Silvia Seidlitz, Katharina Hölzl, Ayca von Garrel, Jan Sellner, Stephan Katzenschlager, Tobias Hölle, Dania Fischer, Maik von der Forst, Felix C. F. Schmitt, Alexander Studier-Fischer, Markus A. Weigand, Lena Maier-Hein, Maximilian Dietrich
{"title":"AI-powered skin spectral imaging enables instant sepsis diagnosis and outcome prediction in critically ill patients","authors":"Silvia Seidlitz, Katharina Hölzl, Ayca von Garrel, Jan Sellner, Stephan Katzenschlager, Tobias Hölle, Dania Fischer, Maik von der Forst, Felix C. F. Schmitt, Alexander Studier-Fischer, Markus A. Weigand, Lena Maier-Hein, Maximilian Dietrich","doi":"10.1126/sciadv.adw1968","DOIUrl":null,"url":null,"abstract":"<div >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–based HSI analysis enables rapid and noninvasive prediction of sepsis and mortality, with a potential clinical value for enhancing diagnosis and treatment.</div>","PeriodicalId":21609,"journal":{"name":"Science Advances","volume":"11 29","pages":""},"PeriodicalIF":11.7000,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.science.org/doi/reader/10.1126/sciadv.adw1968","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Science Advances","FirstCategoryId":"103","ListUrlMain":"https://www.science.org/doi/10.1126/sciadv.adw1968","RegionNum":1,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
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–based HSI analysis enables rapid and noninvasive prediction of sepsis and mortality, with a potential clinical value for enhancing diagnosis and treatment.
期刊介绍:
Science Advances, an open-access journal by AAAS, publishes impactful research in diverse scientific areas. It aims for fair, fast, and expert peer review, providing freely accessible research to readers. Led by distinguished scientists, the journal supports AAAS's mission by extending Science magazine's capacity to identify and promote significant advances. Evolving digital publishing technologies play a crucial role in advancing AAAS's global mission for science communication and benefitting humankind.