u20095.5 showed high AUROC (0.826). The ML approach can yield a robust prediction model, and the Cardi35 score was a convenient predictor for inappropriate therapy.<\/jats:p>","DOI":"10.1038\/s41598-023-46095-y","type":"journal-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T10:02:07Z","timestamp":1699610527000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Risk prediction of inappropriate implantable cardioverter-defibrillator therapy using machine learning"],"prefix":"10.1038","volume":"13","author":[{"given":"Ryo","family":"Tateishi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Makoto","family":"Suzuki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masato","family":"Shimizu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroshi","family":"Shimada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takahiro","family":"Tsunoda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroko","family":"Miyazaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshiki","family":"Misu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yosuke","family":"Yamakami","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masao","family":"Yamaguchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nobutaka","family":"Kato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ami","family":"Isshiki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shigeki","family":"Kimura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroyuki","family":"Fujii","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mitsuhiro","family":"Nishizaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tetsuo","family":"Sasano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,9]]},"reference":[{"key":"46095_CR1","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1056\/NEJMoa013474","volume":"346","author":"AJ Moss","year":"2002","unstructured":"Moss, A. J. et al. Prophylactic implantation of a defibrillator in patients with myocardial infarction and reduced ejection fraction. N. Engl. J. Med. 346, 877\u2013883 (2002).","journal-title":"N. Engl. J. Med."},{"key":"46095_CR2","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1056\/NEJMoa043399","volume":"352","author":"GH Bardy","year":"2005","unstructured":"Bardy, G. H. et al. Amiodarone or an implantable cardioverter-defibrillator for congestive heart failure. N. Engl. J. Med. 352, 225\u2013237 (2005).","journal-title":"N. Engl. J. Med."},{"key":"46095_CR3","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1016\/j.jchf.2019.03.019","volume":"7","author":"SL Kristensen","year":"2019","unstructured":"Kristensen, S. L. et al. Risk models for prediction of implantable cardioverter-defibrillator benefit: insights from the Danish Trial. JACC. Heart Fail. 7, 717\u2013724 (2019).","journal-title":"JACC. Heart Fail."},{"key":"46095_CR4","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1093\/europace\/euab012","volume":"23","author":"TE Verstraelen","year":"2021","unstructured":"Verstraelen, T. E. et al. Development and external validation of prediction models to predict implantable cardioverter-defibrillator efficacy in primary prevention of sudden cardiac death. Europace. 23, 887\u2013897 (2021).","journal-title":"Europace."},{"key":"46095_CR5","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.1016\/j.jacc.2007.09.073","volume":"51","author":"JP Daubert","year":"2008","unstructured":"Daubert, J. P. et al. Inappropriate implantable cardioverter-defibrillator shocks in MADIT II: Frequency, mechanisms, predictors, and survival impact. J. Am. Coll. Cardiol. 51, 1357\u20131365 (2008).","journal-title":"J. Am. Coll. Cardiol."},{"key":"46095_CR6","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1016\/j.jacc.2010.06.059","volume":"57","author":"JB van Rees","year":"2011","unstructured":"van Rees, J. B. et al. Inappropriate implantable cardioverter-defibrillator shocks: Incidence, predictors, and impact on mortality. J. Am. Coll. Cardiol. 57, 556\u2013562 (2011).","journal-title":"J. Am. Coll. Cardiol."},{"key":"46095_CR7","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1161\/CIRCULATIONAHA.113.002472","volume":"128","author":"MH Ruwald","year":"2013","unstructured":"Ruwald, M. H. et al. Influence of diabetes mellitus on inappropriate and appropriate implantable cardioverter-defibrillator therapy and mortality in the Multicenter Automatic Defibrillator Implantation Trial-Reduce Inappropriate Therapy (MADIT-RIT) Trial. Circulation. 128, 694\u2013701 (2013).","journal-title":"Circulation."},{"key":"46095_CR8","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1161\/CIRCRESAHA.120.317345","volume":"128","author":"AJ Rogers","year":"2021","unstructured":"Rogers, A. J. et al. Machine learned cellular phenotypes in cardiomyopathy predict sudden death. Circ. Res. 128, 172\u2013184 (2021).","journal-title":"Circ. Res."