{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T10:12:19Z","timestamp":1767175939856,"version":"build-2238731810"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1013651","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000}}],"reference-count":22,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T00:00:00Z","timestamp":1762214400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000277","name":"Department for Environment, Food and Rural Affairs, UK Government","doi-asserted-by":"publisher","award":["SE3330"],"award-info":[{"award-number":["SE3330"]}],"id":[{"id":"10.13039\/501100000277","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000268","name":"Biotechnology and Biological Sciences Research Council","doi-asserted-by":"publisher","award":["BBS\/E\/D\/20002174"],"award-info":[{"award-number":["BBS\/E\/D\/20002174"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Diagnostic tests that can detect pre-clinical or sub-clinical infection, are one of the most powerful tools in our armoury of weapons to control infectious diseases. Considerable effort has been paid to improving diagnostic testing for human, plant and animal diseases, including strategies for targeting the use of diagnostic tests towards individuals who are more likely to be infected. We use machine learning to assess the surrounding risk landscape under which a diagnostic test is applied to augment its interpretation. We develop this to predict the occurrence of bovine tuberculosis incidents in cattle herds, exploiting the availability of exceptionally detailed testing records. We show that, without compromising test specificity, test sensitivity can be improved so that the proportion of infected herds detected improves by over 5 percentage points, or 240 additional infected herds detected in one year beyond those detected by the skin test alone. We also use feature importance testing for assessing the weighting of risk factors. While many factors are associated with increased risk of incidents, of note are several factors that suggest that in some herds there is a higher risk of infection going undetected.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1013651","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T18:41:47Z","timestamp":1762281707000},"page":"e1013651","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning augmented diagnostic testing to identify sources of variability in test performance"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7650-1598","authenticated-orcid":true,"given":"Christopher Jon","family":"Banks","sequence":"first","affiliation":[]},{"given":"Aeron","family":"Sanchez","sequence":"additional","affiliation":[]},{"given":"Vicki","family":"Stewart","sequence":"additional","affiliation":[]},{"given":"Kate","family":"Bowen","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Doherty","sequence":"additional","affiliation":[]},{"given":"Oliver","family":"Tearne","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9897-6794","authenticated-orcid":true,"given":"Graham","family":"Smith","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0919-6401","authenticated-orcid":true,"given":"Rowland R.","family":"Kao","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2025,11,4]]},"reference":[{"issue":"1768","key":"pcbi.1013651.ref001","first-page":"20131634","article-title":"A restatement of the natural science evidence base relevant to the control of bovine tuberculosis in Great Britain","volume":"280","author":"HCJ Godfray","year":"2013","journal-title":"Proc Biol Sci."},{"key":"pcbi.1013651.ref002","unstructured":"Department for Environment, Food and Rural Affairs. Bovine TB: How to spot and report the disease; 2021. https:\/\/www.gov.uk\/guidance\/bovine-tb"},{"key":"pcbi.1013651.ref003","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1186\/1746-6148-8-51","article-title":"Risk factors for bovine Tuberculosis at the national level in Great Britain","volume":"8","author":"PR Bessell","year":"2012","journal-title":"BMC Vet Res."},{"key":"pcbi.1013651.ref004","unstructured":"Uberoi E. Bovine TB Statistics: Great Britain. House of Commons Library; 2019."},{"key":"pcbi.1013651.ref005","article-title":"The road not traveled: Bovine tuberculosis in England, Wales, and Michigan, USA","author":"DJ O\u2019Brien","year":"2023","journal-title":"One Health Cases."},{"issue":"8","key":"pcbi.1013651.ref006","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0043217","article-title":"Estimation of the relative sensitivity of the comparative tuberculin skin test in tuberculous cattle herds subjected to depopulation","volume":"7","author":"K Karolemeas","year":"2012","journal-title":"PLoS One."