{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T15:03:16Z","timestamp":1775574196624,"version":"3.50.1"},"posted":{"date-parts":[[2026,4,4]]},"group-title":"Public and Global Health","reference-count":33,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T00:00:00Z","timestamp":1775260800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,4,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Introduction<\/jats:title>\n                  <jats:p>Current tuberculosis (TB) screening tools, such as the WHO four-symptom screen (W4SS), lack sufficient sensitivity and specificity for effective community-based active case finding, contributing to both missed diagnoses and unnecessary diagnostic evaluations. This study aimed to develop and validate a machine learning (ML) model to improve TB risk prediction among persons aged \u226515 years in community settings of Zambia and South Africa.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>A large, harmonized dataset was created from four community-based TB prevalence surveys in South Africa and Zambia (N=169,813), restricted to individuals not under treatment at the time of survey. A binary reference outcome was defined based on available microbiological and radiographic data, grouping individuals as either \u2018Possible TB\u2019 or \u2018Unlikely TB\u2019. An XGBoost model was trained on 80% (N=135,854) of the data using demographic, clinical, and socio-economic variables, and model interpretability was assessed using SHapley Additive exPlanations (SHAP) values. Internal validation was performed using a 20% hold-out test set (N=33,959). Model performance was assessed using discrimination, calibration, and clinical utility measures compared to the W4SS and against WHO\u2019s 2025 Target Product Profile (TPP) for a tool in a two-step screening algorithm.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Overall, 16,413 (9.7%) of individuals were labelled as \u2018Possible TB\u2019. On the test set, the XGBoost model yielded an area under the curve (AUC) of 79.7% (95% CI: 78.7, 80.7), outperforming the W4SS (AUC 57.0%; 95% CI: 56.1, 57.8). The XGBoost model achieved 81.5% sensitivity (95% CI: 77.6, 84.9) at a 60% specificity threshold. This exceeded the W4SS, which achieved only 38.2% sensitivity (95% CI: 36.5, 39.9) on the same dataset. SHAP analysis identified age, previous TB treatment, times treated for TB and unemployment as the primary contributors to risk.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>The ML XGBoost model shows promise as a screening tool to support community-based active case finding activities prior to diagnostic testing. However, as performance remained below TPP targets, and adding variables, e.g. on geolocation, could be considered.<\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.03.30.26349632","type":"posted-content","created":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T15:55:17Z","timestamp":1775318117000},"source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of a machine learning model for community-based tuberculosis screening among persons aged \u2265 15 years in South Africa and Zambia"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6047-0923","authenticated-orcid":false,"given":"Alexandra J.","family":"Zimmer","sequence":"first","affiliation":[{"name":"Heidelberg University Medical Faculty, Heidelberg University Hospital, Department of Infectious Disease and Tropical Medicine, Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kindie","family":"Fentahun Muchie","sequence":"additional","affiliation":[{"name":"Heidelberg University Medical Faculty, Heidelberg University Hospital, Department of Infectious Disease and Tropical Medicine, Heidelberg, Germany"},{"name":"Department of Epidemiology and Biostatistics, School of Public Health, College of Medicine and Health Sciences, Bahir Dar University, Bahir Dar, Ethiopia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henry","family":"Loharja","sequence":"additional","affiliation":[{"name":"Heidelberg University Medical Faculty, Heidelberg University Hospital, Department of Infectious Disease and Tropical Medicine, Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lisa","family":"Koeppel","sequence":"additional","affiliation":[{"name":"Heidelberg University Medical Faculty, Heidelberg University Hospital, Department of Infectious Disease and Tropical Medicine, Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Ayles","sequence":"additional","affiliation":[{"name":"Zambart, University of Zambia School of Public Health Ridgeway Campus, Lusaka, Zambia"},{"name":"Clinical Research Department, London School of Hygiene and Tropical Medicine, Keppel Street, London UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0485-2919","authenticated-orcid":false,"given":"Maria del Mar","family":"Castro","sequence":"additional","affiliation":[{"name":"Heidelberg University Medical Faculty, Heidelberg University Hospital, Department of Infectious Disease and Tropical Medicine, Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evangelia","family":"Christodoulou","sequence":"additional","affiliation":[{"name":"German Cancer Research Center (DKFZ) Heidelberg, Div. Intelligent Medical Systems, Germany"},{"name":"National Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and