{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T08:22:48Z","timestamp":1793780568219,"version":"4.6.1"},"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosglobalpublichealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Glob Public Health"],"abstract":"<jats:p>The Ministry of Health and Social Welfare of South Africa has made significant efforts to combat tuberculosis (TB), guided by the National Strategic Plan for addressing HIV, STIs, and TB. However, progress in preventing and eradicating TB has been seriously hindered by reliance on ineffective diagnostic methods. This study aimed to predict and improve TB diagnosis in South Africa using machine learning techniques. Data from the National Income Dynamics Survey, conducted by the Southern African Labour and Development Research Units, were analyzed. The dataset underwent a 70:30 train-test split for Random Forest (RF), Decision Trees (DTs), Support Vector Machines (SVMs), Gradient Boosting Machines (GBMs), Artificial Neural Networks (ANNs), and Logistic Regression (LR). Hyperparameter tuning and impurity-based measures were employed to rank variable importance. RF achieved 87.50% sensitivity and an F1-score of 92.5%. DT achieved a sensitivity of 90.92% and an F1-score of 93.01%. ANN yielded 81.72% sensitivity and an F1-score of 87.53%. SGBMs showed 91.32% sensitivity and 94.55% F1-score. SVMs showed 90.03% sensitivity and 97.72% F1-score. LR achieved a sensitivity of 96.55% and an F1-score of 96.80%. Machine Learning (ML) techniques, with accuracy rates of more than 80% present a significant opportunity for enhancing TB prediction and diagnosis in South Africa. This predictive technique may be beneficial in resource-constrained settings, including those in sub-Saharan Africa.<\/jats:p>","DOI":"10.1371\/journal.pgph.0004674","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:41:31Z","timestamp":1762540891000},"page":"e0004674","update-policy":"https:\/\/doi.org\/10.1371\/journal.pgph.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Predicting and improving diagnosis of tuberculosis outcomes in South Africa using machine learning techniques"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1438-4020","authenticated-orcid":true,"given":"Moses","family":"Asori","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Desmond Mbe-Nyire","family":"Mpuure","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Katey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6733-1539","authenticated-orcid":true,"given":"Razak M.","family":"Gyasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,11,7]]},"reference":[{"key":"pgph.0004674.ref001","unstructured":"WHO W. Global tuberculosis report 2023. 2023. https:\/\/www.who.int\/teams\/global-tuberculosis-programme\/tb-reports\/global-tuberculosis-report-2023"},{"key":"pgph.0004674.ref002","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.socscimed.2015.01.046","article-title":"The economic burden of TB diagnosis and treatment in South Africa","volume":"130","author":"N Foster","year":"2015","journal-title":"Soc Sci Med"},{"issue":"1","key":"pgph.0004674.ref003","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1186\/s12913-021-06398-0","article-title":"Health system determinants of tuberculosis mortality in South Africa: a causal loop model","volume":"21","author":"M Osman","year":"2021","journal-title":"BMC Health Serv Res"},{"issue":"1","key":"pgph.0004674.ref004","doi-asserted-by":"crossref","DOI":"10.1136\/bmjgh-2018-001097","article-title":"Tuberculosis: treatment failure, or failure to treat? Lessons from India and South Africa","volume":"4","author":"N Padayatchi","year":"2019","journal-title":"BMJ Glob Health"},{"key":"pgph.0004674.ref005","doi-asserted-by":"crossref","first-page":"2368","DOI":"10.1109\/BIBM.2018.8621525","article-title":"Using Deep Learning to Classify X-ray Images of Potential Tuberculosis Patients.","author":"O Yadav","year":"2018","journal-title":"2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)"},{"key":"pgph.0004674.ref006","article-title":"Tuberculosis drug resistance profiling based on machine learning: A literature review","volume":"26","author":"A Sharma","year":"2022","journal-title":"Brazilian Journal of Infectious Diseases"},{"key":"pgph.0004674.ref007","doi-asserted-by":"crossref","first-page":"2399428","DOI":"10.1155\/2022\/2399428","article-title":"AI-Assisted Tuberculosis Detection and Classification from Chest X-Rays Using a Deep Learning Normalization-Free Network Model","volume":"2022","author":"V Acharya","year":"2022","journal-title":"Comput Intell Neurosci"},{"issue":"1","key":"pgph.0004674.ref008","doi-asserted-by":"crossref","first-page":"5487","DOI":"10.1038\/s41598-020-62368-2","article-title":"Artificial Intelligence and Machine learning based prediction of resistant and susceptible mutations in Mycobacterium tuberculosis","volume":"10","author":"S Jamal","year":"2020","journal-title":"Sci Rep"},{"key":"pgph.0004674.ref009","doi-asserted-by":"crossref","unstructured":"Kalhori SRN, Zeng XJ. Evaluation and comparison of different machine learning methods to predict outcome of tuberculosis treatment course. 