{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T10:20:12Z","timestamp":1788862812367,"version":"build-2803163510"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T00:00:00Z","timestamp":1662076800000},"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. Physiol."],"abstract":"<jats:p>Hypothermia is a life-threatening condition where the temperature of the body drops below 35\u00b0C and is a key source of concern in Intensive Care Units (ICUs). Early identification can help to nudge clinical management to initiate early interventions. Despite its importance, very few studies have focused on the early prediction of hypothermia. In this study, we aim to monitor and predict Hypothermia (30\u00a0min-4\u00a0h) ahead of its onset using machine learning (ML) models developed on physiological vitals and to prospectively validate the best performing model in the pediatric ICU. We developed and evaluated ML algorithms for the early prediction of hypothermia in a pediatric ICU. Sepsis advanced forecasting engine ICU Database (SafeICU) data resource is an in-house ICU source of data built in the Pediatric ICU at the All-India Institute of Medical Science (AIIMS), New Delhi. Each time-stamp at 1-min resolution was labeled for the presence of hypothermia to construct a retrospective cohort of pediatric patients in the SafeICU data resource. The training set consisted of windows of the length of 4.2\u00a0h with a lead time of 30\u00a0min-4\u00a0h from the onset of hypothermia. A set of 3,835 hand-engineered time-series features were calculated to capture physiological features from the time series. Features selection using the Boruta algorithm was performed to select the most important predictors of hypothermia. A battery of models such as gradient boosting machine, random forest, AdaBoost, and support vector machine (SVM) was evaluated utilizing five-fold test sets. The best-performing model was prospectively validated. A total of 148 patients with 193 ICU stays were eligible for the model development cohort. Of 3,939 features, 726 were statistically significant in the Boruta analysis for the prediction of Hypothermia. The gradient boosting model performed best with an Area Under the Receiver Operating Characteristic curve (AUROC) of 85% (SD = 1.6) and a precision of 59.2% (SD = 8.8) for a 30-min lead time before the onset of Hypothermia onset. As expected, the model showed a decline in model performance at higher lead times, such as AUROC of 77.2% (SD = 2.3) and precision of 41.34% (SD = 4.8) for 4\u00a0h ahead of Hypothermia onset. Our GBM(gradient boosting machine) model produced equal and superior results for the prospective validation, where an AUROC of 79.8% and a precision of 53% for a 30-min lead time before the onset of Hypothermia whereas an AUROC of 69.6% and a precision of 38.52% for a (30\u00a0min-4\u00a0h) lead time prospective validation of Hypothermia. Therefore, this work establishes a pipeline termed <jats:italic>ThermoGnose<\/jats:italic> for predicting hypothermia, a major complication in pediatric ICUs.<\/jats:p>","DOI":"10.3389\/fphys.2022.921884","type":"journal-article","created":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T09:47:50Z","timestamp":1662112070000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Early prediction of hypothermia in pediatric intensive care units using machine learning"],"prefix":"10.3389","volume":"13","author":[{"given":"Pradeep","family":"Singh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aditya","family":"Nagori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rakesh","family":"Lodha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tavpritesh","family":"Sethi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,9,2]]},"reference":[{"key":"B37","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.procs.2019.09.167","article-title":"The proposal of undersampling method for learning from imbalanced datasets","volume":"159","author":"Bach","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"B1","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/B978-0-12-818438-7.00002-2","article-title":"The rise of artificial intelligence in healthcare applications","author":"Bohr","year":"2020","journal-title":"Artif. Intell. Healthc."},{"key":"B2","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1056\/NEJMra1114208","article-title":"Accidental hypothermia","volume":"367","author":"Brown","year":"2012","journal-title":"N. Engl. J. Med."},{"key":"B28","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.1056\/NEJMp1702071","article-title":"Machine learning and prediction in medicine-beyond the peak of inflated expectations","volume":"376","author":"Chen","year":"2017","journal-title":"N. Engl. J. Med."