Heidelberg University Hospital, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Greg J.","family":"Fox","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Health, The University of Sydney, Sydney, NSW Australia 2006"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6713-3495","authenticated-orcid":false,"given":"Mary","family":"Gaeddert","sequence":"additional","affiliation":[{"name":"Heidelberg University Medical Faculty, Heidelberg University Hospital, Department of Infectious Disease and Tropical Medicine, Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yohhei","family":"Hamada","sequence":"additional","affiliation":[{"name":"Institute for Global Health, University College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris","family":"Isaacs","sequence":"additional","affiliation":[{"name":"Connected Diagnostics Ltd, London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathan","family":"Kapata","sequence":"additional","affiliation":[{"name":"Medical Faculty, Heidelberg University, Germany"},{"name":"Centre for Global Health and Development in Africa, Lusaka, Zambia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pascalina","family":"Chanda-Kapata","sequence":"additional","affiliation":[{"name":"Independent Health and Development Consultant, Lusaka, Zambia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kasra","family":"Karimi","sequence":"additional","affiliation":[{"name":"Heidelberg University Medical Faculty, Heidelberg University Hospital, Department of Infectious Disease and Tropical Medicine, Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nkatya","family":"Kasese","sequence":"additional","affiliation":[{"name":"Zambart, University of Zambia School of Public Health Ridgeway Campus, Lusaka, Zambia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5023-6658","authenticated-orcid":false,"given":"Andrew D.","family":"Kerkhoff","sequence":"additional","affiliation":[{"name":"Division of HIV, Infectious Diseases, and Global Medicine, Zuckerberg San Francisco General Hospital and Trauma Center, University of California San Francisco, San Francisco, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Irwin","family":"Law","sequence":"additional","affiliation":[{"name":"Department for HIV, tuberculosis, hepatitis and sexually transmitted infections, World Health Organization, Geneva, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lena","family":"Maier-Hein","sequence":"additional","affiliation":[{"name":"German Cancer Research Center (DKFZ) Heidelberg, Div. Intelligent Medical Systems, Germany"},{"name":"National Center for Tumor Diseases (NCT), NCT Heidelberg, a partnership between DKFZ and Heidelberg University Hospital, Germany"},{"name":"DKFZ Heidelberg, Helmholtz Imaging, Germany"},{"name":"Faculty of Mathematics and Computer Science, Heidelberg University, Germany"},{"name":"Medical Faculty, Heidelberg University, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian M.","family":"Marx","sequence":"additional","affiliation":[{"name":"Heidelberg University Medical Faculty, Heidelberg University Hospital, Department of Infectious Disease and Tropical Medicine, Heidelberg, Germany"},{"name":"South African Centre for Epidemiological Modelling and Analysis (SACEMA), Center for Epidemic Response and Innovation, School of Data Science, Stellenbosch University, Stellenbosch, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minyoi M.","family":"Maimbolwa","sequence":"additional","affiliation":[{"name":"Tuberculosis Department, Centre of Infectious Disease Research in Zambia (CIDRZ), Lusaka, Zambia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sizulu","family":"Moyo","sequence":"additional","affiliation":[{"name":"Human Sciences Research Council, Cape Town, South Africa; Faculty of Medical and Health Sciences, Stellenbosch University, Cape Town, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thuli","family":"Mthiyane","sequence":"additional","affiliation":[{"name":"South Africa Medical Research Council, Pretoria, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Monde","family":"Muyoyeta","sequence":"additional","affiliation":[{"name":"Tuberculosis Department, Centre of Infectious Disease Research in Zambia (CIDRZ), Lusaka, Zambia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joacim","family":"Rockl\u00f6v","sequence":"additional","affiliation":[{"name":"Human Sciences Research Council, Cape Town, South Africa; Faculty of Medical and Health Sciences, Stellenbosch University, Cape Town, South Africa"},{"name":"South Africa Medical Research Council, Pretoria, South Africa"},{"name":"Interdisciplinary Centre for Scientific Computing, Heidelberg University, Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ab","family":"Schaap","sequence":"additional","affiliation":[{"name":"Zambart, University of Zambia School of Public Health Ridgeway Campus, Lusaka, Zambia"},{"name":"Clinical Research Department, London School of Hygiene and Tropical Medicine, Keppel Street, London UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seda","family":"Yerlikaya","sequence":"additional","affiliation":[{"name":"Heidelberg University Medical Faculty, Heidelberg University Hospital, Department of Infectious Disease and Tropical Medicine, Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Opata","sequence":"additional","affiliation":[{"name":"Interdisciplinary Centre for Scientific Computing, Heidelberg University, Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudia M.","family":"Denkinger","sequence":"additional","affiliation":[{"name":"Heidelberg University Medical Faculty, Heidelberg University Hospital, Department of Infectious Disease and Tropical Medicine, Heidelberg, Germany"},{"name":"German Center of Infection Research, Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026040707200404000_2026.03.30.26349632v1.1","unstructured":"World Health Organization. Global Tuberculosis Report 2025. 