2013.","DOI":"10.4236\/jilsa.2013.53020"},{"issue":"10","key":"pgph.0004674.ref010","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0309151","article-title":"Machine learning algorithms to predict treatment success for patients with pulmonary tuberculosis","volume":"19","author":"S Ahamed Fayaz","year":"2024","journal-title":"PLoS One"},{"issue":"5","key":"pgph.0004674.ref011","doi-asserted-by":"crossref","first-page":"3910","DOI":"10.3390\/ijerph20053910","article-title":"Machine Learning Prediction Model of Tuberculosis Incidence Based on Meteorological Factors and Air Pollutants","volume":"20","author":"N Tang","year":"2023","journal-title":"Int J Environ Res Public Health"},{"key":"pgph.0004674.ref012","doi-asserted-by":"crossref","first-page":"101944","DOI":"10.1016\/j.tube.2020.101944","article-title":"A machine learning-based framework for predicting treatment failure in tuberculosis: A case study of six countries","volume":"123","author":"M Asad","year":"2020","journal-title":"Tuberculosis"},{"key":"pgph.0004674.ref013","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/s12879-015-0750-1","article-title":"Patterns of HIV, TB, and non-communicable disease multi-morbidity in peri-urban South Africa- a cross sectional study","volume":"15","author":"T Oni","year":"2015","journal-title":"BMC Infect Dis"},{"key":"pgph.0004674.ref014","doi-asserted-by":"crossref","DOI":"10.1186\/s12889-016-3972-2","article-title":"Risk factors for mortality in TB patients: A 10-year electronic record review in a South African province","volume":"17","author":"JC Heunis","year":"2017","journal-title":"BMC Public Health"},{"key":"pgph.0004674.ref015","article-title":"In-depth: What new WHO TB numbers mean for SA","author":"C Tomlinson","year":"2023","journal-title":"Spotlight"},{"issue":"20","key":"pgph.0004674.ref016","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics13203163","article-title":"Integrating Molecular Diagnostics and GIS Mapping: A Multidisciplinary Approach to Understanding Tuberculosis Disease Dynamics in South Africa Using Xpert MTB\/RIF","volume":"13","author":"LE Scott","year":"2023","journal-title":"Diagnostics"},{"key":"pgph.0004674.ref017","unstructured":"NIDS. NIDS | South Africa Income Dynamics. http:\/\/www.nids.uct.ac.za\/. 2024. Accessed 2025 March 13."},{"key":"pgph.0004674.ref018","unstructured":"WHO W. Global tuberculosis report 2013. 2013. https:\/\/www.who.int\/publications\/i\/item\/9789241564656"},{"issue":"4","key":"pgph.0004674.ref019","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0122514","article-title":"Tuberculosis prevention in South Africa","volume":"10","author":"GM Knight","year":"2015","journal-title":"PLoS One"},{"issue":"8","key":"pgph.0004674.ref020","doi-asserted-by":"crossref","first-page":"863","DOI":"10.5588\/ijtld.17.0652","article-title":"Daily cough frequency in tuberculosis and association with household infection","volume":"22","author":"RD Turner","year":"2018","journal-title":"Int J Tuberc Lung Dis"},{"key":"pgph.0004674.ref021","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.tube.2019.05.003","article-title":"Is cough really necessary for TB transmission?","volume":"117","author":"B Patterson","year":"2019","journal-title":"Tuberculosis (Edinb)"},{"key":"pgph.0004674.ref022","first-page":"238","article-title":"Acute pneumonia and its complications","author":"CS Mani","year":"2018","journal-title":"Princ Pract Pediatr Infect Dis"},{"key":"pgph.0004674.ref023","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.120.019144","article-title":"Latent tuberculosis infection and elevated incidence of hypertension","volume":"9","author":"E Mandieka","year":"2020","journal-title":"Journal of the American Heart Association"},{"key":"pgph.0004674.ref024","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1128\/CMR.00036-20","article-title":"The echo of pulmonary tuberculosis: mechanisms of clinical symptoms and other disease-induced systemic complications","volume":"33","author":"L Luies","year":"2020","journal-title":"Clinical Microbiology Reviews"},{"issue":"2","key":"pgph.0004674.ref025","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1093\/trstmh\/try124","article-title":"The double burden of diabetes and global infection in low and middle-income countries","volume":"113","author":"S Dunachie","year":"2019","journal-title":"Trans