Machine learning based clinical decision tool to predict acute kidney injury and survival in therapeutic hypothermia treated neonates

Abstract Therapeutic hypothermia (TH) significantly reduces mortality and morbidities in neonates with Neonatal Encephalopathy (NE). NE may result in neonatal death and multisystem organ impairment, including acute kidney injury (AKI). Our study aimed to utilize machine learning (ML) methods to pred...

Full description

Saved in:
Bibliographic Details
Main Authors: Elif Keles, Syed Yaseen Ali, Pia Wintermark, Pieter Annaert, Floris Groenendaal, Suzan Şahin, Mehmet Yekta Öncel, Didem Armangil, Esin Koc, Malcolm R. Battin, Alistair J. Gunn, Adam Frymoyer, Valerie Chock, Djalila Mekahli, John van den Anker, Anne Smits, Karel Allegaert, Ulas Bagci
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-01141-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849326013406773248
author Elif Keles
Syed Yaseen Ali
Pia Wintermark
Pieter Annaert
Floris Groenendaal
Suzan Şahin
Mehmet Yekta Öncel
Didem Armangil
Esin Koc
Malcolm R. Battin
Alistair J. Gunn
Adam Frymoyer
Valerie Chock
Djalila Mekahli
John van den Anker
Anne Smits
Karel Allegaert
Ulas Bagci
author_facet Elif Keles
Syed Yaseen Ali
Pia Wintermark
Pieter Annaert
Floris Groenendaal
Suzan Şahin
Mehmet Yekta Öncel
Didem Armangil
Esin Koc
Malcolm R. Battin
Alistair J. Gunn
Adam Frymoyer
Valerie Chock
Djalila Mekahli
John van den Anker
Anne Smits
Karel Allegaert
Ulas Bagci
author_sort Elif Keles
collection DOAJ
description Abstract Therapeutic hypothermia (TH) significantly reduces mortality and morbidities in neonates with Neonatal Encephalopathy (NE). NE may result in neonatal death and multisystem organ impairment, including acute kidney injury (AKI). Our study aimed to utilize machine learning (ML) methods to predict the outcome of TH-treated NE neonates developing AKI and death during TH. In this retrospective multinational study, 1149 TH-treated NE neonates and 801 controls were included. AKI was classified using KDIGO neonatal criteria based on serum creatinine measurements. The ML model incorporated gestational age, birth weight, postnatal age, and serum creatinine values. The algorithm used all these covariates to predict one of five outcomes: survival with/without AKI, mortality with/without AKI, and hospitalized non-NE controls. The XGBoost model achieved an AUC of 95% and an accuracy of 75.08% in predicting AKI and survival, surpassing other ML classifiers that demonstrated accuracy levels ranging from 54% to 65%. To our knowledge this is the first ML model trained on multicenter, multinational data specifically aimed at predicting neonates’ AKI, death, and survival within the first three days. Our ML scoring systems’ code and user interface are freely available ( https://github.com/NUBagciLab/Therapeutic-Hypothermia-Outcome-Classification , https://thprediction.streamlit.app/ ). This tool has potential to support neonatologists to personalize therapies, and to optimize pharmacotherapy for renally cleared drugs.
format Article
id doaj-art-ed42b05b191e43288734fb1bb2db2e1f
institution Kabale University
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ed42b05b191e43288734fb1bb2db2e1f2025-08-20T03:48:15ZengNature PortfolioScientific Reports2045-23222025-05-0115111710.1038/s41598-025-01141-9Machine learning based clinical decision tool to predict acute kidney injury and survival in therapeutic hypothermia treated neonatesElif Keles0Syed Yaseen Ali1Pia Wintermark2Pieter Annaert3Floris Groenendaal4Suzan Şahin5Mehmet Yekta Öncel6Didem Armangil7Esin Koc8Malcolm R. Battin9Alistair J. Gunn10Adam Frymoyer11Valerie Chock12Djalila Mekahli13John van den Anker14Anne Smits15Karel Allegaert16Ulas Bagci17Department of Radiology, Feinberg School of Medicine, Northwestern UniversityDepartment of Radiology, Feinberg School of Medicine, Northwestern UniversityDivision of Newborn Medicine, Department of Pediatrics, Montreal Children’s Hospital, Research Institute of the McGill University Health Centre, McGill UniversityDepartment of Pharmaceutical and Pharmacological Sciences, KU LeuvenDepartment of Neonatology, Wilhelmina Children’s Hospital, University Medical Center Utrecht, and Utrecht UniversityDepartment of Neonatology, Faculty of Medicine, Izmir Demokrasi UniversityDepartment of Neonatology, Faculty of Medicine, İzmir Katip Çelebi UniversityNeonatal Intensive Care Unit, Koru HospitalDepartment of Neonatology, Faculty of Medicine, Gazi UniversityNewborn Service, Auckland City Hospital, Health New ZealandDepartment of Physiology, University of AucklandNeonatal and Developmental Medicine, Stanford University School of MedicineNeonatal and