{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T14:15:37Z","timestamp":1778163337917,"version":"3.51.4"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:00:00Z","timestamp":1778112000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T00:00:00Z","timestamp":1778112000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100001130","name":"Gerber Foundation","doi-asserted-by":"publisher","award":["10804"],"award-info":[{"award-number":["10804"]}],"id":[{"id":"10.13039\/100001130","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pediatr Cardiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Fluid overload is common after neonatal congenital cardiac surgery (CCS) and is frequently managed with continuous furosemide infusions requiring iterative dose titration. An interpretable prediction model could support more consistent early postoperative dosing decisions. We hypothesized that a novel, interpretable machine learning approach could accurately predict furosemide dosing decisions in neonates following CCS. We identified term neonates admitted to the Pediatric Cardiothoracic ICU at a large academic children\u2019s hospital between 8\/1\/2014 and 3\/1\/2023 following CCS with cardiopulmonary bypass. Demographic and clinical data from the first 48 postoperative hours were used to train, validate, and test a Tropical Geometry\u2013Based Fuzzy Neural Network Regressor (TGFNN-R) tasked with predicting furosemide infusion dose changes after CCS. The TGFNN-R was primed with clinician heuristics and provides transparent explanations behind predictions. A held-out internal validation\/testing cohort was drawn from the same single-center population. Data from 506 neonates were extracted; 398 received a continuous furosemide infusion. Mean age at surgery was 6.2 (\u00b1\u20095.1) days; 67.3% were White. The most common surgeries were Stage I (Norwood) (25.1%) and arterial switch operation (18.6%). There were 783 furosemide dose increases and 224 dose decreases. Test set performance was R\u00b2=0.515, mean absolute error\u2009=\u20090.119\u00a0mg\/kg\/hr, and false positive rate\u2009=\u20090.062. In this retrospective single-center cohort of neonates following CCS, an interpretable TGFNN-R model predicted and explained furosemide dose changes with good test performance. Next steps include external validation and nonclinical studies evaluating the model within clinical decision support and closed-loop paradigms to achieve prespecified fluid balance goals.<\/jats:p>","DOI":"10.1007\/s00246-026-04289-x","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T13:53:22Z","timestamp":1778162002000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Novel, Interpretable Machine Learning Model Predicts Furosemide Dosing After Congenital Cardiac Surgery"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6367-2865","authenticated-orcid":false,"given":"Daniel E.","family":"Ehrmann","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew W.","family":"Hodgman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emily M.","family":"Wittrup","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John R.","family":"Charpie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabe E.","family":"Owens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ranjit","family":"Aiyagari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kayvan","family":"Najarian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,7]]},"reference":[{"key":"4289_CR1","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s00467-017-3818-x","volume":"33","author":"KE Mah","year":"2018","unstructured":"Mah KE, Hao S, Sutherland SM et al (2018) Fluid overload independent of acute kidney injury predicts poor outcomes in neonates following congenital heart surgery. Pediatr Nephrol 33:511\u2013520","journal-title":"Pediatr Nephrol"},{"key":"4289_CR2","doi-asserted-by":"publisher","first-page":"2591","DOI":"10.1097\/CCM.0000000000000517","volume":"42","author":"J Seguin","year":"2014","unstructured":"Seguin J, Albright B, Vertullo L et al (2014) Extent, risk factors, and outcome of fluid overload after pediatric heart surgery*. Crit Care Med 42:2591\u20132599","journal-title":"Crit Care Med"},{"key":"4289_CR3","doi-asserted-by":"publisher","unstructured":"Luppes VAC, Willems A, Hazekamp MG et al (2023) Fluid Overload in Pediatric Univentricular Patients Undergoing Fontan Completion. J Cardiovasc Dev Dis 10. https:\/\/doi.org\/10.3390\/jcdd10040156","DOI":"10.3390\/jcdd10040156"},{"key":"4289_CR4","doi-asserted-by":"publisher","first-page":"2288","DOI":"10.1016\/j.athoracsur.2021.12.078","volume":"114","author":"DK