{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T02:59:42Z","timestamp":1785207582754,"version":"3.55.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000050","name":"National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["HL144927"],"award-info":[{"award-number":["HL144927"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["GM121342"],"award-info":[{"award-number":["GM121342"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Cardiac Resynchronization Therapy (CRT) is a widely used, device-based therapy for patients with left ventricle (LV) failure. Unfortunately, many patients do not benefit from CRT, so there is potential value in identifying this group of non-responders before CRT implementation. Past studies suggest that predicting CRT response will require diverse variables, including demographic, biomarker, and LV function data. Accordingly, the objective of this study was to integrate diverse variable types into a machine learning algorithm for predicting individual patient responses to CRT.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>We built an ensemble classification algorithm using previously acquired data from the SMART-AV CRT clinical trial (n\u2009=\u2009794 patients). We used five-fold stratified cross-validation on 80% of the patients (n\u2009=\u2009635) to train the model with variables collected at 0 months (before initiating CRT), and the remaining 20% of the patients (n\u2009=\u2009159) were used as a hold-out test set for model validation. To improve model interpretability, we quantified feature importance values using SHapley Additive exPlanations (SHAP) analysis and used Local Interpretable Model-agnostic Explanations (LIME) to explain patient-specific predictions.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Our classification algorithm incorporated 26 patient demographic and medical history variables, 12 biomarker variables, and 18 LV functional variables, which yielded correct prediction of CRT response in 71% of patients. Additional patient stratification to identify the subgroups with the highest or lowest likelihood of response showed 96% accuracy with 22 correct predictions out of 23 patients in the highest and lowest responder groups.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>Computationally integrating general patient characteristics, comorbidities, therapy history, circulating biomarkers, and LV function data available before CRT intervention can improve the prediction of individual patient responses.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12911-022-02015-0","type":"journal-article","created":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T08:04:07Z","timestamp":1667203447000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Interpretable machine learning predicts cardiac resynchronization therapy responses from personalized biochemical and biomechanical features"],"prefix":"10.1186","volume":"22","author":[{"given":"Anamul","family":"Haque","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Doug","family":"Stubbs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nina C.","family":"Hubig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francis G.","family":"Spinale","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William J.","family":"Richardson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,31]]},"reference":[{"issue":"22","key":"2015_CR1","doi-asserted-by":"publisher","first-page":"2407","DOI":"10.1161\/CIRCULATIONAHA.112.000112","volume":"128","author":"FW Prinzen","year":"2013","unstructured":"Prinzen FW, Vernooy K, Auricchio A. Cardiac resynchronization therapy: state-of-the-art of current applications, guidelines, ongoing trials, and areas of controversy. Circulation. 