{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T19:13:01Z","timestamp":1791313981543,"version":"4.3.1"},"reference-count":54,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"29","content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Adv."],"published-print":{"date-parts":[[2025,7,18]]},"abstract":"<jats:p>With sepsis remaining a leading cause of mortality, early identification of patients with sepsis and those at high risk of death is a challenge of high socioeconomic importance. Given the potential of hyperspectral imaging (HSI) to monitor microcirculatory alterations, we propose a deep learning approach to automated sepsis diagnosis and mortality prediction using a single HSI cube acquired within seconds. In a prospective observational study, we collected HSI data from the palms and fingers of more than 480 intensive care unit patients. Neural networks applied to HSI measurements predicted sepsis and mortality with areas under the receiver operating characteristic curve (AUROCs) of 0.80 and 0.72, respectively. Performance improved substantially with additional clinical data, reaching AUROCs of 0.94 for sepsis and 0.83 for mortality. We conclude that deep learning\u2013based HSI analysis enables rapid and noninvasive prediction of sepsis and mortality, with a potential clinical value for enhancing diagnosis and treatment.<\/jats:p>","DOI":"10.1126\/sciadv.adw1968","type":"journal-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:58:34Z","timestamp":1752861514000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":19,"title":["AI-powered skin spectral imaging enables instant sepsis diagnosis and outcome prediction in critically ill patients"],"prefix":"10.1126","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1122-4793","authenticated-orcid":true,"given":"Silvia","family":"Seidlitz","sequence":"first","affiliation":[{"name":"Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany."},{"name":"Helmholtz Information and Data Science School for Health, Heidelberg\/Karlsruhe, Germany."},{"name":"Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany."},{"name":"National Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and university medical center Heidelberg, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4664-0604","authenticated-orcid":true,"given":"Katharina","family":"H\u00f6lzl","sequence":"additional","affiliation":[{"name":"Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany."},{"name":"Medical Faculty, Department of Anesthesiology, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6534-5351","authenticated-orcid":true,"given":"Ayca","family":"von Garrel","sequence":"additional","affiliation":[{"name":"Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany."},{"name":"Medical Faculty, Department of Anesthesiology, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4469-8343","authenticated-orcid":true,"given":"Jan","family":"Sellner","sequence":"additional","affiliation":[{"name":"Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany."},{"name":"Helmholtz Information and Data Science School for Health, Heidelberg\/Karlsruhe, Germany."},{"name":"Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany."},{"name":"National Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and university medical center Heidelberg, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephan","family":"Katzenschlager","sequence":"additional","affiliation":[{"name":"Medical Faculty, Department of Anesthesiology, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"H\u00f6lle","sequence":"additional","affiliation":[{"name":"Medical Faculty, Department of Anesthesiology, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2086-0107","authenticated-orcid":true,"given":"Dania","family":"Fischer","sequence":"additional","affiliation":[{"name":"Medical Faculty, Department of Anesthesiology, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5381-6535","authenticated-orcid":true,"given":"Maik","family":"von der Forst","sequence":"additional","affiliation":[{"name":"Medical Faculty, Department of Anesthesiology, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix C. F.","family":"Schmitt","sequence":"additional","affiliation":[{"name":"Medical Faculty, Department of Anesthesiology, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8682-9300","authenticated-orcid":true,"given":"Alexander","family":"Studier-Fischer","sequence":"additional","affiliation":[{"name":"Department of General, Visceral, and Transplantation Surgery, Heidelberg University Hospital, Heidelberg, Germany."},{"name":"Department of Urology and Urosurgery, Medical Faculty of the University of Heidelberg, University Medical Center Mannheim, Mannheim, Germany."},{"name":"Division of Intelligent Systems and Robotics in Urology (ISRU), German Cancer Research Center (DKFZ), Heidelberg, Germany."},{"name":"DKFZ Hector Cancer Institute at the University Medical Center Mannheim, Mannheim, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus A.","family":"Weigand","sequence":"additional","affiliation":[{"name":"Medical Faculty, Department of Anesthesiology, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4910-9368","authenticated-orcid":true,"given":"Lena","family":"Maier-Hein","sequence":"additional","affiliation":[{"name":"Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany."},{"name":"Helmholtz Information and Data Science School for Health, Heidelberg\/Karlsruhe, Germany."},{"name":"Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany."},{"name":"National Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and university medical center Heidelberg, Heidelberg, Germany."},{"name":"Heidelberg University Hospital, Surgical Clinic, Surgical AI Research Group, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0960-038X","authenticated-orcid":true,"given":"Maximilian","family":"Dietrich","sequence":"additional","affiliation":[{"name":"Medical Faculty, Department of Anesthesiology, Heidelberg University Hospital, Heidelberg University, Heidelberg, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0287"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(19)32989-7"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000000330"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0025-7125(05)70309-6"},{"key":"e_1_3_2_6_2","doi-asserted-by":"crossref","unstructured":"J.