{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T20:03:44Z","timestamp":1784837024864,"version":"3.55.0"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["82060341"],"award-info":[{"award-number":["82060341"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The specific research fund of The Innovation Platform for Academicians of Hainan Province","award":["YSPTZX202134"],"award-info":[{"award-number":["YSPTZX202134"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>\n                      To assess whether liver and kidney metabolomics combined with machine learning can distinguish seawater drowning from postmortem submersion after CO\n                      <jats:sub>2<\/jats:sub>\n                      euthanasia and estimate postmortem interval (PMI) under controlled conditions.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Sixty male Sprague\u2013Dawley rats were assigned to a seawater-drowning group or a postmortem-submersion group after CO\n                      <jats:sub>2<\/jats:sub>\n                      euthanasia (30 per group). Liver and kidney tissues were collected at 0, 12, 24, 36, 48, and 72 h after death and analyzed by untargeted LC\u2013MS\/MS. Principal component analysis (PCA) and cross-validated orthogonal partial least squares discriminant analysis (OPLS-DA) were used to characterize global metabolic variation. Random Forest (RF), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Gradient Boosting Decision Tree (GBDT) were evaluated using repeated 10-fold cross-validation (five repeats; 50 folds in total). PMI-specific XGBoost models used 20 metabolites selected within each training fold by absolute Spearman correlation and were assessed by repeated 10-fold and leave-one-time-point-out cross-validation. SHAP analysis summarized feature contributions.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      PCA showed that dominant metabolic variation was mainly associated with PMI, with substantial overlap between the two groups in the PC1\u2013PC2 space. Cross-validated OPLS-DA identified group-associated structure in liver and kidney, with Q\n                      <jats:sup>2<\/jats:sup>\n                      (cum) values of 0.847 and 0.723, respectively. Mean classification AUCs ranged from 0.973 to 0.996 in liver and from 0.931 to 1.000 in kidney. Under repeated 10-fold cross-validation, the liver and kidney PMI models achieved MAEs of 4.78 and 4.05 h and R\n                      <jats:sup>2<\/jats:sup>\n                      values of 0.823 and 0.892, respectively. Under leave-one-time-point-out cross-validation, MAEs increased to 13.52 and 13.64 h, while R\n                      <jats:sup>2<\/jats:sup>\n                      values were 0.587 and 0.592. SHAP analysis showed partly different metabolite contribution patterns between the two organs.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      In this controlled rat model, liver and kidney metabolomic profiles combined with machine learning supported discrimination between seawater drowning and postmortem submersion after CO\n                      <jats:sub>2<\/jats:sub>\n                      euthanasia and captured PMI-related metabolic changes. The classification models, PMI-specific XGBoost regression models, and SHAP analyses characterized organ-specific metabolite patterns associated with discrimination between the two modeled conditions and PMI prediction.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0353958","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T19:13:26Z","timestamp":1784834006000},"page":"e0353958","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrated machine learning for cause-of-death classification and postmortem interval prediction: Liver and kidney metabolomics from seawater-immersed rat cadavers"],"prefix":"10.1371","volume":"21","author":[{"given":"Jianghuan","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuzhao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siqi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiao","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoshi","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunchao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Ha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2156-0520","authenticated-orcid":true,"given":"Jianqiang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"key":"pone.0353958.ref001","doi-asserted-by":"crossref","first-page":"112251","DOI":"10.1016\/j.forsciint.2024.112251","article-title":"Diagnosing fatal drownings: A review of the postmortem findings","volume":"364","author":"A Tyr","year":"2024","journal-title":"Forensic Sci Int"},{"issue":"20","key":"pone.0353958.ref002","doi-asserted-by":"crossref","first-page":"2302","DOI":"10.3390\/diagnostics14202302","article-title":"Forensic Diatom Analysis: Where Do We Stand and What Are the Latest Diagnostic Advances?","volume":"14","author":"S Tambuzzi","year":"2024","journal-title":"Diagnostics (Basel)"},{"issue":"2","key":"pone.0353958.ref003","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1007\/s00414-024-03397-8","article-title":"The medico-legal interpretation of diatom findings for the diagnosis of fatal drowning: a systematic