2013;128(22):2407\u201318. doi:https:\/\/doi.org\/10.1161\/CIRCULATIONAHA.112.000112.","journal-title":"Circulation"},{"issue":"22","key":"2015_CR2","doi-asserted-by":"publisher","first-page":"2502","DOI":"10.1001\/jama.297.22.2502","volume":"297","author":"FA McAlister","year":"2007","unstructured":"McAlister FA, Ezekowitz J, Hooton N, et al. Cardiac resynchronization therapy for patients with left ventricular systolic dysfunction: a systematic review. JAMA. 2007;297(22):2502\u201314. doi:https:\/\/doi.org\/10.1001\/jama.297.22.2502.","journal-title":"JAMA"},{"issue":"11","key":"2015_CR3","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1093\/eurheartj\/ehi826","volume":"27","author":"NM Hawkins","year":"2006","unstructured":"Hawkins NM, Petrie MC, MacDonald MR, Hogg KJ, McMurray JJ. Selecting patients for cardiac resynchronization therapy: electrical or mechanical dyssynchrony? Eur Heart J. 2006;27(11):1270\u201381. doi:https:\/\/doi.org\/10.1093\/eurheartj\/ehi826.","journal-title":"Eur Heart J"},{"issue":"19","key":"2015_CR4","doi-asserted-by":"publisher","first-page":"1463","DOI":"10.1093\/eurheartj\/ehw270","volume":"38","author":"C Daubert","year":"2017","unstructured":"Daubert C, Behar N, Martins RP, Mabo P, Leclercq C. Avoiding non-responders to cardiac resynchronization therapy: a practical guide. Eur Heart J. 2017;38(19):1463\u201372. doi:https:\/\/doi.org\/10.1093\/eurheartj\/ehw270.","journal-title":"Eur Heart J"},{"issue":"Suppl 2","key":"2015_CR5","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1111\/j.1540-8159.2006.00486.x","volume":"29","author":"A Achilli","year":"2006","unstructured":"Achilli A, Peraldo C, Sassara M, et al. Prediction of response to cardiac resynchronization therapy: the selection of candidates for CRT (SCART) study. Pacing Clin Electrophysiol. 2006;29(Suppl 2):11\u20139. doi:https:\/\/doi.org\/10.1111\/j.1540-8159.2006.00486.x.","journal-title":"Pacing Clin Electrophysiol"},{"issue":"1","key":"2015_CR6","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.cell.2020.03.022","volume":"181","author":"J Goecks","year":"2020","unstructured":"Goecks J, Jalili V, Heiser LM, Gray JW. How Machine Learning Will Transform Biomedicine. Cell. 2020;181(1):92\u2013101. doi:https:\/\/doi.org\/10.1016\/j.cell.2020.03.022.","journal-title":"Cell"},{"issue":"4","key":"2015_CR7","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1177\/0840470419848428","volume":"32","author":"M Lavigne","year":"2019","unstructured":"Lavigne M, Mussa F, Creatore MI, Hoffman SJ, Buckeridge DL. A population health perspective on artificial intelligence. Health Manage Forum. 2019;32(4):173\u20137. doi:https:\/\/doi.org\/10.1177\/0840470419848428.","journal-title":"Health Manage Forum"},{"issue":"10","key":"2015_CR8","doi-asserted-by":"publisher","first-page":"e0222397","DOI":"10.1371\/journal.pone.0222397","volume":"14","author":"SY Hu","year":"2019","unstructured":"Hu SY, Santus E, Forsyth AW, et al. Can machine learning improve patient selection for cardiac resynchronization therapy? PLoS ONE. 2019;14(10):e0222397. doi:https:\/\/doi.org\/10.1371\/journal.pone.0222397. Published 2019 Oct 3.","journal-title":"PLoS ONE"},{"issue":"7","key":"2015_CR9","doi-asserted-by":"publisher","first-page":"e007316","DOI":"10.1161\/CIRCEP.119.007316","volume":"12","author":"AK Feeny","year":"2019","unstructured":"Feeny AK, Rickard J, Patel D, et al. Machine Learning Prediction of Response to Cardiac Resynchronization Therapy: Improvement Versus Current Guidelines. Circ Arrhythm Electrophysiol. 2019;12(7):e007316. doi:https:\/\/doi.org\/10.1161\/CIRCEP.119.007316.","journal-title":"Circ Arrhythm Electrophysiol"},{"issue":"1","key":"2015_CR10","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1002\/ejhf.1333","volume":"21","author":"M Cikes","year":"2019","unstructured":"Cikes M, Sanchez-Martinez S, Claggett B, et al. Machine learning-based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy. Eur J Heart Fail. 2019;21(1):74\u201385. doi:https:\/\/doi.org\/10.1002\/ejhf.1333.","journal-title":"Eur J Heart Fail"},{"issue":"1","key":"2015_CR11","doi-asserted-by":"publisher","first-page":"e005499","DOI":"10.1161\/CIRCEP.117.005499","volume":"11","author":"MM Kalscheur","year":"2018","unstructured":"Kalscheur MM, Kipp RT, Tattersall MC, et al. Machine Learning Algorithm Predicts Cardiac Resynchronization Therapy Outcomes: Lessons From the COMPANION Trial. Circ Arrhythm Electrophysiol. 