Bailly","year":"2022","unstructured":"Bailly DK, Alten JA, Gist KM et al (2022) Fluid Accumulation After Neonatal Congenital Cardiac Operation: Clinical Implications and Outcomes. Ann Thorac Surg 114:2288\u20132294","journal-title":"Ann Thorac Surg"},{"key":"4289_CR5","doi-asserted-by":"publisher","first-page":"e237","DOI":"10.1097\/pq9.0000000000000237","volume":"4","author":"JM Simsic","year":"2019","unstructured":"Simsic JM, Dolan K, Miller J et al (2019) Guidelines for Diuretic Utilization Reduce High Charge Medications. Pediatr Qual Saf 4:e237","journal-title":"Pediatr Qual Saf"},{"key":"4289_CR6","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1007\/s001340000819","volume":"27","author":"MM van der Vorst","year":"2001","unstructured":"van der Vorst MM, van Ruys-Dudok I, Kist-van Holthe JE et al (2001) Continuous intravenous furosemide in haemodynamically unstable children after cardiac surgery. Intensive Care Med 27:711\u2013715","journal-title":"Intensive Care Med"},{"key":"4289_CR7","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1186\/s12882-016-0323-6","volume":"17","author":"R Claure-Del Granado","year":"2016","unstructured":"Claure-Del Granado R, Mehta RL (2016) Fluid overload in the ICU: evaluation and management. BMC Nephrol 17:109","journal-title":"BMC Nephrol"},{"key":"4289_CR8","doi-asserted-by":"publisher","first-page":"e019396","DOI":"10.1161\/JAHA.120.019396","volume":"10","author":"F Sperotto","year":"2021","unstructured":"Sperotto F, Davidson JA, Smith-Parrish MN et al (2021) Development of Care Curves Following the Stage 1 Palliation: A Comparison of Intensive Care Among 5 Centers. J Am Heart Assoc 10:e019396","journal-title":"J Am Heart Assoc"},{"key":"4289_CR9","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1016\/j.jacc.2020.12.022","volume":"77","author":"VS Rao","year":"2021","unstructured":"Rao VS, Ivey-Miranda JB, Cox ZL et al (2021) Natriuretic equation to predict loop diuretic response in patients with heart failure. J Am Coll Cardiol 77:695\u2013708","journal-title":"J Am Coll Cardiol"},{"key":"4289_CR10","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1002\/ejhf.1533","volume":"21","author":"J Biegus","year":"2019","unstructured":"Biegus J, Zymlinski R, Siwolowski P et al (2019) Controlled decongestion by Reprieve therapy in acute heart failure: results of the TARGET-1 and TARGET-2 studies. Eur J Heart Fail 21:1079\u20131087","journal-title":"Eur J Heart Fail"},{"key":"4289_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/2110-5820-3-1","volume":"3","author":"A Bougl\u00e9","year":"2013","unstructured":"Bougl\u00e9 A, Harrois A, Duranteau J (2013) Resuscitative strategies in traumatic hemorrhagic shock. Ann Intensive Care 3:1","journal-title":"Ann Intensive Care"},{"key":"4289_CR12","doi-asserted-by":"publisher","first-page":"R155","DOI":"10.1186\/cc7149","volume":"12","author":"M Merouani","year":"2008","unstructured":"Merouani M, Guignard B, Vincent F et al (2008) Norepinephrine weaning in septic shock patients by closed loop control based on fuzzy logic. Crit Care 12:R155","journal-title":"Crit Care"},{"key":"4289_CR13","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/s10877-023-01119-w","volume":"38","author":"A Joosten","year":"2024","unstructured":"Joosten A, Rinehart J, Cannesson M et al (2024) Control of mean arterial pressure using a closed-loop system for norepinephrine infusion in severe brain injury patients: the COMAT randomized controlled trial. J Clin Monit Comput 38:25\u201330","journal-title":"J Clin Monit Comput"},{"key":"4289_CR14","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1186\/s13054-020-2810-1","volume":"24","author":"P von Platen","year":"2020","unstructured":"von Platen P, Pomprapa A, Lachmann B, Leonhardt S (2020) The dawn of physiological closed-loop ventilation-a review. Crit Care 24:121","journal-title":"Crit Care"},{"key":"4289_CR15","doi-asserted-by":"publisher","first-page":"373","DOI":"10.3182\/20120829-3-HU-2029.00102","volume":"45","author":"GA Dumont","year":"2012","unstructured":"Dumont GA (2012) Closed-Loop Control of Anesthesia - A Review. IFAC Proc Volumes 45:373\u2013378","journal-title":"IFAC Proc Volumes"},{"key":"4289_CR16","doi-asserted-by":"publisher","first-page":"033001","DOI":"10.1088\/2516-1091\/ac6d36","volume":"4","author":"J-O Hahn","year":"2022","unstructured":"Hahn J-O, Inan OT (2022) Physiological closed-loop control in critical care: opportunities for innovations. Prog Biomed Eng 4:033001","journal-title":"Prog Biomed Eng"},{"key":"4289_CR17","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1038\/s41551-018-0305-z","volume":"2","author":"K-H