{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:10:02Z","timestamp":1757610602014,"version":"3.44.0"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:00:00Z","timestamp":1752192000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Sepsis is a life-threatening condition that is one of the major causes of death worldwide. Early detection of sepsis is required for fast initialization of an appropriate therapy. Complete blood count data containing information about white blood cells, platelets, hemoglobin, red blood cells, and mean corpuscular volume could serve as early indicators. However, previous approaches are limited by their interpretability (i.e., investigating the influence of feature values on individual predictions) and accessibility (i.e., easy accessibility for clinicians without programming expertise).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We developed a graph-based approach for training machine learning (ML) algorithms to incorporate time-series information for prediction based on complete blood count data. Additionally, we investigated the effect of integrating different ratios to a healthy reference measurement to improve the performance of the previously published ML model. Finally, we developed a web application based on our approaches to increase accessibility.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>While it was irrelevant how exactly the ratio was formed, our approach increased the sensitivity at 80% specificity across all ML models from up to 78.2% to up to 82.9% on an internal dataset (i.e., same tertiary care center) and from 65.4% to 73.4% on an external dataset (i.e., independent tertiary care center) for prospective time-series analysis. Additionally, we propose SBC-SHAP (https:\/\/mdoa-tools.bi.denbi.de\/sbc-shap), a web application that visualizes the sepsis risks and individual interpretations of several ML classifiers.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>We are confident that this tool will increase the interpretability and accessibility of ML models for predicting sepsis based on complete blood count data. SBC-SHAP is open-sourced on https:\/\/github.com\/danielwalke\/sbc_app.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jalm\/jfaf091","type":"journal-article","created":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T11:12:37Z","timestamp":1752232357000},"page":"1226-1240","source":"Crossref","is-referenced-by-count":0,"title":["SBC-SHAP: Increasing the Accessibility and Interpretability of Machine Learning Algorithms for Sepsis Prediction"],"prefix":"10.1093","volume":"10","author":[{"given":"Daniel","family":"Walke","sequence":"first","affiliation":[{"name":"Bioprocess Engineering, Otto von Guericke University , Magdeburg ,","place":["Germany"]},{"name":"Database and Software Engineering Group, Otto von Guericke University , Magdeburg ,","place":["Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Steinbach","sequence":"additional","affiliation":[{"name":"Institute of Laboratory Medicine, Clinical Chemistry and Molecular Diagnostics, Leipzig University Hospital , Leipzig ,","place":["Germany"]},{"name":"Medical Informatics Center\u2014Department for Clinical AI and Translational Medicine, University of Leipzig Medical Center , Leipzig ,","place":["Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thorsten","family":"Kaiser","sequence":"additional","affiliation":[{"name":"University Institute for Laboratory Medicine, Microbiology and Clinical Pathobiochemistry, OWL University Hospital of Bielefeld University , Detmold ,","place":["Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Sch\u00f6nhuth","sequence":"additional","affiliation":[{"name":"Faculty of Technology, Bielefeld University , Bielefeld ,","place":["Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gunter","family":"Saake","sequence":"additional","affiliation":[{"name":"Database and Software Engineering Group, Otto von Guericke University , Magdeburg ,","place":["Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Broneske","sequence":"additional","affiliation":[{"name":"German Center for Higher Education Research and Science Studies (DZHW) , Hannover ,","place":["Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Heyer","sequence":"additional","affiliation":[{"name":"Faculty of Technology, Bielefeld University , Bielefeld ,","place":["Germany"]},{"name":"Multidimensional Omics Analyses Group, Leibniz-Institut f\u00fcr Analytische Wissenschaften\u2014ISAS\u2014e.V. , Dortmund ,","place":["Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,7,11]]},"reference":[{"key":"2025090311533875600_jfaf091-B1","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/S0140-6736(19)32989-7","article-title":"Global, regional, and national sepsis incidence and mortality, 1990\u20132017: analysis for the Global Burden of Disease study","volume":"395","author":"Rudd","year":"2020","journal-title":"Lancet"},{"key":"2025090311533875600_jfaf091-B2","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1093\/clinchem\/hvae001","article-title":"Applying machine learning to blood count data predicts sepsis with ICU admission","volume":"70","author":"Steinbach","year":"2024","journal-title":"Clin Chem"},{"key":"2025090311533875600_jfaf091-B3","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1111\/imr.12499","article-title":"The immune