},{"key":"B3","first-page":"785","article-title":"XGBoost: A scalable tree boosting system","author":"Chen","year":"2016"},{"key":"B4","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.neucom.2018.03.067","article-title":"Time series FeatuRe extraction on basis of scalable hypothesis tests (tsfresh \u2013 a Python package)","volume":"307","author":"Christ","year":"2018","journal-title":"Neurocomputing"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2081","DOI":"10.1093\/cvr\/cvz309","article-title":"Moderate but not severe hypothermia causes pro-arrhythmic changes in cardiac electrophysiology","volume":"116","author":"Dietrichs","year":"2020","journal-title":"Cardiovasc. Res."},{"key":"B6","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.ijid.2021.05.031","article-title":"Association of hypothermia with increased mortality rate in SARS-CoV-2 infection","volume":"108","author":"Fatteh","year":"2021","journal-title":"Int. J. Infect. Dis."},{"key":"B7","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1093\/bjaceaccp\/mks063","article-title":"Temperature management in critically ill patients","volume":"13","author":"Faulds","year":"2013","journal-title":"Continuing Educ. Anaesth. Crit. Care & Pain"},{"key":"B8","volume-title":"The pocket outdoor survival guide: The ultimate guide for short-term survival","author":"Fears","year":"2011"},{"key":"B9","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1046\/j.1442-2026.2001.00172.x","article-title":"Emergency treatment of hypothermia","volume":"13","author":"Giesbrecht","year":"2001","journal-title":"Emerg. Med."},{"key":"B34","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1136\/amiajnl-2013-001815","article-title":"From vital signs to clinical outcomes for patients with sepsis: a machine learning basis for a clinical decision support system","volume":"21","author":"Gultepe","year":"2014","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"B10","doi-asserted-by":"publisher","first-page":"349","DOI":"10.4310\/SII.2009.v2.n3.a8","article-title":"Multi-class AdaBoost","volume":"2","author":"Hastie","year":"2009","journal-title":"Stat. Interface"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aab3719","article-title":"A targeted real-time early warning score (TREWScore) for septic shock","volume":"7","author":"Henry","year":"2015","journal-title":"Sci. Transl. Med."},{"key":"B11","doi-asserted-by":"publisher","first-page":"43","DOI":"10.2147\/RRN.S297470","article-title":"The effect of admission hypothermia for neonatal death among neonates admitted to neonatal intensive care unit at sheik hassan yabare jigjiga university referral hospital in jigjiga city, Somali region, eastern Ethiopia","volume":"11","author":"Ibrahim","year":"2021","journal-title":"Res. Rep. Neonatol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1080\/10618600.1996.10474713","article-title":"R: A language for data analysis and graphics","volume":"5","author":"Ihaka","year":"1996","journal-title":"J. Comput. Graph. Stat."},{"key":"B13","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1136\/svn-2017-000101","article-title":"Artificial intelligence in healthcare: Past, present and future","volume":"2","author":"Jiang","year":"2017","journal-title":"Stroke Vasc. Neurol."},{"key":"B14","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.aucc.2017.01.008","article-title":"Inadvertent hypothermia and mortality in critically ill adults: Systematic review and meta-analysis","volume":"31","author":"Kiekkas","year":"2018","journal-title":"Aust. Crit. Care"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1377\/hlthaff.2014.0053","article-title":"Big data And new knowledge in medicine: The thinking, training, and tools needed for a learning health system","volume":"33","author":"Krumholz","year":"2014","journal-title":"Health Aff. (Millwood)"},{"key":"B15","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1097\/SHK.0000000000000426","article-title":"Norepinephrine: Not too much, too long","volume":"44","author":"Martin","year":"2015","journal-title":"Shock"},{"key":"B35","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.jbi.2017.11.015","article-title":"Flexible, cluster-based analysis of the electronic medical record of sepsis with composite mixture models","volume":"78","author":"Mayhew","year":"2018","journal-title":"J. Biomed. Inform."