{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"Research Square"}],"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T07:02:53Z","timestamp":1785135773568,"version":"3.55.0"},"posted":{"date-parts":[[2026,7,27]]},"group-title":"In Review","reference-count":25,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,7,23]]},"abstract":"<title>Abstract<\/title>\n                <p>Background\n Tuberculosis (TB) remains a major global health challenge, disproportionately affecting vulnerable populations in resource-limited settings. In Rwanda, the burden is high among high-risk groups including prisoners, mining workers, people living with HIV, and healthcare workers. Despite well-established national surveillance infrastructure, published evidence on applying machine learning (ML) to routinely collected electronic medical records (EMR) for identifying factors associated with TB in these populations remains limited.  This study develops and compares multiple ML models to identify factors associated with TB among high-risk groups using national surveillance data from Kigali health facilities, while emphasizing careful feature engineering to avoid information leakage.\nMethods\n We conducted a retrospective, cross-sectional analysis of 2,254 high-risk patient EMR from Rwanda Biomedical Center (RBC) surveillance systems, with TB status defined by GeneXpert results. Rigorous data cleaning and preprocessing were performed, including exclusion of records with indeterminate outcomes, removal of diagnostic and operational variables that could introduce information leakage, imputation of missing values, normalization of numerical features, and one-hot encoding of categorical variables. Multiple supervised ML models were developed and evaluated using a stratified train\u2013test split, including logistic regression (LR), balanced random forest (BRF), gradient boosting methods (XGBoost, LightGBM, and GBM), support vector machines (SVM) with a radial basis function kernel, and an EasyEnsemble classifier. Model performance was assessed using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic (ROC) curve (AUC).\nResults\n After excluding indeterminate GeneXpert outcomes, 358 cases were retained for evaluation. Ensemble-based models showed consistently strong and stable performance, with BRF achieving the highest discrimination (AUC\u2009=\u20090.86), while GBM, SVM, and EasyEnsemble classifiers showed comparable performance across accuracy, precision, recall, and F1-score. Feature-importance analysis identified clinically meaningful factors, associated with TB, including site of disease, age, TB-related body mass index, HIV status, and diabetes status, indicating that the models relied on plausible biological and demographic risk factors rather than diagnostic artifacts.\nConclusions\n This first application of EMR-driven ML for identifying TB risk factor associations in Rwanda shows that ensemble models, combined with rigorous leakage control, achieve promising performance among high-risk populations. These tools could support national TB surveillance and screening to enhance early detection and resource allocation.<\/p>","DOI":"10.21203\/rs.3.rs-10453356\/v1","type":"posted-content","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T06:30:55Z","timestamp":1785133855000},"source":"Crossref","is-referenced-by-count":0,"title":["Machine learning approaches for tuberculosis prevalence and risk factor association among high-risk groups in Kigali health facilities"],"prefix":"10.21203","author":[{"given":"Theophilla","family":"Igihozo","sequence":"first","affiliation":[{"name":"College of Medicine and Health Sciences, University of Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fiacre Rugamba","family":"Rugero","sequence":"additional","affiliation":[{"name":"College of Medicine and Health Sciences, University of Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma Marie","family":"Umutoniwase","sequence":"additional","affiliation":[{"name":"College of Medicine and Health Sciences, University of Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emelie","family":"Ndoli","sequence":"additional","affiliation":[{"name":"College of Medicine and Health Sciences, University of Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Niyonshuti","sequence":"additional","affiliation":[{"name":"College of Medicine and Health Sciences, University of Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rwubaka","family":"Eugene","sequence":"additional","affiliation":[{"name":"College