2025."},{"key":"2026040707200404000_2026.03.30.26349632v1.2","unstructured":"World Health Organization. WHO Consolidated Guidelines on Tuberculosis: Module 2: Screening: Systematic Screening for Tuberculosis Disease. 2021. Accessed October 23, 2025. https:\/\/www.who.int\/publications\/i\/item\/9789240022676"},{"key":"2026040707200404000_2026.03.30.26349632v1.3","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(19)30024-8"},{"key":"2026040707200404000_2026.03.30.26349632v1.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmyco.2016.09.023"},{"key":"2026040707200404000_2026.03.30.26349632v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/S2214-109X(25)00276-1"},{"key":"2026040707200404000_2026.03.30.26349632v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/S1473-3099(24)00011-2"},{"key":"2026040707200404000_2026.03.30.26349632v1.7","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciaa1402"},{"key":"2026040707200404000_2026.03.30.26349632v1.8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1000391"},{"key":"2026040707200404000_2026.03.30.26349632v1.9","doi-asserted-by":"publisher","DOI":"10.1016\/S2352-3018(18)30137-1"},{"key":"2026040707200404000_2026.03.30.26349632v1.10","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph15040729"},{"key":"2026040707200404000_2026.03.30.26349632v1.11","doi-asserted-by":"publisher","DOI":"10.5588\/ijtld.22.0567"},{"key":"2026040707200404000_2026.03.30.26349632v1.12","unstructured":"World Health Organization. Target product profiles for tuberculosis screening tests. 2025. Accessed October 24, 2025. https:\/\/www.who.int\/publications\/i\/item\/9789240113572"},{"key":"2026040707200404000_2026.03.30.26349632v1.13","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-023-04698-z"},{"key":"2026040707200404000_2026.03.30.26349632v1.14","doi-asserted-by":"publisher","DOI":"10.2196\/68898"},{"key":"2026040707200404000_2026.03.30.26349632v1.15","doi-asserted-by":"publisher","DOI":"10.5588\/ijtld.16.0059"},{"key":"2026040707200404000_2026.03.30.26349632v1.16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1003420"},{"key":"2026040707200404000_2026.03.30.26349632v1.17","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciz1221"},{"key":"2026040707200404000_2026.03.30.26349632v1.18","doi-asserted-by":"publisher","DOI":"10.1093\/ofid\/ofu095"},{"key":"2026040707200404000_2026.03.30.26349632v1.19","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"2026040707200404000_2026.03.30.26349632v1.20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0146392"},{"key":"2026040707200404000_2026.03.30.26349632v1.21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1004278"},{"key":"2026040707200404000_2026.03.30.26349632v1.22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172881"},{"key":"2026040707200404000_2026.03.30.26349632v1.23","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m441"},{"key":"2026040707200404000_2026.03.30.26349632v1.24","doi-asserted-by":"publisher","DOI":"10.1002\/sim.8806"},{"key":"2026040707200404000_2026.03.30.26349632v1.25","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v045.i03"},{"key":"2026040707200404000_2026.03.30.26349632v1.26","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/63.3.581"},{"key":"2026040707200404000_2026.03.30.26349632v1.27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1705.07874"},{"key":"2026040707200404000_2026.03.30.26349632v1.28","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X06295361"},{"key":"2026040707200404000_2026.03.30.26349632v1.29","doi-asserted-by":"publisher","DOI":"10.32614\/CRAN.package.rmda"},{"key":"2026040707200404000_2026.03.30.26349632v1.30","doi-asserted-by":"publisher","DOI":"10.21037\/jtd-2025-604"},{"key":"2026040707200404000_2026.03.30.26349632v1.31","unstructured":"WHO recommends near point-of-care tests, tongue swabs, and sputum pooling for TB diagnosis. Accessed March 27, 2026. https:\/\/www.who.int\/news\/item\/09-03-2026-who-recommends-near-point-of-care-tests--tongue-swabs--and-sputum-pooling-for-tb-diagnosis"},{"key":"2026040707200404000_2026.03.30.26349632v1.32","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1203517109"},{"key":"2026040707200404000_2026.03.30.26349632v1.33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtbi.2024.111988"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.03.30.26349632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T14:20:38Z","timestamp":1775571638000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.03.30.26349632"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.64898\/2026.03.30.26349632","relation":{},"subject":[],"published":{"date-parts":[[2026,4,4]]},"subtype":"preprint"}}