{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T16:01:50Z","timestamp":1790352110733,"version":"4.1.0"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007210","name":"RWTH Aachen University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007210","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cardiovasc Eng Tech"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Thrombosis in rotary blood pumps arises from complex flow conditions that remain difficult to translate into reliable and interpretable risk predictions using existing computational models. This limitation reflects an incomplete understanding of how specific flow features contribute to thrombus initiation and growth. This study introduces an feature-based supervised machine learning framework for spatial assessment of activation-based thrombogenic risk based directly on computational fluid dynamics-derived flow features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A logistic regression model combined with a structured feature-selection pipeline is used to derive a compact and physically interpretable feature set, including nonlinear feature combinations. The framework is trained using spatial risk patterns from a validated, macro-scale platelet-activation\u2013based thrombosis model for two representative scenarios.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The model reproduces the labeled risk distributions and identifies distinct sets of flow features associated with increased thrombosis risk. When applied to a centrifugal pump, despite training on a single axial pump operating point, the model predicts plausible thrombosis-prone regions. These results indicate that interpretable machine learning can link local flow features to activation-based thrombogenic risk while remaining computationally efficient and mechanistically transparent. The low computational cost enables rapid thrombogenicity screening without repeated or costly physics-based simulations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed framework complements physics-based thrombosis and platelet-activation modeling and provides a methodological basis for integrating interpretable machine learning into CFD-driven thrombogenicity analysis and device design workflows.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s13239-026-00828-y","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:59:10Z","timestamp":1774893550000},"page":"357-366","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Interpretable Machine Learning for Feature-Based Classification of Platelet Activation in Rotary Blood Pumps"],"prefix":"10.1007","volume":"17","author":[{"given":"Christopher","family":"Blum","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5582-6905","authenticated-orcid":false,"given":"Michael","family":"Neidlin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,30]]},"reference":[{"issue":"1","key":"828_CR1","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.healun.2013.11.001","volume":"33","author":"JK Kirklin","year":"2014","unstructured":"Kirklin, J. K., et al. Interagency registry for mechanically assisted circulatory support (INTERMACS) analysis of pump thrombosis in the HeartMate II left ventricular assist device. J. Heart Lung Transplant. Off. Publ. Int. Soc. Heart Transplant. 33(1):12\u201322, 2014. https:\/\/doi.org\/10.1016\/j.healun.2013.11.001.","journal-title":"J. Heart Lung Transplant. Off. Publ. Int. Soc. Heart Transplant."},{"issue":"3","key":"828_CR2","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1097\/MAT.0000000000001230","volume":"67","author":"SR Olson","year":"2021","unstructured":"Olson, S. R., et al. Thrombosis and bleeding in extracorporeal membrane oxygenation (ECMO) without anticoagulation: a systematic review. ASAIO J. 67(3):290\u2013296, 2021. https:\/\/doi.org\/10.1097\/MAT.0000000000001230.","journal-title":"ASAIO J."},{"issue":"1","key":"828_CR3","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1182\/asheducation-2015.1.61","volume":"2015","author":"L Kreuzinger Baumann","year":"2015","unstructured":"Kreuzinger Baumann, L., and M. P. Massicotte. Mechanical circulatory support: balancing bleeding and clotting in high-risk patients. Hematol. Am. Soc. Hematol. Educ. Program. 2015(1):61\u201368, 2015. https:\/\/doi.org\/10.1182\/asheducation-2015.1.61.","journal-title":"Hematol. Am. Soc. Hematol. Educ. Program."},{"issue":"3","key":"828_CR4","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/s10237-012-0417-4","volume":"12","author":"SC Shadden","year":"2013","unstructured":"Shadden, S. C., and S. Hendabadi. Potential fluid mechanic pathways of platelet activation. Biomech. Model. Mechanobiol. 12(3):467\u2013474, 2013. https:\/\/doi.org\/10.1007\/s10237-012-0417-4.","journal-title":"Biomech. Model. Mechanobiol."