{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T18:14:46Z","timestamp":1783361686345,"version":"3.54.6"},"reference-count":26,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"unspecified","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Department of Clinical Microbiology, Rigshospitalet, Denmark","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]},{"name":"Beta-Health Foundation","award":["1188"],"award-info":[{"award-number":["1188"]}]},{"name":"Den Frie Forskningsfond","award":["3101-00040B"],"award-info":[{"award-number":["3101-00040B"]}]},{"DOI":"10.13039\/501100009708","name":"Novo Nordisk Foundation","doi-asserted-by":"crossref","award":["18OC0033946"],"award-info":[{"award-number":["18OC0033946"]}],"id":[{"id":"10.13039\/501100009708","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Digit Health"],"accepted":{"date-parts":[[2026,5,28]]},"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and evaluate machine learning (ML) models capable of reliably predicting the focus of bacterial infections in hospitalised patients, addressing limitations of conventional microbiological diagnostics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and analysis<\/jats:title>\n                    <jats:p>We conducted a retrospective study using data from 10\u2009153 patients admitted to Rigshospitalet, Denmark, between 1 November 2019 and 3 June 2023. The dataset included microbiological findings, biochemical measurements and vital parameters. ML models were trained and evaluated, with outputs calibrated using Venn-ABERS calibration. Model uncertainty was quantified through conformal risk control to provide statistically robust uncertainty estimates.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>This study shows that the XGBoost model demonstrated the best performance, achieving a log loss of 0.209\u00b10.006 (mean\u00b1SD) and an area under the receiver operating characteristic curve of 0.93\u00b10.007. Incorporating conformal prediction techniques enhanced predictive reliability by combining high accuracy with calibrated probabilistic predictions and uncertainty estimates.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We find that ML models, particularly XGBoost combined with conformal prediction frameworks, can accurately predict the focus of bacterial infections while providing robust uncertainty quantification. This approach offers a promising addition to conventional diagnostic methods, potentially improving clinical decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjdh-2026-000068","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T10:40:11Z","timestamp":1781779211000},"page":"e000068","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning-based prediction of bacterial infection foci: model development, calibration and uncertainty quantification using conformal prediction methods"],"prefix":"10.1136","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7822-8037","authenticated-orcid":false,"given":"Jacob","family":"Bahnsen Schmidt","sequence":"first","affiliation":[{"name":"Department of Clinical Microbiology, Rigshospitalet, Copenhagen, Denmark"},{"name":"Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7912-1985","authenticated-orcid":false,"given":"Karen Leth","family":"Nielsen","sequence":"additional","affiliation":[{"name":"Department of Clinical Microbiology, Rigshospitalet, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dmytro","family":"Strunin","sequence":"additional","affiliation":[{"name":"Department of Clinical Microbiology, Rigshospitalet, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikolai S","family":"Kirkby","sequence":"additional","affiliation":[{"name":"Department of Clinical Microbiology, Rigshospitalet, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesper Q","family":"Thomassen","sequence":"additional","affiliation":[{"name":"Department of Clinical Biochemistry, Rigshospitalet, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steen C","family":"Rasmussen","sequence":"additional","affiliation":[{"name":"Department of Clinical Microbiology, Rigshospitalet, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruth","family":"Frikke-Schmidt","sequence":"additional","affiliation":[{"name":"Department of Clinical Biochemistry, Rigshospitalet, Copenhagen, Denmark"},{"name":"Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0888-4616","authenticated-orcid":false,"given":"Frederik Boetius","family":"Hertz","sequence":"additional","affiliation":[{"name":"Department of Clinical Microbiology, Rigshospitalet, Copenhagen, Denmark"},{"name":"Department of Immunology and Microbiology, University of Copenhagen, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8626-1575","authenticated-orcid":false,"given":"Allan Peter","family":"Engsig-Karup","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,6,18]]},"reference":[{"key":"2026070610204595000_2.1.e000068.1","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-025-01821-6","article-title":"Prediction of bloodstream infection using machine learning based primarily on biochemical data","volume":"15","author":"Marandi","year":"2025","journal-title":"Sci Rep"},{"key":"2026070610204595000_2.1.e000068.2","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.1093\/jac\/dky514","article-title":"Supervised machine learning for the prediction of infection on admission to hospital: a prospective observational cohort study","volume":"74","author":"Rawson","year":"2019","journal-title":"J Antimicrob Chemother"},{"key":"2026070610204595000_2.1.e000068.3","unstructured":"Shafer G , Vovk V . A Tutorial on Conformal Prediction. J Mach Learn Res 2008;9."