Yu","year":"2018","unstructured":"Yu K-H, Beam AL, Kohane IS (2018) Artificial intelligence in healthcare. Nat Biomed Eng 2:719\u2013731","journal-title":"Nat Biomed Eng"},{"key":"4289_CR18","doi-asserted-by":"crossref","unstructured":"Khan B, Fatima H, Qureshi A et al (2023) Drawbacks of artificial intelligence and their potential solutions in the healthcare sector. Biomed Mater Devices 1\u20138","DOI":"10.1007\/s44174-023-00063-2"},{"key":"4289_CR19","doi-asserted-by":"publisher","first-page":"e48633","DOI":"10.2196\/48633","volume":"11","author":"M Hassan","year":"2024","unstructured":"Hassan M, Kushniruk A, Borycki E (2024) Barriers to and facilitators of artificial intelligence adoption in health care: Scoping review. JMIR Hum Factors 11:e48633","journal-title":"JMIR Hum Factors"},{"key":"4289_CR20","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","volume":"385","author":"GS Collins","year":"2024","unstructured":"Collins GS, Moons KGM, Dhiman P et al (2024) TRIPOD\u2009+\u2009AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 385:e078378","journal-title":"BMJ"},{"key":"4289_CR21","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1177\/2150135115586814","volume":"6","author":"KD Piggott","year":"2015","unstructured":"Piggott KD, Soni M, Decampli WM et al (2015) Acute Kidney Injury and Fluid Overload in Neonates Following Surgery for Congenital Heart Disease. World J Pediatr Congenit Heart Surg 6:401\u2013406","journal-title":"World J Pediatr Congenit Heart Surg"},{"key":"4289_CR22","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.1016\/S0003-4975(97)00714-5","volume":"64","author":"GB Luciani","year":"1997","unstructured":"Luciani GB, Nichani S, Chang AC et al (1997) Continuous versus intermittent furosemide infusion in critically ill infants after open heart operations. Ann Thorac Surg 64:1133\u20131139","journal-title":"Ann Thorac Surg"},{"key":"4289_CR23","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1097\/PCC.0b013e3181b806fc","volume":"11","author":"MG Gaies","year":"2010","unstructured":"Gaies MG, Gurney JG, Yen AH et al (2010) Vasoactive\u2013inotropic score as a predictor of morbidity and mortality in infants after cardiopulmonary bypass. Pediatr Crit Care Med 11:234\u2013238","journal-title":"Pediatr Crit Care Med"},{"key":"4289_CR24","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s10157-019-01805-7","volume":"24","author":"K Ueno","year":"2020","unstructured":"Ueno K, Shiokawa N, Takahashi Y et al (2020) Kidney Disease: Improving Global Outcomes in neonates with acute kidney injury after cardiac surgery. Clin Exp Nephrol 24:167\u2013173","journal-title":"Clin Exp Nephrol"},{"key":"4289_CR25","doi-asserted-by":"publisher","first-page":"4","DOI":"10.3389\/frai.2020.00004","volume":"3","author":"F Emmert-Streib","year":"2020","unstructured":"Emmert-Streib F, Yang Z, Feng H et al (2020) An Introductory Review of Deep Learning for Prediction Models With Big Data. Front Artif Intell 3:4","journal-title":"Front Artif Intell"},{"key":"4289_CR26","doi-asserted-by":"publisher","first-page":"266","DOI":"10.3934\/Neuroscience.2019.4.266","volume":"6","author":"E Vlamou","year":"2019","unstructured":"Vlamou E, Papadopoulos B (2019) Fuzzy logic systems and medical applications. AIMS Neurosci 6:266\u2013272","journal-title":"AIMS Neurosci"},{"key":"4289_CR27","unstructured":"Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv [cs.LG]"},{"key":"4289_CR28","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3211765","author":"H Yao","year":"2022","unstructured":"Yao H, Derksen H, Golbus JR et al (2022) A Novel Tropical Geometry-Based Interpretable Machine Learning Method: Pilot Application to Delivery of Advanced Heart Failure Therapies. IEEE J Biomed Health Inf PP. https:\/\/doi.org\/10.1109\/JBHI.2022.3211765","journal-title":"IEEE J Biomed Health Inf PP"},{"key":"4289_CR29","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1017\/S1047951114001450","volume":"25","author":"M Gaies","year":"2015","unstructured":"Gaies M, Cooper DS, Tabbutt S et al (2015) Collaborative quality improvement in the cardiac intensive care unit: development of the Paediatric Cardiac Critical Care Consortium (PC4). Cardiol Young 25:951\u2013957","journal-title":"Cardiol Young"},{"key":"4289_CR30","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1007\/s00134-014-3391-8","volume":"40","author":"DT Selewski","year":"2014","unstructured":"Selewski DT, Cornell TT, Heung M et al (2014) Validation of the KDIGO acute kidney injury criteria in a pediatric critical care population. Intensive Care