review","volume":"139","author":"A Tyr","year":"2025","journal-title":"Int J Legal Med"},{"issue":"2","key":"pone.0353958.ref004","first-page":"147","article-title":"Physiology Of Drowning: A Review","volume":"31","author":"JJLM Bierens","year":"2016","journal-title":"Physiology (Bethesda)"},{"issue":"12","key":"pone.0353958.ref005","doi-asserted-by":"crossref","first-page":"801","DOI":"10.3390\/metabo11120801","article-title":"The Application of Metabolomics in Forensic Science with Focus on Forensic Toxicology and Time-of-Death Estimation","volume":"11","author":"J Dawidowska","year":"2021","journal-title":"Metabolites"},{"issue":"3","key":"pone.0353958.ref006","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.3390\/ijms26031034","article-title":"\u201cOmics\u201d and Postmortem Interval Estimation: A Systematic Review","volume":"26","author":"L Secco","year":"2025","journal-title":"Int J Mol Sci"},{"issue":"9","key":"pone.0353958.ref007","doi-asserted-by":"crossref","first-page":"1946","DOI":"10.1021\/acs.chemrestox.1c00211","article-title":"Looking for Post-Mortem Metabolomic Standardization: Waiting for Godot-The Importance of Post-Mortem Interval in Forensic Metabolomics","volume":"34","author":"A Chighine","year":"2021","journal-title":"Chem Res Toxicol"},{"issue":"3","key":"pone.0353958.ref008","doi-asserted-by":"crossref","first-page":"887","DOI":"10.1007\/s00414-023-02975-6","article-title":"PMI estimation through metabolomics and potassium analysis on animal vitreous humour","volume":"137","author":"E Locci","year":"2023","journal-title":"Int J Legal Med"},{"issue":"7","key":"pone.0353958.ref009","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1007\/s11306-020-01700-3","article-title":"Post-mortem changes in metabolomic profiles of human serum, aqueous humor and vitreous humor","volume":"16","author":"EA Zelentsova","year":"2020","journal-title":"Metabolomics"},{"issue":"3","key":"pone.0353958.ref010","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/s11306-024-02117-y","article-title":"Postmortem metabolomics: influence of time since death on the level of endogenous compounds in human femoral blood. Necessary to be considered in metabolome study planning?","volume":"20","author":"AE Steuer","year":"2024","journal-title":"Metabolomics"},{"key":"pone.0353958.ref011","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.83658","article-title":"The \u201cForensOMICS\u201d approach for postmortem interval estimation from human bone by integrating metabolomics, lipidomics, and proteomics","volume":"11","author":"A Bonicelli","year":"2022","journal-title":"Elife"},{"issue":"3","key":"pone.0353958.ref012","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1007\/s00414-022-02783-4","article-title":"A preliminary study on early postmortem submersion interval (PMSI) estimation and cause-of-death discrimination based on nontargeted metabolomics and machine learning algorithms","volume":"136","author":"F-Y Zhang","year":"2022","journal-title":"Int J Legal Med"},{"issue":"5","key":"pone.0353958.ref013","doi-asserted-by":"crossref","first-page":"2037","DOI":"10.1007\/s00414-024-03258-4","article-title":"A fundamental study on postmortem submersion interval estimation by metabolomics analyzing of gastrocnemius muscle from submersed rat models in freshwater","volume":"138","author":"F-Y Zhang","year":"2024","journal-title":"Int J Legal Med"},{"issue":"1","key":"pone.0353958.ref014","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1007\/s00414-022-02844-8","article-title":"A novel method for determining postmortem interval based on the metabolomics of multiple organs combined with ensemble learning techniques","volume":"137","author":"X-J Lu","year":"2023","journal-title":"Int J Legal Med"},{"issue":"5","key":"pone.0353958.ref015","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1007\/s00018-023-04754-3","article-title":"Proteome alterations in human autopsy tissues in relation to time after death","volume":"80","author":"\u00c9 Kocsm\u00e1r","year":"2023","journal-title":"Cell Mol Life Sci"},{"issue":"1","key":"pone.0353958.ref016","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1186\/s12866-023-02786-0","article-title":"Dissecting the microbial community structure of internal organs during the early postmortem period in a murine corpse model","volume":"23","author":"R Liu","year":"2023","journal-title":"BMC Microbiol"},{"key":"pone.0353958.ref017","doi-asserted-by":"crossref","first-page":"1052808","DOI":"10.3389\/fmicb.2022.1052808","article-title":"Microbial communities in the liver and brain are informative for postmortem submersion interval estimation in the late phase of decomposition: A study in mouse cadavers recovered from freshwater","volume":"13","author":"L Wang","year":"2022","journal-title":"Front Microbiol"},{"issue":"6","key":"pone.0353958.ref018","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1007\/s11306-018-1367-3","article-title":"Guidelines and considerations for the use of system suitability and quality control samples in mass spectrometry assays applied in untargeted clinical metabolomic studies","volume":"14","author":"D