of Medicine and Health Sciences, University of Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Sibomana","sequence":"additional","affiliation":[{"name":"College of Business and Economics, University of Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melissa","family":"Uwase","sequence":"additional","affiliation":[{"name":"College of Medicine and Health Sciences, University of Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dieudonne","family":"Kayiranga","sequence":"additional","affiliation":[{"name":"College of Medicine and Health Sciences, University of Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Mugisha","sequence":"additional","affiliation":[{"name":"College of Medicine and Health Sciences, University of Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Celestin","family":"Twizere","sequence":"additional","affiliation":[{"name":"Health Informatics, Regional Center of Excellence in Biomedical Engineering & E-Health, University of Rwanda, Kigali Innovation City"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isambi Sailon","family":"Mbalawata","sequence":"additional","affiliation":[{"name":"African Institute for Mathematical Sciences Research and Innovation Centre"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davila-Roman","family":"Victor","sequence":"additional","affiliation":[{"name":"School of Medicine, Washington University in St. Louis, St. Louis"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adams","family":"Wilcox","sequence":"additional","affiliation":[{"name":"School of Medicine, Washington University in St. Louis, St. Louis"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Randi","family":"Foraker","sequence":"additional","affiliation":[{"name":"School of Medicine, University of Missouri, Columbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isaac","family":"Gomina","sequence":"additional","affiliation":[{"name":"School of Medicine, University of Missouri, Columbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelle","family":"Schneider","sequence":"additional","affiliation":[{"name":"Institute for Informatics, Data Science and Biostatistics, Washington University in St. Louis, St. Louis"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Tumusiime","sequence":"additional","affiliation":[{"name":"College of Medicine and Health Sciences, University of Rwanda"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmy","family":"Mugisha","sequence":"additional","affiliation":[{"name":"Health Informatics, Regional Center of Excellence in Biomedical Engineering & E-Health, University of Rwanda, Kigali Innovation City"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/S00415-022-11052-8","article-title":"Global morbidity and mortality of central nervous system tuberculosis: a systematic review and meta-analysis","volume":"269","author":"Navarro-Flores A","year":"2022","unstructured":"Navarro-Flores A, Fernandez-Chinguel JE, Pacheco-Barrios N, Soriano-Moreno DR, Pacheco-Barrios K. Global morbidity and mortality of central nervous system tuberculosis: a systematic review and meta-analysis. J Neurol 2022. 2022;269:7. https:\/\/doi.org\/10.1007\/S00415-022-11052-8.","journal-title":"J Neurol 2022"},{"key":"ref2","unstructured":"World Health Organization. Global tuberculosis report 2025. Geneva, World Health Organization. : 2025. Licence: CC BY-NC-SA 3.0 IGO. Available from: https:\/\/www.who.int\/teams\/global-tuberculosis-programme\/tb-reports\/global-tuberculosis-report-2025"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1093\/inthealth\/ihac039","article-title":"Continuous surveillance of drug-resistant TB burden in Rwanda: a retrospective cross-sectional study","volume":"15","author":"Habimana-Mucyo Y","year":"2023","unstructured":"Habimana-Mucyo Y, Dushime A, Migambi P, Habiyambere I, Semuto Ngabonziza JC, Decroo T. Continuous surveillance of drug-resistant TB burden in Rwanda: a retrospective cross-sectional study. Int Health. 