2018;11(1):e005499. doi:https:\/\/doi.org\/10.1161\/CIRCEP.117.005499.","journal-title":"Circ Arrhythm Electrophysiol"},{"issue":"12","key":"2015_CR12","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1016\/j.jacep.2021.06.009","volume":"7","author":"SJ Howell","year":"2021","unstructured":"Howell SJ, Stivland T, Stein K, Ellenbogen KA, Tereshchenko LG. Using Machine-Learning for Prediction of the Response to Cardiac Resynchronization Therapy: The SMART-AV Study. JACC Clin Electrophysiol. 2021;7(12):1505\u201315. doi:https:\/\/doi.org\/10.1016\/j.jacep.2021.06.009.","journal-title":"JACC Clin Electrophysiol"},{"key":"2015_CR13","doi-asserted-by":"publisher","first-page":"611055","DOI":"10.3389\/fcvm.2021.611055","volume":"8","author":"M Tokodi","year":"2021","unstructured":"Tokodi M, Behon A, Merkel ED, et al. Sex-Specific Patterns of Mortality Predictors Among Patients Undergoing Cardiac Resynchronization Therapy: A Machine Learning Approach. Front Cardiovasc Med. 2021;8:611055. doi:https:\/\/doi.org\/10.3389\/fcvm.2021.611055. Published 2021 Feb 25.","journal-title":"Front Cardiovasc Med"},{"issue":"3","key":"2015_CR14","doi-asserted-by":"publisher","first-page":"989","DOI":"10.1007\/s10554-020-02083-1","volume":"37","author":"A Gallard","year":"2021","unstructured":"Gallard A, Hubert A, Smiseth O, et al. Prediction of response to cardiac resynchronization therapy using a multi-feature learning method. Int J Cardiovasc Imaging. 2021;37(3):989\u201398. doi:https:\/\/doi.org\/10.1007\/s10554-020-02083-1.","journal-title":"Int J Cardiovasc Imaging"},{"issue":"5","key":"2015_CR15","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1016\/j.hrthm.2018.11.026","volume":"16","author":"FG Spinale","year":"2019","unstructured":"Spinale FG, Meyer TE, Stolen CM, et al. Development of a biomarker panel to predict cardiac resynchronization therapy response: Results from the SMART-AV trial. Heart Rhythm. 2019;16(5):743\u201353. doi:https:\/\/doi.org\/10.1016\/j.hrthm.2018.11.026.","journal-title":"Heart Rhythm"},{"issue":"1","key":"2015_CR16","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1186\/s12911-020-01332-6","volume":"20","author":"J Amann","year":"2020","unstructured":"Amann J, Blasimme A, Vayena E, Frey D, Madai VI. Precise4Q consortium. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Med Inform Decis Mak. 2020;20(1):310. doi:https:\/\/doi.org\/10.1186\/s12911-020-01332-6. Published 2020 Nov 30.","journal-title":"BMC Med Inform Decis Mak"},{"key":"2015_CR17","doi-asserted-by":"publisher","first-page":"569","DOI":"10.3233\/SHTI220527","volume":"294","author":"M Aj\u010devi\u0107","year":"2022","unstructured":"Aj\u010devi\u0107 M, Miladinovi\u0107 A, Furlanis G, et al. Wake-up Stroke Outcome Prediction by Interpretable Decision Tree Model. Stud Health Technol Inform. 2022;294:569\u201370. doi:https:\/\/doi.org\/10.3233\/SHTI220527.","journal-title":"Stud Health Technol Inform"},{"key":"2015_CR18","doi-asserted-by":"publisher","unstructured":"Elshawi R, Al-Mallah MH, Sakr S. On the interpretability of machine learning-based model for predicting hypertension. BMC Med Inform Decis Mak. 2019;19(1):146. Published 2019 Jul 29. doi:https:\/\/doi.org\/10.1186\/s12911-019-0874-0.","DOI":"10.1186\/s12911-019-0874-0"},{"issue":"25","key":"2015_CR19","doi-asserted-by":"publisher","first-page":"2660","DOI":"10.1161\/CIRCULATIONAHA.110.992552","volume":"122","author":"K Ellenbogen","year":"2010","unstructured":"Ellenbogen K, Gold M, Meyer T, et al. Primary results from the SmartDelay determined AV optimization: a comparison to other AV delay methods used in cardiac resynchronization therapy (SMART-AV) trial: a randomized trial comparing empirical, echocardiography-guided, and algorithmic atrioventri. Circulation. 