Broadhurst","year":"2018","journal-title":"Metabolomics"},{"issue":"2","key":"pone.0353958.ref019","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1007\/s11306-023-02080-0","article-title":"Establishing a framework for best practices for quality assurance and quality control in untargeted metabolomics","volume":"20","author":"JD Mosley","year":"2024","journal-title":"Metabolomics"},{"issue":"1","key":"pone.0353958.ref020","doi-asserted-by":"crossref","first-page":"6656","DOI":"10.1038\/s41467-022-34537-6","article-title":"Metabolite annotation from knowns to unknowns through knowledge-guided multi-layer metabolic networking","volume":"13","author":"Z Zhou","year":"2022","journal-title":"Nat Commun"},{"issue":"7","key":"pone.0353958.ref021","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1038\/s41592-021-01197-1","article-title":"Mass spectrometry-based metabolomics: a guide for annotation, quantification and best reporting practices","volume":"18","author":"S Alseekh","year":"2021","journal-title":"Nat Methods"},{"issue":"5","key":"pone.0353958.ref022","doi-asserted-by":"crossref","first-page":"678","DOI":"10.1002\/dta.2540","article-title":"Analytical considerations for (un)-targeted metabolomic studies with special focus on forensic applications","volume":"11","author":"MI Boxler","year":"2019","journal-title":"Drug Test Anal"},{"issue":"1","key":"pone.0353958.ref023","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1039\/C4MB00414K","article-title":"PLS\/OPLS models in metabolomics: the impact of permutation of dataset rows on the K-fold cross-validation quality parameters","volume":"11","author":"MN Triba","year":"2015","journal-title":"Mol Biosyst"},{"key":"pone.0353958.ref024","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, California, United States, 2016. 785\u201394. https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"issue":"1","key":"pone.0353958.ref025","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From Local Explanations to Global Understanding with Explainable AI for Trees","volume":"2","author":"SM Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"issue":"2","key":"pone.0353958.ref026","doi-asserted-by":"crossref","first-page":"512","DOI":"10.3390\/biomedicines10020512","article-title":"Comparative Study of the Aftereffect of CO2 Inhalation or Tiletamine-Zolazepam-Xylazine Anesthesia on Laboratory Outbred Rats and Mice","volume":"10","author":"ON Khokhlova","year":"2022","journal-title":"Biomedicines"},{"issue":"5","key":"pone.0353958.ref027","doi-asserted-by":"crossref","first-page":"109794","DOI":"10.1016\/j.isci.2024.109794","article-title":"Postmortem metabolomics as a high-throughput cause-of-death screening tool for human death investigations","volume":"27","author":"LJ Ward","year":"2024","journal-title":"iScience"},{"issue":"30","key":"pone.0353958.ref028","doi-asserted-by":"crossref","first-page":"16123","DOI":"10.1021\/acs.analchem.4c05796","article-title":"Untangling the Postmortem Metabolome: A Machine Learning Approach for Accurate PMI Estimation","volume":"97","author":"IMM L\u00f8ber","year":"2025","journal-title":"Anal Chem"},{"issue":"1","key":"pone.0353958.ref029","doi-asserted-by":"crossref","first-page":"1504","DOI":"10.1038\/s41467-026-69158-w","article-title":"The human metabolome and machine learning improves predictions of the post-mortem interval","volume":"17","author":"R Magnusson","year":"2026","journal-title":"Nat Commun"},{"key":"pone.0353958.ref030","doi-asserted-by":"crossref","first-page":"116443","DOI":"10.1016\/j.jpba.2024.116443","article-title":"Untargeted and targeted metabolomics analysis of CO poisoning and mechanical asphyxia postmortem interval biomarkers in rat and human plasma by GCMS","volume":"251","author":"Y Fu","year":"2024","journal-title":"J Pharm Biomed Anal"},{"issue":"2","key":"pone.0353958.ref031","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1007\/s12024-023-00643-0","article-title":"A pilot study investigating early postmortem interval of rats based on ambient temperature and postmortem interval-related metabolites in blood","volume":"20","author":"S Fang","year":"2024","journal-title":"Forensic Sci Med Pathol"},{"issue":"5","key":"pone.0353958.ref032","doi-asserted-by":"crossref","first-page":"2561","DOI":"10.1007\/s00414-025-03523-0","article-title":"Estimation of postmortem interval under different ambient temperatures based on multi-organ metabolomics and machine learning algorithm","volume":"139","author":"W Fan","year":"2025","journal-title":"Int J Legal Med"},{"issue":"11","key":"pone.0353958.ref033","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0224365","article-title":"Machine learning algorithm validation with a limited sample size","volume":"14","author":"A Vabalas","year":"2019","journal-title":"PLoS One"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T19:13:38Z","timestamp":1784834018000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353958"}},"subtitle":[],"editor":[{"given":"Naji Arafat","family":"Mahat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,23]]},"references-count":33,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,23]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0353958","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,23]]}}}