Developmental Medicine, Stanford University School of MedicineDepartment of Development and Regeneration, KU LeuvenDivision of Clinical Pharmacology, Children’s National HospitalDepartment of Development and Regeneration, KU LeuvenDepartment of Pharmaceutical and Pharmacological Sciences, KU LeuvenDepartment of Radiology, Feinberg School of Medicine, Northwestern UniversityAbstract Therapeutic hypothermia (TH) significantly reduces mortality and morbidities in neonates with Neonatal Encephalopathy (NE). NE may result in neonatal death and multisystem organ impairment, including acute kidney injury (AKI). Our study aimed to utilize machine learning (ML) methods to predict the outcome of TH-treated NE neonates developing AKI and death during TH. In this retrospective multinational study, 1149 TH-treated NE neonates and 801 controls were included. AKI was classified using KDIGO neonatal criteria based on serum creatinine measurements. The ML model incorporated gestational age, birth weight, postnatal age, and serum creatinine values. The algorithm used all these covariates to predict one of five outcomes: survival with/without AKI, mortality with/without AKI, and hospitalized non-NE controls. The XGBoost model achieved an AUC of 95% and an accuracy of 75.08% in predicting AKI and survival, surpassing other ML classifiers that demonstrated accuracy levels ranging from 54% to 65%. To our knowledge this is the first ML model trained on multicenter, multinational data specifically aimed at predicting neonates’ AKI, death, and survival within the first three days. Our ML scoring systems’ code and user interface are freely available ( https://github.com/NUBagciLab/Therapeutic-Hypothermia-Outcome-Classification , https://thprediction.streamlit.app/ ). This tool has potential to support neonatologists to personalize therapies, and to optimize pharmacotherapy for renally cleared drugs.https://doi.org/10.1038/s41598-025-01141-9
spellingShingle Elif Keles
Syed Yaseen Ali
Pia Wintermark
Pieter Annaert
Floris Groenendaal
Suzan Şahin
Mehmet Yekta Öncel
Didem Armangil
Esin Koc
Malcolm R. Battin
Alistair J. Gunn
Adam Frymoyer
Valerie Chock
Djalila Mekahli
John van den Anker
Anne Smits
Karel Allegaert
Ulas Bagci
Machine learning based clinical decision tool to predict acute kidney injury and survival in therapeutic hypothermia treated neonates
Scientific Reports
title Machine learning based clinical decision tool to predict acute kidney injury and survival in therapeutic hypothermia treated neonates
title_full Machine learning based clinical decision tool to predict acute kidney injury and survival in therapeutic hypothermia treated neonates
title_fullStr Machine learning based clinical decision tool to predict acute kidney injury and survival in therapeutic hypothermia treated neonates
title_full_unstemmed Machine learning based clinical decision tool to predict acute kidney injury and survival in therapeutic hypothermia treated neonates
title_short Machine learning based clinical decision tool to predict acute kidney injury and survival in therapeutic hypothermia treated neonates
title_sort machine learning based clinical decision tool to predict acute kidney injury and survival in therapeutic hypothermia treated neonates
url https://doi.org/10.1038/s41598-025-01141-9
work_keys_str_mv AT elifkeles machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT syedyaseenali machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT piawintermark machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT pieterannaert machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT florisgroenendaal machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT suzansahin machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT mehmetyektaoncel machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT didemarmangil machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT esinkoc machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT malcolmrbattin machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT alistairjgunn machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT adamfrymoyer machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT valeriechock machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT djalilamekahli machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT johnvandenanker machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT annesmits machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT karelallegaert machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates
AT ulasbagci machinelearningbasedclinicaldecisiontooltopredictacutekidneyinjuryandsurvivalintherapeutichypothermiatreatedneonates