},{"key":"2026070610204595000_2.1.e000068.4","doi-asserted-by":"crossref","first-page":"1653","DOI":"10.1515\/cclm-2024-0070","article-title":"The EFLM European Urinalysis Guideline 2023","volume":"62","author":"Kouri","year":"2024","journal-title":"Clin Chem Lab Med"},{"key":"2026070610204595000_2.1.e000068.5","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.0830","article-title":"Diagnostic Stewardship in Community-Acquired Pneumonia With Syndromic Molecular Testing: A Randomized Clinical Trial","volume":"7","author":"Markussen","year":"2024","journal-title":"JAMA Netw Open"},{"key":"2026070610204595000_2.1.e000068.6","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1056\/NEJMoa2404991","article-title":"Antibiotic Treatment for 7 versus 14 Days in Patients with Bloodstream Infections","volume":"392","year":"2025","journal-title":"N Engl J Med"},{"key":"2026070610204595000_2.1.e000068.7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2026070610204595000_2.1.e000068.8","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . Xgboost: a scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining; 2016:785\u201394. doi:10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"2026070610204595000_2.1.e000068.9","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203450"},{"key":"2026070610204595000_2.1.e000068.10","unstructured":"Angelopoulos AN , Bates S . A gentle introduction to conformal prediction and distribution-free uncertainty quantification. arXiv [Preprint] 2021."},{"key":"2026070610204595000_2.1.e000068.11","unstructured":"Vovk V , Petej I . Venn-abers predictors. arXiv [Preprint] 2012."},{"key":"2026070610204595000_2.1.e000068.12","unstructured":"Manokhin V . Practical guide to applied conformal prediction in python. Birmingham: Packt Publishing Ltd,"},{"key":"2026070610204595000_2.1.e000068.13","unstructured":"Manokhin V , et al . Multi-class probabilistic classification using inductive and cross venn\u2013abers predictors. In: Gammerman A , Vovk V , Luo Z , eds. 228\u201340."},{"key":"2026070610204595000_2.1.e000068.14","unstructured":"Angelopoulos AN , Bates S , Fisch A , et al . Conformal risk control. arXiv [Preprint] 2022."},{"key":"2026070610204595000_2.1.e000068.15","doi-asserted-by":"crossref","unstructured":"Huang X , Marques-Silva J . The inadequacy of shapley values for explainability. arXiv [Preprint] 2023. doi:10.1016\/j.ijar.2023.109112","DOI":"10.1016\/j.ijar.2023.109112"},{"key":"2026070610204595000_2.1.e000068.16","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":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2026070610204595000_2.1.e000068.17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cca.2016.03.017"},{"key":"2026070610204595000_2.1.e000068.18","doi-asserted-by":"crossref","DOI":"10.1186\/cc13106","article-title":"The impact of body temperature abnormalities on the disease severity and outcome in patients with severe sepsis: an analysis from a multicenter, prospective survey of severe sepsis","volume":"17","author":"Kushimoto","year":"2013","journal-title":"Crit Care"},{"key":"2026070610204595000_2.1.e000068.19","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1111\/j.1466-8238.2007.00358.x","article-title":"AUC: a misleading measure of the performance of predictive distribution models","volume":"17","author":"Lobo","year":"2008","journal-title":"Global Ecology and Biogeography"},{"key":"2026070610204595000_2.1.e000068.20","unstructured":"Matos J . Critical appraisal of fairness metrics in clinical predictive AI. 2025."},{"key":"2026070610204595000_2.1.e000068.21","doi-asserted-by":"publisher","DOI":"10.1145\/3485766"},{"key":"2026070610204595000_2.1.e000068.22","unstructured":"Cresswell JC , Sui Y , Kumar B , et al . Conformal prediction sets improve human decision making. arXiv 13744 [Preprint] 2024."},{"key":"2026070610204595000_2.1.e000068.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.arr.2003.07.002"},{"key":"2026070610204595000_2.1.e000068.24","doi-asserted-by":"publisher","DOI":"10.1183\/09031936.96.09081736"},{"key":"2026070610204595000_2.1.e000068.25","doi-asserted-by":"publisher","DOI":"10.1039\/C7MD00528H"},{"key":"2026070610204595000_2.1.e000068.26","doi-asserted-by":"publisher","DOI":"10.1128\/AAC.00338-07"}],"container-title":["BMJ Digital Health &amp; AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjdh-2026-000068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T17:22:51Z","timestamp":1783358571000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjdigitalhealth.bmj.com\/lookup\/doi\/10.1136\/bmjdh-2026-000068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,6,18]]},"published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1136\/bmjdh-2026-000068"],"URL":"https:\/\/doi.org\/10.1136\/bmjdh-2026-000068","relation":{},"ISSN":["3049-575X"],"issn-type":[{"value":"3049-575X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}