},{"issue":"11","key":"828_CR5","doi-asserted-by":"publisher","first-page":"1164","DOI":"10.1016\/j.healun.2017.05.008","volume":"36","author":"P Shah","year":"2017","unstructured":"Shah, P., U. S. Tantry, K. P. Bliden, and P. A. Gurbel. Bleeding and thrombosis associated with ventricular assist device therapy. J. Heart Lung Transplant. Off. Publ. Int. Soc. Heart Transplant. 36(11):1164\u20131173, 2017. https:\/\/doi.org\/10.1016\/j.healun.2017.05.008.","journal-title":"J. Heart Lung Transplant. Off. Publ. Int. Soc. Heart Transplant."},{"issue":"28","key":"828_CR6","doi-asserted-by":"publisher","DOI":"10.1002\/adhm.202500436","volume":"14","author":"J Ren","year":"2025","unstructured":"Ren, J., et al. Vorticity-facilitated platelet aggregation: a high expansion-ratio stenotic microfluidic platform unravels the role of complex flow dynamics in arterial thrombosis. Adv. Healthc. Mater.14(28):e2500436, 2025. https:\/\/doi.org\/10.1002\/adhm.202500436.","journal-title":"Adv. Healthc. Mater."},{"issue":"1","key":"828_CR7","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.jtha.2023.08.021","volume":"22","author":"N Grande Guti\u00e9rrez","year":"2024","unstructured":"Grande Guti\u00e9rrez, N., D. Mukherjee, and D. Bark. Decoding thrombosis through code: a review of computational models. J. Thromb. Haemost. 22(1):35\u201347, 2024. https:\/\/doi.org\/10.1016\/j.jtha.2023.08.021.","journal-title":"J. Thromb. Haemost."},{"issue":"1","key":"828_CR8","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1097\/MAT.0b013e31815d6898","volume":"54","author":"M Nobili","year":"2008","unstructured":"Nobili, M., J. Sheriff, U. Morbiducci, A. Redaelli, and D. Bluestein. Platelet activation due to hemodynamic shear stresses: damage accumulation model and comparison to in vitro measurements. ASAIO J. 54(1):64\u201372, 2008. https:\/\/doi.org\/10.1097\/MAT.0b013e31815d6898.","journal-title":"ASAIO J."},{"issue":"6","key":"828_CR9","doi-asserted-by":"publisher","first-page":"1127","DOI":"10.1007\/s10237-013-0469-0","volume":"12","author":"JS Soares","year":"2013","unstructured":"Soares, J. S., J. Sheriff, and D. Bluestein. A novel mathematical model of activation and sensitization of platelets subjected to dynamic stress histories. Biomech. Model. Mechanobiol. 12(6):1127\u20131141, 2013. https:\/\/doi.org\/10.1007\/s10237-013-0469-0.","journal-title":"Biomech. Model. Mechanobiol."},{"key":"828_CR10","doi-asserted-by":"publisher","first-page":"42720","DOI":"10.1038\/srep42720","volume":"7","author":"W-T Wu","year":"2017","unstructured":"Wu, W.-T., M. A. Jamiolkowski, W. R. Wagner, N. Aubry, M. Massoudi, and J. F. Antaki. Multi-constituent simulation of thrombus deposition. Sci. Rep. 7:42720, 2017. https:\/\/doi.org\/10.1038\/srep42720.","journal-title":"Sci. Rep."},{"issue":"6","key":"828_CR11","doi-asserted-by":"publisher","first-page":"1713","DOI":"10.1007\/s10237-016-0793-2","volume":"15","author":"JO Taylor","year":"2016","unstructured":"Taylor, J. O., R. S. Meyer, S. Deutsch, and K. B. Manning. Development of a computational model for macroscopic predictions of device-induced thrombosis. Biomech. Model. Mechanobiol. 15(6):1713\u20131731, 2016. https:\/\/doi.org\/10.1007\/s10237-016-0793-2.","journal-title":"Biomech. Model. Mechanobiol."},{"issue":"10","key":"828_CR12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1010277","volume":"18","author":"R M\u00e9ndez Rojano","year":"2022","unstructured":"M\u00e9ndez Rojano, R., A. Lai, M. Zhussupbekov, G. W. Burgreen, K. Cook, and J. F. Antaki. A fibrin enhanced thrombosis model for medical devices operating at low shear regimes or large surface areas. PLoS Comput. Biol.18(10):e1010277, 2022. https:\/\/doi.org\/10.1371\/journal.pcbi.1010277.","journal-title":"PLoS Comput. Biol."},{"issue":"8","key":"828_CR13","doi-asserted-by":"publisher","first-page":"1836","DOI":"10.1093\/annonc\/mdy166","volume":"29","author":"HA Haenssle","year":"2018","unstructured":"Haenssle, H. A., et al. Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann. Oncol. Off. J. Eur. Soc. Med. Oncol. 29(8):1836\u20131842, 2018. https:\/\/doi.org\/10.1093\/annonc\/mdy166.","journal-title":"Ann. Oncol. Off. J. Eur. Soc. Med. Oncol."},{"issue":"8","key":"828_CR14","doi-asserted-by":"publisher","first-page":"2691","DOI":"10.1038\/s41591-025-03747-y","volume":"31","author":"S Yan","year":"2025","unstructured":"Yan, S., et al. A multimodal vision foundation model for clinical dermatology. Nat. Med. 31(8):2691\u20132702, 2025. https:\/\/doi.org\/10.1038\/s41591-025-03747-y.","journal-title":"Nat. Med."},{"issue":"9","key":"828_CR15","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1007\/s00134-023-07157-x","volume":"49","author":"AF Stephens","year":"2023","unstructured":"Stephens, A. F., et al. ECMO PAL: using deep neural networks for survival prediction in venoarterial extracorporeal membrane oxygenation. Intensive Care Med. 49(9):1090\u20131099, 2023. https:\/\/doi.org\/10.1007\/s00134-023-07157-x.","journal-title":"Intensive Care Med."