R Soc Trop Med Hyg"},{"issue":"4","key":"pgph.0004674.ref026","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1001\/archinte.167.4.335","article-title":"Risk of tuberculosis from exposure to tobacco smoke: a systematic review and meta-analysis","volume":"167","author":"MN Bates","year":"2007","journal-title":"Arch Intern Med"},{"key":"pgph.0004674.ref027","first-page":"2248","volume-title":"Comparative quantification of health risks: global and regional burden of disease attributable to selected major risk factors","author":"M Ezzati","year":"2004"},{"issue":"1","key":"pgph.0004674.ref028","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1186\/s13011-020-00301-6","article-title":"The prevalence and factors associated with alcohol use disorder among people living with HIV\/AIDS in Africa: a systematic review and meta-analysis","volume":"15","author":"M Necho","year":"2020","journal-title":"Subst Abuse Treat Prev Policy"},{"key":"pgph.0004674.ref029","doi-asserted-by":"crossref","first-page":"109300","DOI":"10.1016\/j.drugalcdep.2022.109300","article-title":"Prevalence and socio-structural determinants of tobacco exposure in young women: Data from the Healthy Trajectories Initiative (HeLTI) study in urban Soweto, South Africa","volume":"232","author":"LM Soepnel","year":"2022","journal-title":"Drug Alcohol Depend"},{"issue":"3","key":"pgph.0004674.ref030","first-page":"278","article-title":"The clinical epidemiology of childhood pulmonary tuberculosis: a critical review of literature from the pre-chemotherapy era","volume":"8","author":"BJ Marais","year":"2004","journal-title":"Int J Tuberc Lung Dis"},{"key":"pgph.0004674.ref031","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.ijid.2016.12.016","article-title":"Tuberculosis and hypertension-a systematic review of the literature","volume":"56","author":"AB Seegert","year":"2017","journal-title":"Int J Infect Dis"},{"issue":"1","key":"pgph.0004674.ref032","doi-asserted-by":"crossref","first-page":"79","DOI":"10.5588\/ijtld.13.0288","article-title":"Tuberculosis increases the subsequent risk of acute coronary syndrome: a nationwide population-based cohort study","volume":"18","author":"W-S Chung","year":"2014","journal-title":"Int J Tuberc Lung Dis"},{"issue":"6","key":"pgph.0004674.ref033","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1016\/0962-8479(95)90529-4","article-title":"Incidence of pulmonary tuberculosis among diabetics","volume":"76","author":"SJ Kim","year":"1995","journal-title":"Tuber Lung Dis"},{"issue":"6","key":"pgph.0004674.ref034","first-page":"696","article-title":"Diabetes mellitus is strongly associated with tuberculosis in Indonesia","volume":"10","author":"B Alisjahbana","year":"2006","journal-title":"Int J Tuberc Lung Dis"},{"key":"pgph.0004674.ref035","volume-title":"National Strategic Plan for HIV | TB | STIs","author":"Welfare M","year":"2024"},{"issue":"10","key":"pgph.0004674.ref036","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0240370","article-title":"Predicting hypertension using machine learning: Findings from Qatar Biobank Study","volume":"15","author":"LA AlKaabi","year":"2020","journal-title":"PLoS One"},{"issue":"1","key":"pgph.0004674.ref037","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1007\/s42399-023-01568-z","article-title":"WHO goals and beyond: managing HIV\/TB co-infection in South Africa","volume":"5","author":"C Olivier","year":"2023","journal-title":"SN Compr Clin Med"},{"issue":"6","key":"pgph.0004674.ref038","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0217836","article-title":"Study on knowledge about associated factors of Tuberculosis (TB) and TB\/HIV co-infection among young adults in two districts of South Africa","volume":"14","author":"S Shamu","year":"2019","journal-title":"PLoS One"},{"issue":"1","key":"pgph.0004674.ref039","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1186\/s12879-018-3256-9","article-title":"HIV and TB co-infection in the ART era: CD4 count distributions and TB case fatality in Cape Town","volume":"18","author":"R Kaplan","year":"2018","journal-title":"BMC Infect Dis"}],"container-title":["PLOS Global Public Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pgph.0004674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:41:38Z","timestamp":1762540898000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pgph.0004674"}},"subtitle":[],"editor":[{"given":"Somayeh","family":"Hessam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,11,7]]},"references-count":39,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11,7]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pgph.0004674","relation":{},"ISSN":["2767-3375"],"issn-type":[{"value":"2767-3375","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,7]]}}}