{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T01:11:02Z","timestamp":1761181862076,"version":"build-2065373602"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3011802"],"award-info":[{"award-number":["2023YFC3011802"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Accurately predicting the mortality risk of hypothermia patients is crucial for clinical decision-making, offering ample time for physicians to intervene. However, existing methods are invasive and difficult to implement in pre-hospital settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, records of 2,700 hypothermia patients from 125 hospitals were extracted from the eICU Collaborative Research database, comprising 360 non-survivors and 2,340 survivors. Four machine learning methods were utilized to develop a mortality prediction model for hypothermia patients based on non-invasive physiological parameters. Data from 122 hospitals were used for model training, while the remainder were utilized for performance validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed machine learning prediction model achieved an area under the receiver operating characteristic curve (AUC) of 0.869 (95%CI: 0.840\u20130.895), demonstrating good mortality predictive performance for hypothermia patients only using non-invasive physiological parameters. Optimal and minimal feature subsets were selected for each machine learning method. The optimal feature subsets contained only 70.6% of the overall features for XGBoost models, while the AUC values increased by 0.039 compared to that of the entire feature subset. The interpretability analysis results highlight the vital importance of the temperature feature in predicting mortality during episodes of hypothermia in patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study developed a mortality prediction method for hypothermia patients only using non-invasive parameters, demonstrating robustness and reliability during multi-center validation. It can offer decision support for remote areas and disaster sites where it is difficult to access invasive parameters.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0334526","type":"journal-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:28:07Z","timestamp":1761154087000},"page":"e0334526","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["A machine learning approach for predicting 72-hour mortality of hypothermic patients only using non-invasive parameters: A multi-center retrospective cohort study"],"prefix":"10.1371","volume":"20","author":[{"given":"Chunliang","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"GuoFeng","family":"Ru","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"GuanJun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiquan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"JiaMeng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YiJing","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8375-8858","authenticated-orcid":true,"given":"Jing","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,10,22]]},"reference":[{"key":"pone.0334526.ref001","doi-asserted-by":"crossref","first-page":"100150","DOI":"10.1016\/j.pcorm.2020.100150","article-title":"Factors contributing to intraoperative hypothermia in patients undergoing elective surgery","volume":"22","author":"A Peixoto C de","year":"2021","journal-title":"Perioperative Care and Operating Room Management"},{"issue":"4","key":"pone.0334526.ref002","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1002\/jgf2.323","article-title":"Hypothermia in a Japanese subtropical climate: Retrospective validation study of severity score and mortality prediction","volume":"21","author":"N Ishimaru","year":"2020","journal-title":"J Gen Fam Med"},{"issue":"11","key":"pone.0334526.ref003","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1136\/emermed-2017-207238","article-title":"Characteristics and outcomes of accidental hypothermia in Japan: the J-Point registry","volume":"35","author":"T Matsuyama","year":"2018","journal-title":"Emerg Med J"},{"issue":"2","key":"pone.0334526.ref004","doi-asserted-by":"crossref","first-page":"76","DOI":"10.59345\/sjfm.v1i2.61","article-title":"Incidental Systemic Hypothermia as a Contributing Factor in Accidental Deaths: A Comparative Study in Jayawijaya, Indonesia","volume":"1","author":"F Auparay","year":"2023","journal-title":"SJFM"},{"issue":"12","key":"pone.0334526.ref005","doi-asserted-by":"crossref","first-page":"4106","DOI":"10.1007\/s00268-020-05750-5","article-title":"The Impact of Accidental Hypothermia on Mortality in Trauma Patients Overall and Patients with Traumatic Brain Injury Specifically: A Systematic Review and Meta-Analysis","volume":"44","author":"D R\u00f6sli","year":"2020","journal-title":"World J Surg"},{"issue":"1","key":"pone.0334526.ref006","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1186\/s12877-021-02459-5","article-title":"Association