{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T18:46:23Z","timestamp":1785782783720,"version":"3.56.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T00:00:00Z","timestamp":1715212800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T00:00:00Z","timestamp":1715212800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"AHA","award":["17PRE33660333\/QAH\/2017 (QAH)"],"award-info":[{"award-number":["17PRE33660333\/QAH\/2017 (QAH)"]}]},{"name":"NSF","award":["#1920920 (PPS)"],"award-info":[{"award-number":["#1920920 (PPS)"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>To provide accurate predictions, current machine learning-based solutions require large, manually labeled training datasets. We implement persistent homology (PH), a topological tool for studying the pattern of data, to analyze echocardiography-based strain data and differentiate between rare diseases like constrictive pericarditis (CP) and restrictive cardiomyopathy (RCM). Patient population (retrospectively registered) included those presenting with heart failure due to CP (n\u2009=\u200951), RCM (n\u2009=\u200947), and patients without heart failure symptoms (n\u2009=\u200953). Longitudinal, radial, and circumferential strains\/strain rates for left ventricular segments were processed into topological feature vectors using Machine learning PH workflow. In differentiating CP and RCM, the PH workflow model had a ROC AUC of 0.94 (Sensitivity\u2009=\u200992%, Specificity\u2009=\u200981%), compared with the GLS model AUC of 0.69 (Sensitivity\u2009=\u200965%, Specificity\u2009=\u200966%). In differentiating between all three conditions, the PH workflow model had an AUC of 0.83 (Sensitivity\u2009=\u200968%, Specificity\u2009=\u200984%), compared with the GLS model AUC of 0.68 (Sensitivity\u2009=\u200952% and Specificity\u2009=\u200976%). By employing persistent homology to differentiate the \u201cpattern\u201d of cardiac deformations, our machine-learning approach provides reasonable accuracy when evaluating small datasets and aids in understanding and visualizing patterns of cardiac imaging data in clinically challenging disease states.<\/jats:p>","DOI":"10.1038\/s41598-024-61201-4","type":"journal-article","created":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T15:02:24Z","timestamp":1715266944000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A novel multi-task machine learning classifier for rare disease patterning using cardiac strain imaging data"],"prefix":"10.1038","volume":"14","author":[{"given":"Nanda K.","family":"Siva","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yashbir","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quincy A.","family":"Hathaway","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Partho P.","family":"Sengupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naveena","family":"Yanamala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,9]]},"reference":[{"key":"61201_CR1","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/s41746-018-0065-x","volume":"1","author":"A Madani","year":"2018","unstructured":"Madani, A., Ong, J. R., Tibrewal, A. & Mofrad, M. R. K. Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease. NPJ Digit. Med. 1, 59 (2018).","journal-title":"NPJ Digit. Med."},{"key":"61201_CR2","first-page":"215","volume-title":"Structured Random Forests for Myocardium Delineation in 3D Echocardiography in Machine Learning in Medical Imaging: 5th International Workshop","author":"JS Domingos","year":"2014","unstructured":"Domingos, J. S., Stebbing, R. V., Leeson, P. & Noble, J. A. Structured Random Forests for Myocardium Delineation in 3D Echocardiography in Machine Learning in Medical Imaging: 5th International Workshop 215\u2013222 (Springer, 2014)."},{"key":"61201_CR3","first-page":"246","volume-title":"Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2016","author":"O Oktay","year":"2016","unstructured":"Oktay, O. et al. Multi-input cardiac image super-resolution using convolutional neural networks. In Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2016 (eds Ourselin, S. et al.) 246\u2013254 (Springer, 2016)."