},{"key":"828_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107772","volume":"168","author":"C Blum","year":"2024","unstructured":"Blum, C., U. Steinseifer, and M. Neidlin. Systematic analysis of non-intrusive polynomial chaos expansion to determine rotary blood pump performance over the entire operating range. Comput. Biol. Med.168:107772, 2024. https:\/\/doi.org\/10.1016\/j.compbiomed.2023.107772.","journal-title":"Comput. Biol. Med."},{"issue":"1","key":"828_CR17","doi-asserted-by":"publisher","first-page":"2515","DOI":"10.1038\/s41598-018-20603-x","volume":"8","author":"A Yazdani","year":"2018","unstructured":"Yazdani, A., et al. Data-driven modeling of hemodynamics and its role on thrombus size and shape in aortic dissections. Sci. Rep. 8(1):2515, 2018. https:\/\/doi.org\/10.1038\/s41598-018-20603-x.","journal-title":"Sci. Rep."},{"key":"828_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2023.108718","volume":"287","author":"Y Zhu","year":"2023","unstructured":"Zhu, Y., et al. AI-aided multiscale modeling of physiologically-significant blood clots. Comput. Phys. Commun.287:108718, 2023. https:\/\/doi.org\/10.1016\/j.cpc.2023.108718.","journal-title":"Comput. Phys. Commun."},{"key":"828_CR19","first-page":"349","volume":"65","author":"TM Morrison","year":"2018","unstructured":"Morrison, T. M. Assessing credibility of computational modeling through verification and validation: application to medical devices. Am. Soc. Mech. Eng. 65:349, 2018.","journal-title":"Am. Soc. Mech. Eng."},{"issue":"4","key":"828_CR20","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1007\/s13239-021-00606-y","volume":"13","author":"C Blum","year":"2022","unstructured":"Blum, C., S. Gro\u00df-Hardt, U. Steinseifer, and M. Neidlin. An accelerated thrombosis model for computational fluid dynamics simulations in rotary blood pumps. Cardiovasc. Eng. Technol. 13(4):638\u2013649, 2022. https:\/\/doi.org\/10.1007\/s13239-021-00606-y.","journal-title":"Cardiovasc. Eng. Technol."},{"issue":"2","key":"828_CR21","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1097\/MAT.0000000000000499","volume":"63","author":"RA Malinauskas","year":"2017","unstructured":"Malinauskas, R. A., et al. FDA benchmark medical device flow models for CFD validation. ASAIO J. 63(2):150\u2013160, 2017. https:\/\/doi.org\/10.1097\/MAT.0000000000000499.","journal-title":"ASAIO J."},{"issue":"2","key":"828_CR22","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/s10494-018-9994-3","volume":"102","author":"N Berg","year":"2019","unstructured":"Berg, N., L. Fuchs, and L. Prahl Wittberg. Flow characteristics and coherent structures in a centrifugal blood pump. Flow Turbul. Combust. 102(2):469\u2013483, 2019. https:\/\/doi.org\/10.1007\/s10494-018-9994-3.","journal-title":"Flow Turbul. Combust"},{"issue":"21","key":"828_CR23","doi-asserted-by":"publisher","first-page":"4033","DOI":"10.1016\/j.bpj.2022.09.040","volume":"121","author":"M Zhussupbekov","year":"2022","unstructured":"Zhussupbekov, M., R. M\u00e9ndez Rojano, W.-T. Wu, and J. F. Antaki. von Willebrand factor unfolding mediates platelet deposition in a model of high-shear thrombosis. Biophys. J. 121(21):4033\u20134047, 2022. https:\/\/doi.org\/10.1016\/j.bpj.2022.09.040.","journal-title":"Biophys. J."},{"key":"828_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbiomech.2021.110915","volume":"132","author":"M Rezaeimoghaddam","year":"2022","unstructured":"Rezaeimoghaddam, M., and F. N. van de Vosse. Continuum modeling of thrombus formation and growth under different shear rates. J. Biomech.132:110915, 2022. https:\/\/doi.org\/10.1016\/j.jbiomech.2021.110915.","journal-title":"J. Biomech."}],"container-title":["Cardiovascular Engineering and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13239-026-00828-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13239-026-00828-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13239-026-00828-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:28:39Z","timestamp":1781191719000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13239-026-00828-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":24,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["828"],"URL":"https:\/\/doi.org\/10.1007\/s13239-026-00828-y","relation":{},"ISSN":["1869-408X","1869-4098"],"issn-type":[{"value":"1869-408X","type":"print"},{"value":"1869-4098","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,30]]},"assertion":[{"value":"15 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All of the authors have nothing to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}