},{"key":"46095_CR9","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.120.009265","volume":"14","author":"M Firouznia","year":"2021","unstructured":"Firouznia, M. et al. Machine learning-derived fractal features of shape and texture of the left atrium and pulmonary veins from cardiac computed tomography scans are associated with risk of recurrence of atrial fibrillation postablation. Circ. Arrhythm. Electrophysiol. 14, e009265 (2021).","journal-title":"Circ. Arrhythm. Electrophysiol."},{"key":"46095_CR10","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.122.010850","volume":"15","author":"S Tang","year":"2022","unstructured":"Tang, S. et al. Machine learning-enabled multimodal fusion of intra-atrial and body surface signals in prediction of atrial fibrillation ablation outcomes. Circ. Arrhythm. Electrophysiol. 15, e010850 (2022).","journal-title":"Circ. Arrhythm. Electrophysiol."},{"key":"46095_CR11","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1093\/europace\/euy257","volume":"21","author":"S Shakibfar","year":"2019","unstructured":"Shakibfar, S. et al. Predicting electrical storms by remote monitoring of implantable cardioverter-defibrillator patients using machine learning. Europace. 21, 268\u2013274 (2019).","journal-title":"Europace."},{"key":"46095_CR12","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.cvdhj.2022.07.001","volume":"3","author":"M Shimizu","year":"2022","unstructured":"Shimizu, M. et al. Machine learning of microvolt-level 12-lead electrocardiogram can help distinguish takotsubo syndrome and acute anterior myocardial infarction. CardioVasc. Digit. Health J. 3, 179\u2013188 (2022).","journal-title":"CardioVasc. Digit. Health J."},{"key":"46095_CR13","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1038\/bmt.2012.244","volume":"48","author":"Y Kanda","year":"2013","unstructured":"Kanda, Y. Investigation of the freely available easy-to-use software \u201cEZR\u201d for medical statistics. Bone Marrow Transplant. 48, 452\u2013458 (2013).","journal-title":"Bone Marrow Transplant."},{"key":"46095_CR14","unstructured":"R Core Team. R: A Language and Environment for Statistical Computing. (R Foundation for Statistical Computing, 2016). https:\/\/www.R-project.org\/. Accessed 24 Mar 2023."},{"key":"46095_CR15","doi-asserted-by":"publisher","first-page":"012015","DOI":"10.1088\/1742-6596\/1828\/1\/012015","volume":"1828","author":"U Gain","year":"2021","unstructured":"Gain, U. & Hotti, V. Low-code AutoML-augmented data pipeline \u2013 a review and experiments. J. Phys. Conf. Ser. 1828, 012015 (2021).","journal-title":"J. Phys. Conf. Ser."},{"key":"46095_CR16","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.amjcard.2020.07.048","volume":"133","author":"HC Lee","year":"2020","unstructured":"Lee, H. C. et al. Prediction of 1-year mortality from acute myocardial infarction using machine learning. Am. J. Cardiol. 133, 23\u201331 (2020).","journal-title":"Am. J. Cardiol."},{"key":"46095_CR17","doi-asserted-by":"crossref","unstructured":"Akiba, T. et al. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; Anchorage, AK, USA. 4\u20138 August 2019. 2623\u20132631 (2019).","DOI":"10.1145\/3292500.3330701"},{"key":"46095_CR18","doi-asserted-by":"publisher","first-page":"6531","DOI":"10.1038\/s41598-023-33045-x","volume":"13","author":"D Gogishvili","year":"2023","unstructured":"Gogishvili, D. et al. Discovery of novel CSF biomarkers to predict progression in dementia using machine learning. Sci. Rep. 13, 6531 (2023).","journal-title":"Sci. Rep."},{"key":"46095_CR19","first-page":"27","volume":"30","author":"SM Lundberg","year":"2017","unstructured":"Lundberg, S. M. & Lee, S. A unified approach to interpreting model predictions. Adv. Neural Inf. Process Syst. 30, 27 (2017).","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"46095_CR20","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1111\/j.1540-8159.2005.00195.x","volume":"28","author":"P Alter","year":"2005","unstructured":"Alter, P., Waldhans, S., Plachta, E., Moosdorf, R. & Grimm, W. Complications of implantable cardioverter defibrillator therapy in 440 consecutive patients. Pacing Clin. Electrophysiol. 28, 926\u2013932 (2005).","journal-title":"Pacing Clin. Electrophysiol."},{"key":"46095_CR21","doi-asserted-by":"publisher","first-page":"1820","DOI":"10.1016\/j.hrthm.2017.08.017","volume":"14","author":"D Birnie","year":"2017","unstructured":"Birnie, D. et al. Continuous optimization of cardiac resynchronization therapy reduces atrial fibrillation in heart failure patients: Results of the Adaptive Cardiac Resynchronization Therapy Trial. Heart Rhythm. 14, 1820\u20131825 (2017).","journal-title":"Heart Rhythm."