},{"key":"61201_CR4","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1016\/j.jcmg.2019.01.044","volume":"12","author":"JU Voigt","year":"2019","unstructured":"Voigt, J. U. & Cvijic, M. 2- and 3-Dimensional myocardial strain in cardiac health and disease. JACC Cardiovasc. Imaging 12, 1849\u20131863 (2019).","journal-title":"JACC Cardiovasc. Imaging"},{"key":"61201_CR5","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1186\/s41747-022-00312-x","volume":"6","author":"Y Singh","year":"2022","unstructured":"Singh, Y. et al. Algebraic topology-based machine learning using MRI predicts outcomes in primary sclerosing cholangitis. Eur. Radiol. Exp. 6, 58 (2022).","journal-title":"Eur. Radiol. Exp."},{"key":"61201_CR6","doi-asserted-by":"publisher","first-page":"5113","DOI":"10.1073\/pnas.1917763117","volume":"117","author":"MR McGuirl","year":"2020","unstructured":"McGuirl, M. R., Volkening, A. & Sandstede, B. Topological data analysis of zebrafish patterns. Proc. Natl. Acad. Sci. U.S.A. 117, 5113\u20135124 (2020).","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"61201_CR7","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1002\/cnm.2655","volume":"30","author":"K Xia","year":"2014","unstructured":"Xia, K. & Wei, G. W. Persistent homology analysis of protein structure, flexibility, and folding. Int. J. Numer. Methods Biomed. Eng. 30, 814\u2013844 (2014).","journal-title":"Int. J. Numer. Methods Biomed. Eng."},{"key":"61201_CR8","doi-asserted-by":"publisher","first-page":"8581","DOI":"10.1038\/ncomms9581","volume":"6","author":"JL Nielson","year":"2015","unstructured":"Nielson, J. L. et al. Topological data analysis for discovery in preclinical spinal cord injury and traumatic brain injury. Nat. Commun. 6, 8581 (2015).","journal-title":"Nat. Commun."},{"key":"61201_CR9","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1214\/15-AOAS886","volume":"10","author":"P Bendich","year":"2016","unstructured":"Bendich, P., Marron, J. S., Miller, E., Pieloch, A. & Skwerer, S. Persistent homology analysis of brain artery trees. Ann. Appl. Stat. 10, 198\u2013218 (2016).","journal-title":"Ann. Appl. Stat."},{"key":"61201_CR10","doi-asserted-by":"publisher","DOI":"10.3390\/s20072006","author":"Y Yan","year":"2020","unstructured":"Yan, Y. et al. Gait rhythm dynamics for neuro-degenerative disease classification via persistence landscape- based topological representation. Sensors (Basel). https:\/\/doi.org\/10.3390\/s20072006 (2020).","journal-title":"Sensors (Basel)."},{"key":"61201_CR11","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1161\/CIRCIMAGING.114.002103","volume":"7","author":"M Amaki","year":"2014","unstructured":"Amaki, M. et al. Diagnostic concordance of echocardiography and cardiac magnetic resonance-based tissue tracking for differentiating constrictive pericarditis from restrictive cardiomyopathy. Circ. Cardiovasc. Imaging 7, 819\u2013827 (2014).","journal-title":"Circ. Cardiovasc. Imaging"},{"key":"61201_CR12","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.jcmg.2007.10.006","volume":"1","author":"PP Sengupta","year":"2008","unstructured":"Sengupta, P. P. et al. Disparate patterns of left ventricular mechanics differentiate constrictive pericarditis from restrictive cardiomyopathy. JACC Cardiovasc. Imaging 1, 29\u201338 (2008).","journal-title":"JACC Cardiovasc. Imaging"},{"key":"61201_CR13","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1161\/CIRCIMAGING.113.001613","volume":"7","author":"TD Welch","year":"2014","unstructured":"Welch, T. D. et al. Echocardiographic diagnosis of constrictive pericarditis: Mayo Clinic criteria. Circ. Cardiovasc. Imaging 7, 526\u2013534 (2014).","journal-title":"Circ. Cardiovasc. Imaging"},{"key":"61201_CR14","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1148\/radiology.182.2.1732952","volume":"182","author":"T Masui","year":"1992","unstructured":"Masui, T., Finck, S. & Higgins, C. B. Constrictive pericarditis and restrictive cardiomyopathy: Evaluation with MR imaging. Radiology 182, 369\u2013373 (1992).","journal-title":"Radiology"},{"key":"61201_CR15","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1161\/hc0402.102975","volume":"105","author":"MD Cerqueira","year":"2002","unstructured":"Cerqueira, M. D. et al. Standardized myocardial segmentation and nomenclature for tomographic imaging of the heart. A statement for healthcare professionals from the Cardiac Imaging Committee of the Council on Clinical Cardiology of the American Heart Association. Circulation 105, 539\u2013542 (2002).","journal-title":"Circulation"},{"key":"61201_CR16","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1007\/s10554-017-1108-0","volume":"33","author":"M Tabassian","year":"2017","unstructured":"Tabassian, M. et al. Machine learning of the spatio-temporal characteristics of echocardiographic