},{"key":"B16","doi-asserted-by":"publisher","first-page":"9638","DOI":"10.3390\/ijerph18189638","article-title":"The efficacy of renal replacement therapy for rewarming of patients in severe accidental hypothermia\u2014systematic review of the literature","volume":"18","author":"Mendrala","year":"2021","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"B17","doi-asserted-by":"publisher","first-page":"207","DOI":"10.32614\/RJ-2017-009","article-title":"imputeTS: Time series missing value imputation in R","volume":"9","author":"Moritz","year":"2017","journal-title":"R. J."},{"key":"B18","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.resuscitation.2021.02.038","article-title":"Clinical staging of accidental hypothermia: The revised Swiss system: Recommendation of the international commission for mountain emergency medicine (ICAR MedCom)","volume":"162","author":"Musi","year":"2021","journal-title":"Resuscitation"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1038\/nbt1206-1565","article-title":"What is a support vector machine?","volume":"24","author":"Noble","year":"2006","journal-title":"Nat. Biotechnol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.1056\/NEJMp1705348","article-title":"Lost in thought \u2014 the limits of the human mind and the future of medicine","volume":"377","author":"Obermeyer","year":"2017","journal-title":"N. Engl. J. Med."},{"key":"B20","first-page":"547","article-title":"Chapter 33 - accidental hypothermia","volume-title":"Handbook of clinical neurology, thermoregulation: From basic neuroscience to clinical neurology, Part II","author":"Paal","year":"2018"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1007\/s10822-020-00314-0","article-title":"Interpretation of machine learning models using shapley values: Application to compound potency and multi-target activity predictions","volume":"34","author":"Rodr\u00edguez-P\u00e9rez","year":"2020","journal-title":"J. Computer-Aided Mol. Des."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1016\/j.jvs.2016.04.026","article-title":"The use of machine learning for the identification of peripheral artery disease and future mortality risk","volume":"64","author":"Ross","year":"2016","journal-title":"J. Vasc. Surg."},{"key":"B22","doi-asserted-by":"publisher","first-page":"e0170152","DOI":"10.1371\/journal.pone.0170152","article-title":"Fever is associated with reduced, hypothermia with increased mortality in septic patients: A meta-analysis of clinical trials","volume":"12","author":"Rumbus","year":"2017","journal-title":"PLOS ONE"},{"key":"B27","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1007\/s10877-018-0219-z","article-title":"Applying machine learning to continuously monitored physiological data","volume":"33","author":"Rush","year":"2019","journal-title":"J. Clin. Monit. Comput."},{"key":"B23","first-page":"64","article-title":"Validating the tele-diagnostic potential of affordable thermography in a big-data data-enabled ICU","author":"Sethi","year":"2017"},{"key":"B24","doi-asserted-by":"publisher","first-page":"11484","DOI":"10.3390\/ijerph182111484","article-title":"Pediatric hypothermia: An ambiguous issue","volume":"18","author":"Singer","year":"2021","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"B31","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","article-title":"A clinically applicable approach to continuous prediction of future acute kidney injury","volume":"572","author":"Toma\u0161ev","year":"2019","journal-title":"Nature"},{"key":"B36","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1111\/acem.12876","article-title":"Prediction of in-hospital mortality in emergency department patients with sepsis: A local big data\u2013driven, machine learning approach","volume":"23","author":"Taylor","year":"2016","journal-title":"Acad. Emerg. Med."},{"key":"B25","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1186\/s13613-018-0448-9","article-title":"Mean arterial pressure and mortality in patients with distributive shock: A retrospective analysis of the MIMIC-III database","volume":"8","author":"Vincent","year":"2018","journal-title":"Ann. Intensive Care"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e45","DOI":"10.2196\/medinform.8680","article-title":"Predicting unplanned transfers to the intensive care unit: A machine learning approach leveraging diverse clinical elements","volume":"5","author":"Wellner","year":"2017","journal-title":"JMIR Med. Inf."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2022.921884\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T09:37:47Z","timestamp":1662975467000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2022.921884\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,2]]},"references-count":37,"alternative-id":["10.3389\/fphys.2022.921884"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2022.921884","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,2]]},"article-number":"921884"}}