between frailty and mortality among patients with accidental hypothermia: a nationwide observational study in Japan","volume":"21","author":"S Takauji","year":"2021","journal-title":"BMC Geriatr"},{"issue":"1","key":"pone.0334526.ref007","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s40560-021-00525-z","article-title":"Machine learning-based prediction models for accidental hypothermia patients","volume":"9","author":"Y Okada","year":"2021","journal-title":"J Intensive Care"},{"issue":"3","key":"pone.0334526.ref008","doi-asserted-by":"crossref","first-page":"97","DOI":"10.4103\/0974-2700.185276","article-title":"Hypothermia as a predictor for mortality in trauma patients at admittance to the Intensive Care Unit","volume":"9","author":"K Balvers","year":"2016","journal-title":"J Emerg Trauma Shock"},{"issue":"2","key":"pone.0334526.ref009","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.resuscitation.2008.10.021","article-title":"Hypothermia and associated outcomes in seriously injured trauma patients in a predominantly sub-tropical climate","volume":"80","author":"LM Aitken","year":"2009","journal-title":"Resuscitation"},{"issue":"4","key":"pone.0334526.ref010","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1159\/000505126","article-title":"Admission Body Temperature in Critically Ill Patients as an Independent Risk Predictor for Overall Outcome","volume":"29","author":"R Erkens","year":"2020","journal-title":"Med Princ Pract"},{"issue":"8","key":"pone.0334526.ref011","doi-asserted-by":"crossref","first-page":"1769","DOI":"10.3390\/ijerph15081769","article-title":"Effect of Hypothermia in the Emergency Department on the Outcome of Trauma Patients: A Cross-Sectional Analysis","volume":"15","author":"T-M Hsieh","year":"2018","journal-title":"Int J Environ Res Public Health"},{"issue":"2","key":"pone.0334526.ref012","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1089\/ham.2020.0179","article-title":"Vital Signs in Accidental Hypothermia","volume":"22","author":"M Pasquier","year":"2021","journal-title":"High Alt Med Biol"},{"issue":"1","key":"pone.0334526.ref013","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s40560-022-00616-5","article-title":"External validation of 5A score model for predicting in-hospital mortality among the accidental hypothermia patients: JAAM-Hypothermia study 2018-2019 secondary analysis","volume":"10","author":"Y Okada","year":"2022","journal-title":"J Intensive Care"},{"key":"pone.0334526.ref014","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.jcrc.2020.07.011","article-title":"Association of triage hypothermia with in-hospital mortality among patients in the emergency department with suspected sepsis","volume":"60","author":"S Ramgopal","year":"2020","journal-title":"J Crit Care"},{"key":"pone.0334526.ref015","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.resuscitation.2018.02.026","article-title":"Hypothermia outcome prediction after extracorporeal life support for hypothermic cardiac arrest patients: The HOPE score","volume":"126","author":"M Pasquier","year":"2018","journal-title":"Resuscitation"},{"issue":"1","key":"pone.0334526.ref016","doi-asserted-by":"crossref","DOI":"10.1002\/ams2.478","article-title":"Derivation of a model to predict mortality in urban patients with accidental hypothermia: a retrospective observational study","volume":"7","author":"T Uemura","year":"2019","journal-title":"Acute Med Surg"},{"issue":"4","key":"pone.0334526.ref017","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1016\/j.ajem.2018.06.025","article-title":"Prognostic factors for patients with accidental hypothermia: A multi-institutional retrospective cohort study","volume":"37","author":"Y Okada","year":"2019","journal-title":"Am J Emerg Med"},{"issue":"1","key":"pone.0334526.ref018","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.injury.2017.11.028","article-title":"Hypothermia indices among severely injured trauma patients undergoing urgent surgery: A single-centred retrospective quality review and analysis","volume":"49","author":"A Alam","year":"2018","journal-title":"Injury"},{"issue":"10","key":"pone.0334526.ref019","doi-asserted-by":"crossref","first-page":"2195","DOI":"10.1007\/s11517-020-02174-0","article-title":"A machine learning approach for mortality prediction only using non-invasive parameters","volume":"58","author":"G Zhang","year":"2020","journal-title":"Med Biol Eng Comput"},{"key":"pone.0334526.ref020","doi-asserted-by":"crossref","first-page":"180178","DOI":"10.1038\/sdata.2018.178","article-title":"The eICU Collaborative Research Database, a freely available multi-center database for critical care research","volume":"5","author":"TJ Pollard","year":"2018","journal-title":"Sci Data"},{"key":"pone.0334526.ref021","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.jclinepi.2021.09.008","article-title":"Missing data was handled inconsistently in