deformation curves for infarct classification. Int. J. Cardiovasc. Imaging 33, 1159\u20131167 (2017).","journal-title":"Int. J. Cardiovasc. Imaging"},{"key":"61201_CR17","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1136\/heartjnl-2015-308657","volume":"102","author":"A Senapati","year":"2016","unstructured":"Senapati, A. et al. Prognostic implication of relative regional strain ratio in cardiac amyloidosis. Heart 102, 748\u2013754 (2016).","journal-title":"Heart"},{"key":"61201_CR18","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1016\/j.ultrasmedbio.2012.11.021","volume":"39","author":"K Negishi","year":"2013","unstructured":"Negishi, K. et al. What is the primary source of discordance in strain measurement between vendors: Imaging or analysis? Ultrasound Med. Biol. 39, 714\u2013720 (2013).","journal-title":"Ultrasound Med. Biol."},{"key":"61201_CR19","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.jcmg.2017.01.027","volume":"11","author":"O Mirea","year":"2018","unstructured":"Mirea, O. et al. Variability and reproducibility of segmental longitudinal strain measurement: A report from the EACVI-ASE strain standardization task force. JACC Cardiovasc. Imaging 11, 15\u201324 (2018).","journal-title":"JACC Cardiovasc. Imaging"},{"key":"61201_CR20","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s00454-002-2885-2","volume":"28","author":"Edelsbrunner","year":"2002","unstructured":"Edelsbrunner, Letscher, & Zomorodian,. Topological persistence and simplification. Discret. Comput. Geom. 28, 511\u2013533 (2002).","journal-title":"Discret. Comput. Geom."},{"key":"61201_CR21","doi-asserted-by":"publisher","first-page":"637684","DOI":"10.3389\/fphys.2021.637684","volume":"12","author":"YM Chung","year":"2021","unstructured":"Chung, Y. M., Hu, C. S., Lo, Y. L. & Wu, H. T. A persistent homology approach to heart rate variability analysis with an application to sleep-wake classification. Front. Physiol. 12, 637684 (2021).","journal-title":"Front. Physiol."},{"key":"61201_CR22","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1038\/s41467-018-03664-4","volume":"9","author":"M Saggar","year":"2018","unstructured":"Saggar, M. et al. Towards a new approach to reveal dynamical organization of the brain using topological data analysis. Nat. Commun. 9, 1399 (2018).","journal-title":"Nat. Commun."},{"key":"61201_CR23","doi-asserted-by":"crossref","unstructured":"Dindin, M., Umeda, Y. & Chazal, F. Topological data analysis for arrhythmia detection through modular neural networks. In Canadian AI 2020\u201433rd Canadian Conference on Artificial Intelligence, Ottawa, Canada (2020).","DOI":"10.1007\/978-3-030-47358-7_17"},{"key":"61201_CR24","doi-asserted-by":"crossref","unstructured":"Ignacio, P. S., Dunstan, C., Escobar, E., Trujillo, L. & Uminsky, D. Classification of single-lead electrocardiograms: TDA informed machine learning. In 18th IEEE International Conference on Machine Learning and Applications (ICMLA), Boca Raton 1241\u20131246 (2019).","DOI":"10.1109\/ICMLA.2019.00204"},{"key":"61201_CR25","doi-asserted-by":"publisher","DOI":"10.3389\/fams.2020.00034","author":"J Nicponski","year":"2020","unstructured":"Nicponski, J. & Jung, J.-H. Topological data analysis of vascular disease: A theoretical framework. Front. Appl. Math. Stat. https:\/\/doi.org\/10.3389\/fams.2020.00034 (2020).","journal-title":"Front. Appl. Math. Stat."},{"key":"61201_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2020.11.009","author":"D Hwang","year":"2021","unstructured":"Hwang, D. et al. Topological data analysis of coronary plaques demonstrates the natural history of coronary atherosclerosis. JACC Cardiovasc. Imaging. https:\/\/doi.org\/10.1016\/j.jcmg.2020.11.009 (2021).","journal-title":"JACC Cardiovasc. Imaging."},{"key":"61201_CR27","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1186\/s13244-023-01413-w","volume":"14","author":"Y Singh","year":"2023","unstructured":"Singh, Y. et al. Topological data analysis in medical imaging: Current state of the art. Insights Imaging 14, 58 (2023).","journal-title":"Insights Imaging"},{"key":"61201_CR28","doi-asserted-by":"publisher","first-page":"4863","DOI":"10.1002\/ehf2.13679","volume":"8","author":"Z Yang","year":"2021","unstructured":"Yang, Z. et al. Left ventricular strain-curve morphology to distinguish between constrictive pericarditis and restrictive cardiomyopathy. ESC Heart Fail. 8, 4863\u20134872 (2021).","journal-title":"ESC Heart Fail."