-L. Vincent ed. Annual Update in Intensive Care and Emergency Medicine 2023 (Springer Nature Switzerland 2023).","DOI":"10.1007\/978-3-031-23005-9"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000002311"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-11226-4"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.5005\/jp-journals-10071-24063"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-17091-5"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-020-02993-5"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2022.104394"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-019-05872-y"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm12175658"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(22)00154-6"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2021.2626"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2023.102124"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2022-100704"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1152\/jappl.1996.81.2.885"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1111\/aas.12581"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.907992"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0b013e3182742e8b"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.annemergmed.2006.08.021"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.mvr.2021.104164"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000037273"},{"key":"e_1_3_2_26_2","unstructured":"M. Dietrich S. Seidlitz N. Schreck M. Wiesenfarth P. Godau M. Tizabi J. Sellner S. Marx S. Kn\u00f6dler M. M. Allers L. Ayala K. Schmidt T. Brenner A. Studier-Fischer F. Nickel B. P. M\u00fcller-Stich A. Kopp-Schneider M. A. Weigand L. Maier-Hein Machine learning-based analysis of hyperspectral images for automated sepsis diagnosis. arXiv:2106.08445 (2021)."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-024-05023-w"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"M. L\u0101cis S. Kazune Z. Marcinkevics U. Rubins A. Grabovskis Hybrid optical prototype for sepsis bedside diagnostics in Novel Optical Systems Methods and Applications XXII C. F. Hahlweg J. R. Mulley Eds. (International Society for Optics and Photonics (SPIE) 2019) vol. 11105 p. 111050P.","DOI":"10.1117\/12.2529230"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-019-2589-0"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1515\/bmt-2017-0155"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1515\/bmt-2017-0145"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012487302797"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-011-2163-y"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.3233\/CH-190784"},{"key":"e_1_3_2_35_2","unstructured":"Royal College of Physicians National Early Warning Score (NEWS) 2: Standardising the Assessment of Acute-Illness Severity in the NHS (Royal College of Physicians 2012)."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1378\/chest.101.6.1644"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1097\/PCC.0b013e3181b806fc"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1097\/00003246-198510000-00009"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13206-021-00041-0"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.7189\/jogh.13.04141"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00650-5"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1186\/cc14726"},{"key":"e_1_3_2_43_2","unstructured":"J. Sellner S. Seidlitz Hyperspectral Tissue Classification (2024); DOI: 10.5281\/zenodo.6577614. https:\/\/github.com\/IMSY-DKFZ\/htc."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3068392"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2535302"},{"key":"e_1_3_2_46_2","doi-asserted-by":"crossref","unstructured":"K. He X. Zhang S. Ren J. Sun \u201cDeep residual learning for image recognition \u201d in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2016) pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_47_2","unstructured":"R. Wightman PyTorch Image Models (2019). https:\/\/doi.org\/10.5281\/zenodo.4414861."},{"key":"e_1_3_2_48_2","unstructured":"I. Loshchilov F. Hutter Decoupled weight decay regularization. arXiv:1711.05101 (2019)."},{"key":"e_1_3_2_49_2","unstructured":"P. Izmailov D. Podoprikhin T. Garipov D. Vetrov A. G. Wilson Averaging weights leads to wider optima and better generalization. arXiv:1803.05407 (2018)."},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12879-023-08614-0"},{"key":"e_1_3_2_51_2","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa F.","year":"2011","unstructured":"F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, E. Duchesnay, Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-7-91"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-023-02151-z"},{"key":"e_1_3_2_54_2","first-page":"28","article-title":"The generalization of \u2018STUDENT\u2019S\u2019problem when several different population varlances are involved","volume":"34","author":"Welch B. L.","year":"1947","unstructured":"B. L. Welch, The generalization of \u2018STUDENT\u2019S\u2019problem when several different population varlances are involved. Biometrika 34, 28\u201335 (1947).","journal-title":"Biometrika"},{"key":"e_1_3_2_55_2","unstructured":"C. E. Bonferroni \u201cIl calcolo delle assicurazioni su gruppi di teste\u201d in Studi in Onore del Professore Salvatore Ortu Carboni (Tipografia des Senato del dott. G. Bardi 1935) pp. 13\u201360."}],"container-title":["Science Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/sciadv.adw1968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:58:41Z","timestamp":1752861521000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/sciadv.adw1968"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":54,"journal-issue":{"issue":"29","published-print":{"date-parts":[[2025,7,18]]}},"alternative-id":["10.1126\/sciadv.adw1968"],"URL":"https:\/\/doi.org\/10.1126\/sciadv.adw1968","relation":{},"ISSN":["2375-2548"],"issn-type":[{"value":"2375-2548","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,18]]},"assertion":[{"value":"2025-01-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eadw1968"}}