2023;15:357\u201364. https:\/\/doi.org\/10.1093\/inthealth\/ihac039.","journal-title":"Int Health"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.1016\/S1473-3099(23)00372-9","article-title":"Burden of tuberculosis among vulnerable populations worldwide: an overview of systematic reviews","volume":"23","author":"Litvinjenko S","year":"2023","unstructured":"Litvinjenko S, Magwood O, Wu S, Wei X. Burden of tuberculosis among vulnerable populations worldwide: an overview of systematic reviews. Lancet Infect Dis. 2023;23:1395\u2013407. https:\/\/doi.org\/10.1016\/S1473-3099(23)00372-9.","journal-title":"Lancet Infect Dis"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1186\/s41182-021-00358-4","article-title":"Diabetes mellitus and HIV infection among active tuberculosis patients in Northwest Ethiopia: health facility-based cross-sectional study","author":"Tulu B","year":"2021","unstructured":"Tulu B, Amsalu E, Zenebe Y, Abebe M, Fetene Y, Agegn M, et al. Diabetes mellitus and HIV infection among active tuberculosis patients in Northwest Ethiopia: health facility-based cross-sectional study. Trop Med Health. 2021;49. https:\/\/doi.org\/10.1186\/s41182-021-00358-4.","journal-title":"Trop Med Health"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/J.PBIOMOLBIO.2023.03.001","article-title":"Machine learning approaches in diagnosing tuberculosis through biomarkers - A systematic review","volume":"179","author":"Balakrishnan V","year":"2023","unstructured":"Balakrishnan V, Kehrabi Y, Ramanathan G, Paul SA, Tiong CK. Machine learning approaches in diagnosing tuberculosis through biomarkers - A systematic review. Prog Biophys Mol Biol. 2023;179:16\u201325. https:\/\/doi.org\/10.1016\/J.PBIOMOLBIO.2023.03.001.","journal-title":"Prog Biophys Mol Biol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1038\/s41598-019-42557-4","article-title":"Efficient Deep Network Architectures for Fast Chest X-Ray Tuberculosis Screening and Visualization","author":"Pasa F","year":"2019","unstructured":"Pasa F, Golkov V, Pfeiffer F, Cremers D, Pfeiffer D. Efficient Deep Network Architectures for Fast Chest X-Ray Tuberculosis Screening and Visualization. Sci Rep. 2019;9. https:\/\/doi.org\/10.1038\/s41598-019-42557-4.","journal-title":"Sci Rep"},{"key":"ref8","unstructured":"RWANDA BIOMEDICAL CENTER IOHDPAC. Tuberculosis and Other Respiratory communicable Diseases Control in Rwanda. Rwanda: 2015."},{"key":"ref9","unstructured":"RWANDA BIOMEDICAL CENTER I of HDP and C. (IHDPC) T and ORCDD (TB&ORD). TB&ORD ANNUAL REPORT. Rwanda: 2016."},{"key":"ref10","unstructured":"RWANDA BIOMEDICAL CENTER. Tuberculosis and Other Respiratory Communicable Diseases Division. Annual Report 2016\u20132017. Rwanda: 2017."},{"key":"ref11","unstructured":"RWANDA BIOMEDICAL CENTER. Rwanda National Tuberculosis and Other Respiratory Communicable Diseases. Annual Report 2017\u20132018. Rwanda: 2018."},{"key":"ref12","unstructured":"RWANDA BIOMEDICAL CENTER. National Tuberculosis and other respiratory communicable Diseases Program. Annual Report 2018\u20132019. 2019."},{"key":"ref13","unstructured":"RWANDA BIOMEDICAL CENTER. National Tuberculosis and Other Respiratory Communicable Diseases Program. Annual Report 2019\u20132020. Rwanda: 2020."},{"key":"ref14","unstructured":"RWANDA BIOMEDICAL CENTER. National Tuberculosis and Other Respiratory communicable diseases program. Annual Report 2020\u20132021. Rwanda: 2021."},{"key":"ref15","unstructured":"RWANDA BIOMEDICAL CENTER. National Tuberculosis and Other Respiratory Communicable Diseases Program. Annual Report 2021\u20132022. Rwanda: 2022."},{"key":"ref16","unstructured":"RWANDA BIOMEDICAL CENTER. Tuberculosis and Other Respiratory communicable Diseases Division Annual Report 2023\/2024. Rwanda: 2024."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-3354948\/v1","article-title":"Comparison of logistic regression with regularized machine learning methods for the prediction of tuberculosis disease in people living with HIV: cross-sectional hospital-based study in Kisumu County, Kenya","author":"Orwa J","year":"2023","unstructured":"Orwa J, Oduor P, Okelloh D, Gethi D, Agaya J, Okumu A, et al. Comparison of logistic regression with regularized machine learning methods for the prediction of tuberculosis disease in people living with HIV: cross-sectional hospital-based study in Kisumu County, Kenya. Res Sq. 2023. https:\/\/doi.org\/10.21203\/rs.3.rs-3354948\/v1.","journal-title":"Res Sq"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SIEDS65500.2025.11021160","author":"Shichman L","year":"2025","unstructured":"Shichman L, Lee K, Turkistani F, Tashman A, Brown D, Heysell S et al. Predictive Modeling and Machine Learning Insights into Multi-Drug Resistant Tuberculosis Treatment Outcomes. 