},{"issue":"10","key":"pcbi.1013651.ref007","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1136\/vr.102961","article-title":"Specificity of the comparative skin test for bovine tuberculosis in Great Britain","volume":"177","author":"AV Goodchild","year":"2015","journal-title":"Vet Rec."},{"issue":"2","key":"pcbi.1013651.ref008","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.rvsc.2005.11.005","article-title":"Ante mortem diagnosis of tuberculosis in cattle: a review of the tuberculin tests, gamma-interferon assay and other ancillary diagnostic techniques","volume":"81","author":"R de la Rua-Domenech","year":"2006","journal-title":"Res Vet Sci."},{"issue":"1","key":"pcbi.1013651.ref009","doi-asserted-by":"crossref","first-page":"2208","DOI":"10.1038\/s41598-021-81716-4","article-title":"Using machine learning improves predictions of herd-level bovine tuberculosis breakdowns in Great Britain","volume":"11","author":"K Sta \u0144ski","year":"2021","journal-title":"Sci Rep."},{"key":"pcbi.1013651.ref010","unstructured":"Northern Ireland Audit Office. The control of bovine tuberculosis in Northern Ireland; 2016. https:\/\/www.niauditoffice.gov.uk\/publications\/control-bovine-tuberculosis-northern-ireland"},{"key":"pcbi.1013651.ref011","unstructured":"TB Hub. Refinements to the interferon-gamma testing policy in the high risk and edge area of England; 2021. https:\/\/tbhub.co.uk\/tb-policy\/england\/refinements-to-the-interferon-gamma-testing-policy-in-the-high-risk-and-edge-area-of-england\/"},{"key":"pcbi.1013651.ref012","unstructured":"Animal and Plant Health Agency. Sam online TB test submission. http:\/\/apha.defra.gov.uk\/official-vets\/access-to-sam\/index.htm"},{"key":"pcbi.1013651.ref013","unstructured":"British Cattle Movement Service. Use cattle tracing system (CTS) online. https:\/\/www.gov.uk\/cattle-tracing-online"},{"key":"pcbi.1013651.ref014","unstructured":"UK Farmcare Ltd. UK Farmcare Ltd. https:\/\/ukfarmcare.com\/"},{"key":"pcbi.1013651.ref015","unstructured":"Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, et al. LightGBM: A highly efficient gradient boosting decision tree. In: Advances in neural information processing systems. vol. 30. Curran Associates, Inc.; 2017."},{"key":"pcbi.1013651.ref016","unstructured":"scikit-learn. Ensembles: Gradient boosting, random forests, bagging, voting, stacking. https:\/\/scikit-learn\/stable\/modules\/ensemble.html#histogram-based-gradient-boosting"},{"issue":"6","key":"pcbi.1013651.ref017","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0176339","article-title":"A systematic approach to estimate the distribution and total abundance of British mammals","volume":"12","author":"S Croft","year":"2017","journal-title":"PLoS One."},{"issue":"31","key":"pcbi.1013651.ref018","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1098\/rsif.2008.0172","article-title":"Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems","volume":"6","author":"T Toni","year":"2009","journal-title":"J R Soc Interface."},{"key":"pcbi.1013651.ref019","unstructured":"Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Advances in neural information processing systems. Curran Associates, Inc.; 2017."},{"key":"pcbi.1013651.ref020","unstructured":"Department for Environment, Food and Rural Affairs. Bovine TB Statistics; 2023. https:\/\/www.gov.uk\/government\/collections\/bovine-tb"},{"issue":"2","key":"pcbi.1013651.ref021","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1017\/S0950268812000635","article-title":"Developing a framework for risk-based surveillance of tuberculosis in cattle: A case study of its application in Scotland","volume":"141","author":"PR Bessell","year":"2013","journal-title":"Epidemiol Infect."},{"issue":"1","key":"pcbi.1013651.ref022","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1017\/S0950268817001935","article-title":"Risk-based strategies for surveillance of tuberculosis infection in cattle for low-risk areas in England and Scotland","volume":"146","author":"LCM Salvador","year":"2018","journal-title":"Epidemiol Infect."}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1013651","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T18:44:19Z","timestamp":1764096259000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013651"}},"subtitle":[],"editor":[{"given":"Hannah E.","family":"Clapham","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,11,4]]},"references-count":22,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013651","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,4]]}}}