UK prediction models: a review of method used","volume":"140","author":"A Tsvetanova","year":"2021","journal-title":"J Clin Epidemiol"},{"key":"pone.0334526.ref022","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/3-540-57091-8_31","article-title":"Automatic one-hot re-encoding for FPGAs","author":"D Allen","year":"1993","journal-title":"Lecture Notes in Computer Science"},{"issue":"6","key":"pone.0334526.ref023","doi-asserted-by":"crossref","first-page":"441","DOI":"10.2471\/BLT.06.034421","article-title":"Standard deviation of anthropometric Z-scores as a data quality assessment tool using the 2006 WHO growth standards: a cross country analysis","volume":"85","author":"Z Mei","year":"2007","journal-title":"Bull World Health Organ"},{"issue":"8","key":"pone.0334526.ref024","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1057\/jors.2008.179","article-title":"A two-stage classification procedure for near-infrared spectra based on multi-scale vertical energy wavelet thresholding and SVM-based gradient-recursive feature elimination","volume":"60","author":"H-W Cho","year":"2009","journal-title":"Journal of the Operational Research Society"},{"key":"pone.0334526.ref025","author":"SD Greenwald","year":"1986"},{"key":"pone.0334526.ref026","first-page":"6","author":"N Spolaor","year":"2013"},{"key":"pone.0334526.ref027","article-title":"Generalized Fisher Score for Feature Selection","author":"Q Gu","year":"2012","journal-title":"CoRR"},{"key":"pone.0334526.ref028","author":"H Park","year":"2010"},{"issue":"7","key":"pone.0334526.ref029","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0159654","article-title":"Machine Learning Techniques for the Detection of Shockable Rhythms in Automated External Defibrillators","volume":"11","author":"C Figuera","year":"2016","journal-title":"PLoS One"},{"issue":"6","key":"pone.0334526.ref030","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1021\/ci034160g","article-title":"Random forest: a classification and regression tool for compound classification and QSAR modeling","volume":"43","author":"V Svetnik","year":"2003","journal-title":"J Chem Inf Comput Sci"},{"issue":"3","key":"pone.0334526.ref031","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/S0300-9572(98)00012-4","article-title":"Logistic regression model to predict outcome after in-hospital cardiac arrest: validation, accuracy, sensitivity and specificity","volume":"36","author":"PM Dodek","year":"1998","journal-title":"Resuscitation"},{"issue":"1","key":"pone.0334526.ref032","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1007\/s40846-023-00777-0","article-title":"Diagnosis of Respiratory Changes in Cystic Fibrosis Using a Soft Voting Ensemble with Bayesian Networks and Machine Learning Algorithms","volume":"43","author":"NP Pinto","year":"2023","journal-title":"J Med Biol Eng"},{"key":"pone.0334526.ref033","first-page":"785","author":"T Chen","year":"2016"},{"issue":"4","key":"pone.0334526.ref034","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1007\/s40484-016-0081-2","article-title":"Performance measures in evaluating machine learning based bioinformatics predictors for classifications","volume":"4","author":"Y Jiao","year":"2016","journal-title":"Quant Biol"},{"issue":"7","key":"pone.0334526.ref035","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1097\/CCM.0000000000003148","article-title":"Inclusion of Unstructured Clinical Text Improves Early Prediction of Death or Prolonged ICU Stay","volume":"46","author":"GE Weissman","year":"2018","journal-title":"Crit Care Med"},{"key":"pone.0334526.ref036","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/j.jss.2017.09.002","article-title":"Postoperative neonatal mortality prediction using superlearning","volume":"221","author":"JN Cooper","year":"2018","journal-title":"J Surg Res"},{"key":"pone.0334526.ref037","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.ijmedinf.2017.10.002","article-title":"Early hospital mortality prediction of intensive care unit patients using an ensemble learning approach","volume":"108","author":"A Awad","year":"2017","journal-title":"Int J Med Inform"},{"issue":"4","key":"pone.0334526.ref038","doi-asserted-by":"crossref","first-page":"954","DOI":"10.1097\/CCM.0b013e3182772adb","article-title":"Dynamic data during hypotensive episode improves mortality predictions among patients with sepsis and hypotension","volume":"41","author":"L Mayaud","year":"2013","journal-title":"Crit Care Med"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0334526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:28:12Z","timestamp":1761154092000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0334526"}},"subtitle":[],"editor":[{"given":"Yashwanth","family":"Nanda Kumar","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":38,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0334526","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,22]]}}}