{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T09:23:31Z","timestamp":1774430611368,"version":"3.50.1"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Admission hypothermia remains a frequent and preventable complication in preterm infants and is associated with increased morbidity and mortality. Early risk stratification may enable timely thermal management and targeted preventive strategies. This study aimed to develop and internally validate multivariable machine learning\u2013based models for predicting admission hypothermia in preterm infants.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a retrospective cohort study including consecutively admitted preterm infants (&amp;lt;37\u202fweeks\u2019 gestation) at a tertiary neonatal referral center in Southwest China (January 2017\u2013January 2025). Admission hypothermia was defined as an axillary temperature &amp;lt;36.5\u202f\u00b0C at NICU admission. The dataset was randomly divided into a training cohort (70%) and a validation cohort (30%). Candidate predictors were selected using least absolute shrinkage and selection operator (LASSO) regression. Six models\u2014logistic regression, decision tree, random forest, support vector machine, artificial neural network, and na\u00efve Bayes\u2014were developed. Model performance was evaluated using discrimination (AUC), calibration, Brier score, and classification metrics. Shapley Additive Explanations (SHAP) were applied to enhance interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 346 preterm infants, 154 (44.5%) experienced admission hypothermia. LASSO identified 11 predictors, including gestational age, birth weight, ambient temperature, transport time, inborn status, and preheated incubator use. In the validation cohort, AUCs ranged from 0.78 to 0.86, with logistic regression and artificial neural network demonstrating the highest discrimination (AUC\u202f=\u202f0.86). Logistic regression showed favorable calibration and interpretability. SHAP analysis identified lower gestational age, lower birth weight, lower ambient temperature, and longer transport time as the strongest contributors to risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Machine learning\u2013based models using routinely available perinatal and environmental variables can effectively predict admission hypothermia in preterm infants. Logistic regression provided robust performance with strong interpretability, supporting its potential integration into early neonatal risk stratification and targeted thermal management strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1811064","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:52:11Z","timestamp":1774421531000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and internal validation of machine learning\u2013based models for predicting admission hypothermia in preterm infants: a retrospective cohort study"],"prefix":"10.3389","volume":"13","author":[{"given":"Xiaokuan","family":"Cao","sequence":"first","affiliation":[{"name":"Department of Neonatology, Children\u2019s Diagnosis and Treatment Center, The Affiliated Traditional Chinese Medicine Hospital, Southwest Medical University","place":["Luzhou, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuqin","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Neonatology, Children\u2019s Diagnosis and Treatment Center, The Affiliated Traditional Chinese Medicine Hospital, Southwest Medical University","place":["Luzhou, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shihan","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Neonatology, Children\u2019s Diagnosis and Treatment Center, The Affiliated Traditional Chinese Medicine Hospital, Southwest Medical University","place":["Luzhou, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengxi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Neonatology, Children\u2019s Diagnosis and Treatment Center, The Affiliated Traditional Chinese Medicine Hospital, Southwest Medical University","place":["Luzhou, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbin","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Neonatology, Children\u2019s Diagnosis and Treatment Center, The Affiliated Traditional Chinese Medicine Hospital, Southwest Medical University","place":["Luzhou, Sichuan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1016\/S0140-6736(23)00878-4","article-title":"National, regional, and global estimates of preterm birth in 2020, with trends from 2010: a systematic analysis","volume":"402","author":"Ohuma","year":"2023","journal-title":"Lancet"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1448","DOI":"10.1038\/s41390-023-02902-w","article-title":"Thermoregulation for very preterm infants in the delivery room: a narrative review","volume":"95","author":"Dunne","year":"2024","journal-title":"Pediatr Res"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"e90454","DOI":"10.7759\/cureus.90454","article-title":"The thermoregulatory effect of immediate skin-to-skin contact for preterm infants: a systematic review and Meta-analysis with trial sequential analysis","volume":"17","author":"Albzea","year":"2025","journal-title":"Cureus."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e2023065117","DOI":"10.1542\/peds.2023-065117","article-title":"Prevention of NICU admission hypothermia in moderate- and late-preterm infants","volume":"154","author":"Winkler","year":"2024","journal-title":"Pediatrics"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1055\/s-0044-1786873","article-title":"Association between neonatal outcomes and admission hypothermia among very preterm infants in Chinese neonatal intensive care units: a multicenter cohort study","volume":"41","author":"Hong","year":"2024","journal-title":"Am J Perinatol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e2024069668","DOI":"10.1542\/peds.2024-069668","article-title":"Hypothermia and adverse outcomes in very preterm infants: a systematic review","volume":"155","author":"Hogeveen","year":"2025","journal-title":"Pediatrics"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"e003263","DOI":"10.1136\/bmjpo-2024-003263","article-title":"Admission temperature in very preterm infants 2012-2021: a Nationwide quality registry study, Norway","volume":"9","author":"Solvang","year":"2025","journal-title":"BMJ Paediatr Open"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"701","DOI":"10.3233\/NPM-230058","article-title":"Hypothermia on admission and its association with neonatal mortality and morbidity in neonatal intensive care unit","volume":"16","author":"Mostafa","year":"2023","journal-title":"J Neonatal Perinatal Med"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"30502225251364989","DOI":"10.1177\/30502225251364989","article-title":"Admission hypothermia and neonatal