},{"key":"61201_CR29","doi-asserted-by":"publisher","first-page":"133","DOI":"10.2174\/157340309788166642","volume":"5","author":"M Dandel","year":"2009","unstructured":"Dandel, M., Lehmkuhl, H., Knosalla, C., Suramelashvili, N. & Hetzer, R. Strain and strain rate imaging by echocardiography\u2014Basic concepts and clinical applicability. Curr. Cardiol. Rev. 5, 133\u2013148 (2009).","journal-title":"Curr. Cardiol. Rev."},{"key":"61201_CR30","doi-asserted-by":"publisher","first-page":"681108","DOI":"10.3389\/frai.2021.681108","volume":"4","author":"F Hensel","year":"2021","unstructured":"Hensel, F., Moor, M. & Rieck, B. A survey of topological machine learning methods. Front. Artif. Intell. 4, 681108 (2021).","journal-title":"Front. Artif. Intell."},{"key":"61201_CR31","doi-asserted-by":"publisher","first-page":"1988","DOI":"10.1016\/j.jacc.2006.08.030","volume":"48","author":"PP Sengupta","year":"2006","unstructured":"Sengupta, P. P. et al. Left ventricular structure and function: Basic science for cardiac imaging. J. Am. Coll. Cardiol 48, 1988\u20132001 (2006).","journal-title":"J. Am. Coll. Cardiol"},{"key":"61201_CR32","doi-asserted-by":"publisher","first-page":"3403","DOI":"10.1103\/PhysRevA.45.3403","volume":"45","author":"MB Kennel","year":"1992","unstructured":"Kennel, M. B., Brown, R. & Abarbanel, H. D. I. Determining embedding dimension for phase-space reconstruction using a geometrical construction. Phys. Rev. A 45, 3403 (1992).","journal-title":"Phys. Rev. A"},{"key":"61201_CR33","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s00454-004-1146-y","volume":"33","author":"A Zomorodian","year":"2005","unstructured":"Zomorodian, A. & Carlsson, G. Computing persistent homology. Discret. Comput. Geom. 33, 249\u2013274 (2005).","journal-title":"Discret. Comput. Geom."},{"key":"61201_CR34","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s00454-002-2885-2","volume":"28","author":"H Edelsbrunner","year":"2000","unstructured":"Edelsbrunner, H., Letscher, D. & Zomorodian, A. Topological persistence and simplification. Discret. Comput. Geom. 28, 511\u2013533 (2000).","journal-title":"Discret. Comput. Geom."},{"key":"61201_CR35","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1090\/S0273-0979-07-01191-3","volume":"45","author":"R Ghrist","year":"2008","unstructured":"Ghrist, R. Barcodes: The persistent topology of data. Bull. Am. Math. Soc. 45, 61\u201375 (2008).","journal-title":"Bull. Am. Math. Soc."},{"key":"61201_CR36","first-page":"77","volume":"16","author":"P Bubenik","year":"2015","unstructured":"Bubenik, P. Statistical topological data analysis using persistence landscapes. J. Mach. Learn. Res. 16, 77\u2013102 (2015).","journal-title":"J. Mach. Learn. Res."},{"key":"61201_CR37","first-page":"1","volume":"18","author":"H Adams","year":"2017","unstructured":"Adams, H. et al. Persistence images: A stable vector representation of persistent homology. J. Mach. Learn. Res. 18, 1\u201335 (2017).","journal-title":"J. Mach. Learn. Res."},{"key":"61201_CR38","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00925","author":"C Tralie","year":"2018","unstructured":"Tralie, C., Saul, N. & Bar-On, R. Ripser py: A lean persistent homology library for python. J. Open Source Softw. https:\/\/doi.org\/10.21105\/joss.00925 (2018).","journal-title":"J. Open Source Softw."},{"key":"61201_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v036.i11","volume":"36","author":"MB Kursa","year":"2010","unstructured":"Kursa, M. B. & Rudnicki, W. R. Feature selection with the boruta package. J. Stat. Softw. 36, 1\u201313 (2010).","journal-title":"J. Stat. Softw."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-61201-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-61201-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-61201-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T15:07:40Z","timestamp":1715267260000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-61201-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,9]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["61201"],"URL":"https:\/\/doi.org\/10.1038\/s41598-024-61201-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,9]]},"assertion":[{"value":"21 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Partho P. Sengupta is a consultant to Heart Sciences, Ultromics, and Kencor Health. Quincy A. Hathaway is the Chief Science Officer for Aspirations LLC. The other authors have nothing to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10672"}}