Med 40:1481\u20131488","journal-title":"Intensive Care Med"},{"key":"4289_CR32","unstructured":"Center for Devices, Radiological Health (2025) Clinical Decision Support Software - Guidance. In: U.S. Food and Drug Administration. https:\/\/www.fda.gov\/regulatory-information\/search-fda-guidance-documents\/clinical-decision-support-software. Accessed 18 Sept 2025"},{"key":"4289_CR33","unstructured":"Food and Drug Administration (2023) Technical Considerations for Medical Devices With Physiologic Closed-Loop Control Technology; Guidance for Industry and Food and Drug Administration Staff; Availability. Federal Register"},{"key":"4289_CR34","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1038\/s41591-024-03364-1","volume":"31","author":"MD McCradden","year":"2025","unstructured":"McCradden MD, London AJ, Gichoya JW et al (2025) CANAIRI: The collaboration for translational artificial intelligence trials in healthcare. Nat Med 31:9\u201311","journal-title":"Nat Med"},{"key":"4289_CR35","doi-asserted-by":"crossref","unstructured":"(2025) For trustworthy AI, keep the human in the loop. Nat Med 31:3207stable","DOI":"10.1038\/s41591-025-04033-7"},{"key":"4289_CR36","doi-asserted-by":"publisher","first-page":"e745","DOI":"10.1016\/S2589-7500(21)00208-9","volume":"3","author":"M Ghassemi","year":"2021","unstructured":"Ghassemi M, Oakden-Rayner L, Beam AL (2021) The false hope of current approaches to explainable artificial intelligence in health care. Lancet Digit Health 3:e745\u2013e750","journal-title":"Lancet Digit Health"},{"key":"4289_CR37","doi-asserted-by":"crossref","unstructured":"Stegmeier N, Alten J, Borasino S et al (2025) Early diuretic administration after neonatal cardiac surgery and association with clinical outcomes: A report from NEPHRON. J Intensive Care Med 8850666251393180","DOI":"10.1177\/08850666251393180"},{"key":"4289_CR38","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1016\/S0895-4356(03)00207-5","volume":"56","author":"SE Bleeker","year":"2003","unstructured":"Bleeker SE, Moll HA, Steyerberg EW et al (2003) External validation is necessary in prediction research: a clinical example. J Clin Epidemiol 56:826\u2013832","journal-title":"J Clin Epidemiol"},{"key":"4289_CR39","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.jclinepi.2015.04.005","volume":"69","author":"EW Steyerberg","year":"2016","unstructured":"Steyerberg EW, Harrell FE Jr (2016) Prediction models need appropriate internal, internal-external, and external validation. J Clin Epidemiol 69:245\u2013247","journal-title":"J Clin Epidemiol"},{"key":"4289_CR40","doi-asserted-by":"publisher","first-page":"5499","DOI":"10.1002\/sim.3069","volume":"26","author":"IR K\u00f6nig","year":"2007","unstructured":"K\u00f6nig IR, Malley JD, Weimar C et al (2007) Practical experiences on the necessity of external validation. Stat Med 26:5499\u20135511","journal-title":"Stat Med"}],"container-title":["Pediatric Cardiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00246-026-04289-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00246-026-04289-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00246-026-04289-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T13:53:33Z","timestamp":1778162013000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00246-026-04289-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,7]]},"references-count":39,"alternative-id":["4289"],"URL":"https:\/\/doi.org\/10.1007\/s00246-026-04289-x","relation":{},"ISSN":["0172-0643","1432-1971"],"issn-type":[{"value":"0172-0643","type":"print"},{"value":"1432-1971","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,7]]},"assertion":[{"value":"29 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 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":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"All procedures performed in this study involving human participants were in accordance with the ethical standards of the institutional research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. The study was approved by the Institutional Review Board at the University of Michigan Medical School (protocol HUM00092309, \u201cDevelopment of Clinical Decision Support Tools in Acute Care,\u201d approved July 24, 2023).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"The Institutional Review Board at the University of Michigan Medical School waived the requirement for informed consent for this retrospective study due to minimal risk to participants and the impracticability of obtaining consent for a large retrospective cohort.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}]}}