},{"key":"46095_CR22","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1016\/j.amjcard.2015.05.060","volume":"116","author":"M Proietti","year":"2015","unstructured":"Proietti, M. et al. Frequency of left ventricular hypertrophy in non-valvular atrial fibrillation. Am. J. Cardiol. 116, 877\u2013882 (2015).","journal-title":"Am. J. Cardiol."},{"key":"46095_CR23","doi-asserted-by":"publisher","first-page":"1149","DOI":"10.1016\/j.jacc.2007.10.062","volume":"51","author":"J Francis","year":"2008","unstructured":"Francis, J. et al. Atrial fibrillation and Brugada syndrome. J. Am. Coll. Cardiol. 51, 1149\u20131153 (2008).","journal-title":"J. Am. Coll. Cardiol."},{"key":"46095_CR24","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1038\/s41591-018-0240-2","volume":"25","author":"ZI Attia","year":"2019","unstructured":"Attia, Z. I. et al. Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram. Nat. Med. 25, 70\u201374 (2019).","journal-title":"Nat. Med."},{"key":"46095_CR25","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1536\/ihj.53.276","volume":"53","author":"A Satoh","year":"2012","unstructured":"Satoh, A. et al. Prediction of inappropriate implantable cardioverter-defibrillator therapies through parameters obtained in a simple exercise stress test. Int. Heart J. 53, 276\u2013281 (2012).","journal-title":"Int. Heart J."},{"key":"46095_CR26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0169933","volume":"12","author":"J Kornej","year":"2017","unstructured":"Kornej, J. et al. The APPLE score\u2014A novel score for the prediction of rhythm outcomes after repeat catheter ablation of atrial fibrillation. PLOS. ONE. 12, e0169933 (2017).","journal-title":"PLOS. ONE."},{"key":"46095_CR27","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1016\/j.hrthm.2014.12.034","volume":"12","author":"V Jacobs","year":"2015","unstructured":"Jacobs, V. et al. The impact of risk score (CHADS2 versus CHA2DS2-VASc) on long-term outcomes after atrial fibrillation ablation. Heart Rhythm. 12, 681\u2013686 (2015).","journal-title":"Heart Rhythm."},{"key":"46095_CR28","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.119.008213","volume":"13","author":"JK Shade","year":"2020","unstructured":"Shade, J. K. et al. Preprocedure application of machine learning and mechanistic simulations predicts likelihood of paroxysmal atrial fibrillation recurrence following pulmonary vein isolation. Circ. Arrhythm. Electrophysiol. 13, e008213 (2020).","journal-title":"Circ. Arrhythm. Electrophysiol."},{"key":"46095_CR29","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.amjcard.2015.10.022","volume":"117","author":"KG Skaarup","year":"2016","unstructured":"Skaarup, K. G. et al. Diagnosing paroxysmal atrial fibrillation in patients with ischemic strokes and transient ischemic attacks using echocardiographic measurements of left atrium function. Am. J. Cardiol. 117, 91\u201399 (2016).","journal-title":"Am. J. Cardiol."},{"key":"46095_CR30","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/S0140-6736(19)31721-0","volume":"394","author":"ZI Attia","year":"2019","unstructured":"Attia, Z. I. et al. An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: A retrospective analysis of outcome prediction. Lancet 394, 861\u2013867 (2019).","journal-title":"Lancet"},{"key":"46095_CR31","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1161\/CIRCULATIONAHA.121.056072","volume":"145","author":"A Yafasova","year":"2022","unstructured":"Yafasova, A. et al. Long-term follow-up of Danish (the Danish study to assess the efficacy of ICDs in patients with nonischemic systolic heart failure on mortality). Circulation 145, 427\u2013436 (2022).","journal-title":"Circulation"},{"key":"46095_CR32","doi-asserted-by":"publisher","first-page":"2353","DOI":"10.1161\/CIRCULATIONAHA.112.113233","volume":"126","author":"MA Rosenberg","year":"2012","unstructured":"Rosenberg, M. A. & Manning, W. J. Diastolic dysfunction and risk of atrial fibrillation: A mechanistic appraisal. Circulation. 126, 2353\u20132362 (2012).","journal-title":"Circulation."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-46095-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-46095-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-46095-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T10:05:33Z","timestamp":1699610733000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-46095-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,9]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["46095"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-46095-y","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,9]]},"assertion":[{"value":"27 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"19586"}}