2010;122(25):2660\u20138. doi:https:\/\/doi.org\/10.1161\/CIRCULATIONAHA.110.992552.","journal-title":"Circulation"},{"key":"2015_CR20","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: Machine Learning in Python. J Mach Learn Res. 2011;12(85):2825\u20132830. http:\/\/jmlr.org\/papers\/v12\/pedregosa11a.html. Accessed August 10, 2021."},{"issue":"1","key":"2015_CR21","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1186\/s12911-019-1004-8","volume":"19","author":"S Uddin","year":"2019","unstructured":"Uddin S, Khan A, Hossain ME, Moni MA. Comparing different supervised machine learning algorithms for disease prediction. BMC Med Inform Decis Mak. 2019;19(1):281. doi:https:\/\/doi.org\/10.1186\/s12911-019-1004-8. Published 2019 Dec 21.","journal-title":"BMC Med Inform Decis Mak"},{"issue":"11","key":"2015_CR22","doi-asserted-by":"publisher","first-page":"3663","DOI":"10.3390\/s21113663","volume":"21","author":"Z Shen","year":"2021","unstructured":"Shen Z, Wu Q, Wang Z, Chen G, Lin B. Diabetic Retinopathy Prediction by Ensemble Learning Based on Biochemical and Physical Data. Sens (Basel). 2021;21(11):3663. doi:https:\/\/doi.org\/10.3390\/s21113663. Published 2021 May 25.","journal-title":"Sens (Basel)"},{"key":"2015_CR23","doi-asserted-by":"publisher","unstructured":"Ali S, Hussain A, Aich S, et al. A Soft Voting Ensemble-Based Model for the Early Prediction of Idiopathic Pulmonary Fibrosis (IPF) Disease Severity in Lungs Disease Patients. Life (Basel). 2021;11(10):1092. Published 2021 Oct 15. doi:https:\/\/doi.org\/10.3390\/life11101092.","DOI":"10.3390\/life11101092"},{"key":"2015_CR24","doi-asserted-by":"publisher","unstructured":"Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30. doi:https:\/\/doi.org\/10.1145\/2939672.2939778.","DOI":"10.1145\/2939672.2939778"},{"key":"2015_CR25","doi-asserted-by":"publisher","unstructured":"Ribeiro MT, Singh S, Guestrin C. Why should I trust you?. Proceedings of the 22nd ACM SIGKDD International Conference on knowledge discovery and data mining. 2016:1135\u20131144. doi:https:\/\/doi.org\/10.1145\/2939672.2939778.","DOI":"10.1145\/2939672.2939778"},{"issue":"4","key":"2015_CR26","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1002\/ehf2.12297","volume":"5","author":"J Osmanska","year":"2018","unstructured":"Osmanska J, Hawkins NM, Toma M, Ignaszewski A, Virani SA. Eligibility for cardiac resynchronization therapy in patients hospitalized with heart failure. ESC Heart Fail. 2018;5(4):668\u201374. doi:https:\/\/doi.org\/10.1002\/ehf2.12297.","journal-title":"ESC Heart Fail"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-022-02015-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-022-02015-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-022-02015-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T20:04:28Z","timestamp":1667246668000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-022-02015-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,31]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["2015"],"URL":"https:\/\/doi.org\/10.1186\/s12911-022-02015-0","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,31]]},"assertion":[{"value":"3 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Our study used de-identified data from the SMART-AV clinical trial, wherein the original patients gave informed consent as approved by each participating institute\u2019s institutional review board []. All methods were performed in accordance with relevant guidelines and regulations.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"AH, DS, and WJR have filed a provisional patent application related to biomarker-based patient selection for cardiac resynchronization therapy and the remaining authors have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"282"}}