mortality in the Ethiopian neonatal network","volume":"12","author":"Yeshanew","year":"2025","journal-title":"Sage Open Pediatr"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1272104","DOI":"10.3389\/fped.2024.1272104","article-title":"Hypothermia amongst neonatal admissions in Kenya: a retrospective cohort study assessing prevalence, trends, associated factors, and its relationship with all-cause neonatal mortality","volume":"12","author":"Wainaina","year":"2024","journal-title":"Front Pediatr"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"102155","DOI":"10.1016\/j.eclinm.2023.102155","article-title":"New World health organization recommendations for care of preterm or low birth weight infants: health policy","volume":"63","year":"2023","journal-title":"EClinicalMedicine"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"109934","DOI":"10.1016\/j.resuscitation.2023.109934","article-title":"International liaison committee on resuscitation neonatal life support task force. Maintaining normothermia immediately after birth in preterm infants <34 weeks' gestation: a systematic review and meta-analysis","volume":"191","author":"Ramaswamy","year":"2023","journal-title":"Resuscitation"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1186\/s12887-024-04960-3","article-title":"Hypothermia in preterm infants admitted to low-resource neonatal units in northern Nigeria: an observational study of occurrence and risk factors","volume":"24","author":"Sanni","year":"2024","journal-title":"BMC Pediatr"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e40301","DOI":"10.7759\/cureus.40301","article-title":"Quality improvement study with low-cost strategies to reduce neonatal admission hypothermia","volume":"15","author":"Pratik","year":"2023","journal-title":"Cureus."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1038\/s41390-024-03774-4","article-title":"AI models in clinical neonatology: a review of modeling approaches and a consensus proposal for standardized reporting of model performance","volume":"98","author":"Husain","year":"2025","journal-title":"Pediatr Res"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"g7594","DOI":"10.1136\/bmj.g7594","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"350","author":"Collins","year":"2015","journal-title":"BMJ"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"e20220042","DOI":"10.1590\/1983-1447.2023.20220042.en","article-title":"Hypothermia among premature newborns on admission to a neonatal intensive care unit","volume":"44","author":"Carvalho","year":"2023","journal-title":"Rev Gaucha Enferm."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1111\/apa.17499","article-title":"Hypothermia-prevalence and risk factors in neonates admitted to a neonatal unit in Tanzania","volume":"114","author":"Braa","year":"2025","journal-title":"Acta Paediatr"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s40348-025-00204-1","article-title":"Relationship of neonatal hypothermia and hypoglycemia in late preterm and term born neonates","volume":"12","author":"Kurz","year":"2025","journal-title":"Mol Cell Pediatr"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"e003473","DOI":"10.1136\/bmjpo-2025-003473","article-title":"Delayed admission temperature normalisation in preterm infants <32 weeks: impact on mortality and neonatal morbidities","volume":"9","author":"Alrahili","year":"2025","journal-title":"BMJ Paediatr Open"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"32","DOI":"10.4168\/aair.2025.17.1.32","article-title":"Skin barrier function in neonates and infants","volume":"17","author":"Choi","year":"2025","journal-title":"Allergy Asthma Immunol Res"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1469724","DOI":"10.3389\/fped.2024.1469724","article-title":"Thermal equilibrium as a predictor of growth efficiency in preterm infants","volume":"12","author":"Heiter","year":"2024","journal-title":"Front Pediatr"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1594729","DOI":"10.3389\/fped.2025.1594729","article-title":"A population-based study of neonatal air transport in the Arctic region of Norway from 1994 to 2023","volume":"13","author":"Trulsen","year":"2025","journal-title":"Front Pediatr"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/8078628","article-title":"Admission hypothermia and factors associated with mortality among admitted hypothermic preterm neonates in neonatal intensive care units of public hospitals of Addis Ababa","volume":"2022","author":"Getaneh","year":"2022","journal-title":"Ethiopia Int J Pediatr"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"oeaf070","DOI":"10.1093\/ehjopen\/oeaf070","article-title":"Variable selection for causal inference, prediction, and descriptive research: a narrative review of recommendations","volume":"5","author":"Dyer","year":"2025","journal-title":"Eur Heart J Open"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"2485","DOI":"10.1038\/s41598-023-28421-6","article-title":"Logistic regression technique is comparable to complex machine learning algorithms in predicting cognitive impairment related to post intensive care syndrome","volume":"13","author":"Wu","year":"2023","journal-title":"Sci Rep"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"e101185","DOI":"10.7759\/cureus.101185","article-title":"Strategies for embedding prediction models in clinical decision-making workflows","volume":"18","author":"Amusa","year":"2026","journal-title":"Cureus"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3390\/informatics7030025","article-title":"Clinical implementation of predictive models embedded within electronic health record systems: a systematic review","volume":"7","author":"Lee","year":"2020","journal-title":"Informatics (MDPI)"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"e2348","DOI":"10.1055\/a-2113-8364","article-title":"The alarm fatigue challenge in the neonatal intensive care unit: a \"before\" and \"after\" study","volume":"41","author":"Stiglich","year":"2024","journal-title":"Am J Perinatol"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1177\/15553434221097357","article-title":"A sociotechnical systems framework for the application of artificial intelligence in health care delivery","volume":"16","author":"Salwei","year":"2022","journal-title":"J Cogn Eng Decis Mak"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1811064\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:52:12Z","timestamp":1774421532000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1811064\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,25]]},"references-count":31,"alternative-id":["10.3389\/fmed.2026.1811064"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1811064","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,25]]},"article-number":"1811064"}}