2025 IEEE Systems and Information Engineering Design Symposium, SIEDS 2025, Institute of Electrical and Electronics Engineers Inc.; 2025, pp. 185\u201390. https:\/\/doi.org\/10.1109\/SIEDS65500.2025.11021160"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000249","article-title":"Machine learning to predict bacteriologic confirmation of Mycobacterium tuberculosis in infants and very young children","author":"Smith JP","unstructured":"Smith JP, Milligan K, McCarthy KD, McHembere W, Okeyo E, Musau SK et al. Machine learning to predict bacteriologic confirmation of Mycobacterium tuberculosis in infants and very young children. PLOS Digital Health 2023;2. https:\/\/doi.org\/10.1371\/journal.pdig.0000249"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgph.0001466","article-title":"A machine learning approach to explore individual risk factors for tuberculosis treatment non-adherence in Mukono district","author":"Gichuhi HW","unstructured":"Gichuhi HW, Magumba M, Kumar M, Mayega RW. A machine learning approach to explore individual risk factors for tuberculosis treatment non-adherence in Mukono district. PLOS Global Public Health 2023;3. https:\/\/doi.org\/10.1371\/journal.pgph.0001466","journal-title":"PLOS Global Public Health"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s12879-024-10282-7","article-title":"Machine learning-based prediction of antibiotic resistance in Mycobacterium tuberculosis clinical isolates from Uganda","author":"Babirye SR","unstructured":"Babirye SR, Nsubuga M, Mboowa G, Batte C, Galiwango R, Kateete DP. Machine learning-based prediction of antibiotic resistance in Mycobacterium tuberculosis clinical isolates from Uganda. BMC Infect Dis 2024;24. https:\/\/doi.org\/10.1186\/s12879-024-10282-7","journal-title":"BMC Infect Dis"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1371\/journal.pone.0180122","article-title":"Evaluation of antibody responses to panels of M. tuberculosis antigens as a screening tool for active tuberculosis in Uganda","author":"Shete PB","year":"2017","unstructured":"Shete PB, Ravindran R, Chang E, Worodria W, Chaisson LH, Andama A, et al. Evaluation of antibody responses to panels of M. tuberculosis antigens as a screening tool for active tuberculosis in Uganda. PLoS ONE. 2017;12. https:\/\/doi.org\/10.1371\/journal.pone.0180122.","journal-title":"PLoS ONE"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1371\/journal.pone.0261246","article-title":"Diabetes mellitus and tuberculosis, a systematic review and meta-analysis with sensitivity analysis for studies comparable for confounders","author":"Foe-Essomba JR","year":"2021","unstructured":"Foe-Essomba JR, Kenmoe S, Tchatchouang S, Ebogo-Belobo JT, Mbaga DS, Kengne-Nd\u00e9 C, et al. Diabetes mellitus and tuberculosis, a systematic review and meta-analysis with sensitivity analysis for studies comparable for confounders. PLoS ONE. 2021;16. https:\/\/doi.org\/10.1371\/journal.pone.0261246.","journal-title":"PLoS ONE"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1177\/20499361221084163","article-title":"Addressing TB-related mortality in adults living with HIV: a review of the challenges and potential solutions","author":"Sullivan A","year":"2022","unstructured":"Sullivan A, Nathavitharana RR. Addressing TB-related mortality in adults living with HIV: a review of the challenges and potential solutions. Ther Adv Infect Dis. 2022;9. https:\/\/doi.org\/10.1177\/20499361221084163.","journal-title":"Ther Adv Infect Dis"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.ijregi.2025.100621","article-title":"Global perspectives on tuberculosis in prisons and incarceration centers - Risk factors, priority needs, challenges for control and the way forward","author":"Nyasulu PS","year":"2025","unstructured":"Nyasulu PS, Hui DS, Mwaba P, Tamuzi JL, Sakala DY, Ntoumi F, et al. Global perspectives on tuberculosis in prisons and incarceration centers - Risk factors, priority needs, challenges for control and the way forward. IJID Reg. 2025;14. https:\/\/doi.org\/10.1016\/j.ijregi.2025.100621.","journal-title":"IJID Reg"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10453356\/v1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10453356\/v1.html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T06:30:57Z","timestamp":1785133857000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchsquare.com\/article\/rs-10453356\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,27]]},"references-count":25,"URL":"https:\/\/doi.org\/10.21203\/rs.3.rs-10453356\/v1","relation":{},"subject":[],"published":{"date-parts":[[2026,7,27]]},"subtype":"preprint"}}