system's role in sepsis progression, resolution, and long-term outcome","volume":"274","author":"Delano","year":"2016","journal-title":"Immunol Rev"},{"key":"2025090311533875600_jfaf091-B4","doi-asserted-by":"crossref","first-page":"1881","DOI":"10.3390\/diagnostics11101881","article-title":"The value of a complete blood count (CBC) for sepsis diagnosis and prognosis","volume":"11","author":"Agnello","year":"2021","journal-title":"Diagnostics (Basel)"},{"journal-title":"PLoS ONE","article-title":"Edges are all you need: potential of medical time series analysis with graph neural networks","author":"Walke","key":"2025090311533875600_jfaf091-B5"},{"key":"2025090311533875600_jfaf091-B6","first-page":"4768","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"2025090311533875600_jfaf091-B7","first-page":"9240","article-title":"GNNExplainer: generating explanations for graph neural networks","author":"Ying","year":"2019"},{"article-title":"Parameterized explainer for graph neural network","year":"2020","author":"Luo","key":"2025090311533875600_jfaf091-B8"},{"first-page":"1","article-title":"GRAPHSHAP: explaining identity-aware graph classifiers through the language of motifs","author":"Perotti","key":"2025090311533875600_jfaf091-B9"},{"key":"2025090311533875600_jfaf091-B10","first-page":"827","article-title":"GNNShap: scalable and accurate GNN explanation using shapley values","author":"Akkas","year":"2024"},{"key":"2025090311533875600_jfaf091-B11","first-page":"477","article-title":"InferLine: latency-aware provisioning and scaling for prediction serving pipelines","author":"Crankshaw","year":"2020"},{"author":"Whalen","key":"2025090311533875600_jfaf091-B12"},{"author":"GitHub","key":"2025090311533875600_jfaf091-B13"},{"author":"GitHub","key":"2025090311533875600_jfaf091-B14"},{"first-page":"785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","key":"2025090311533875600_jfaf091-B15"},{"year":"1995","author":"Ho","key":"2025090311533875600_jfaf091-B16"},{"key":"2025090311533875600_jfaf091-B17","doi-asserted-by":"publisher","DOI":"10.1201\/9781315139470","author":"Breiman","year":"2017","edition":"1st Ed"},{"key":"2025090311533875600_jfaf091-B18","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1111\/j.2517-6161.1958.tb00292.x","article-title":"The regression analysis of binary sequences","volume":"20","author":"Cox","year":"1958","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"2025090311533875600_jfaf091-B19","unstructured":"Gibb S, Ahrens P, Steinbach D, Schmidt M, Kaiser T. sbcdata: laboratory diagnostics from septic and non-septic patients used in the AMPEL project. 2024. 10.5281\/zenodo.10781419 (Accessed June 2025)."},{"key":"2025090311533875600_jfaf091-B20","doi-asserted-by":"crossref","first-page":"R200","DOI":"10.1186\/cc12894","article-title":"Body temperature patterns as a predictor of hospital-acquired sepsis in afebrile adult intensive care unit patients: a case-control study","volume":"17","author":"Drewry","year":"2013","journal-title":"Crit Care"},{"key":"2025090311533875600_jfaf091-B21","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1016\/S1473-3099(12)70323-7","article-title":"Procalcitonin as a diagnostic marker for sepsis: a systematic review and meta-analysis","volume":"13","author":"Wacker","year":"2013","journal-title":"Lancet Infect Dis"},{"key":"2025090311533875600_jfaf091-B22","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1007\/s001340050715","article-title":"C-reactive protein as an indicator of sepsis","volume":"24","author":"P\u00f3voa","year":"1998","journal-title":"Intensive Care Med"},{"key":"2025090311533875600_jfaf091-B23","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1007\/s44163-024-00102-x","article-title":"Clustering graph data: the roadmap to spectral techniques","volume":"4","author":"Mondal","year":"2024","journal-title":"Discov Artif Intell"},{"key":"2025090311533875600_jfaf091-B24","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1515\/JLM.2011.004","article-title":"Multizentrische ermittlung von referenzbereichen f\u00fcr parameter des maschinellen blutbildes\/multicentric determination of reference ranges for automated blood counts","volume":"35","author":"Nebe","year":"2011","journal-title":"LaboratoriumsMedizin"},{"key":"2025090311533875600_jfaf091-B25","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1016\/S0889-8588(18)30148-5","article-title":"The automated CBC. A current perspective","volume":"8","author":"Gulati","year":"1994","journal-title":"Hematol Oncol Clin North Am"}],"container-title":["The Journal of Applied Laboratory Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jalm\/article-pdf\/10\/5\/1226\/63727413\/jfaf091.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jalm\/article-pdf\/10\/5\/1226\/63727413\/jfaf091.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T15:54:44Z","timestamp":1756914884000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jalm\/article\/10\/5\/1226\/8196543"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,11]]},"references-count":25,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,7,11]]},"published-print":{"date-parts":[[2025,9,3]]}},"URL":"https:\/\/doi.org\/10.1093\/jalm\/jfaf091","relation":{},"ISSN":["2475-7241"],"issn-type":[{"type":"electronic","value":"2475-7241"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,7,11]]}}}