{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T23:53:48Z","timestamp":1783122828510,"version":"3.54.6"},"reference-count":25,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n<jats:title>Background<\/jats:title>\n<jats:p>Tuberculosis (TB) remains one of the top infectious killers in the world and a prominent fatal disease in developing countries. This study proposes a prototypical solution to early prevention of TB based on its primary symptoms, signs, and risk factors, implemented by means of machine learning (ML) predictive algorithms. Further novelty of the study lies in the uniqueness of patient dataset collected from three top-ranked hospitals of Sindh, Pakistan, <jats:italic>via<\/jats:italic> a self-administered survey patient-records that comprises a set of questions asked by the doctors treating TB patients in real-time. A total of 1,200 survey patient-records were evenly distributed among all three hospitals, viz. ICT Kotri, LUMHS Jamshoro, and Civil Hospital Hyderabad.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>Methods<\/jats:title>\n<jats:p>To develop the required prototypes, the research made use of five distinct benchmark ML algorithms: decision tree (DT), Gaussian naive Bayes (GNB), logistic regression classifier (LRC), adaptive boosting (AdaBoost), and neural network (NN), whose performance was evaluated by considering various performance metrics, <jats:italic>i.e<\/jats:italic>., accuracy, precision, recall, F1 score, and confusion matrix.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>Results<\/jats:title>\n<jats:p>The experimental results, graphically visualized and systematically discoursed, demonstrate that early detection of TB classifiers, including DT, GNB, LRC, AdaBoost, and NN, attained accuracy rates of 92.11%, 89.04%, 90.35%, 93.42%, and 92.98%, respectively. These results indicate effective diagnosis of TB disease by each implemented ML algorithm.<\/jats:p>\n<\/jats:sec>","DOI":"10.7717\/peerj-cs.2397","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T09:01:48Z","timestamp":1729069308000},"page":"e2397","source":"Crossref","is-referenced-by-count":7,"title":["Machine learning based tuberculosis (ML-TB) health predictor model: early TB health disease prediction with ML models for prevention in developing countries"],"prefix":"10.7717","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3915-8660","authenticated-orcid":true,"given":"Priyanka","family":"Karmani","sequence":"first","affiliation":[{"name":"Institute of Mathematics and Computer Science, University of Sindh, Jamshoro, Sindh, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5752-0520","authenticated-orcid":true,"given":"Aftab Ahmed","family":"Chandio","sequence":"additional","affiliation":[{"name":"Institute of Mathematics and Computer Science, University of Sindh, Jamshoro, Sindh, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Imtiaz Ali","family":"Korejo","sequence":"additional","affiliation":[{"name":"Institute of Mathematics and Computer Science, University of Sindh, Jamshoro, Sindh, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oluwarotimi Williams","family":"Samuel","sequence":"additional","affiliation":[{"name":"School of Computing and Data Science Research Center, University of Derby, Derby, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Majed","family":"Aborokbah","sequence":"additional","affiliation":[{"name":"Faculty of Computers and Information Technology, University of Tabuk, Tabuk, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2024,10,16]]},"reference":[{"key":"10.7717\/peerj-cs.2397\/ref-1","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.smhl.2017.04.003","article-title":"Improving tuberculosis diagnostics using deep learning and mobile health technologies among resource-poor communities in Peru","volume":"1","author":"Alcantara","year":"2017","journal-title":"Smart Health"},{"key":"10.7717\/peerj-cs.2397\/ref-2","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1007\/978-3-642-22709-7_34","article-title":"Classification and rule-based approach to diagnose pulmonary tuberculosis","volume-title":"Advances in Computing and Communications: First International Conference, ACC 2011, Kochi, India, July 22\u201324, 2011. Proceedings, Part I","author":"Dongardive","year":"2011"},{"key":"10.7717\/peerj-cs.2397\/ref-3","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1007\/978-0-8176-4542-7_18","article-title":"Neural networks: an application for predicting smear-negative pulmonary tuberculosis","volume-title":"Advances in Statistical Methods for the Health Sciences","author":"dos Santos","year":"2007"},{"issue":"4","key":"10.7717\/peerj-cs.2397\/ref-4","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1378\/chest.116.4.968","article-title":"Predicting active pulmonary tuberculosis using an artificial neural network","volume":"116","author":"El-Solh","year":"1999","journal-title":"Chest Journal"},{"issue":"3","key":"10.7717\/peerj-cs.2397\/ref-5","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/s10916-009-9369-3","article-title":"Tuberculosis disease diagnosis using artificial neural network trained with a genetic algorithm","volume":"35","author":"Elveren","year":"2011","journal-title":"Journal of Medical Systems"},{"issue":"3","key":"10.7717\/peerj-cs.2397\/ref-6","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s10916-008-9241-x","article-title":"Tuberculosis disease diagnosis using artificial neural networks","volume":"34","author":"Er","year":"2010","journal-title":"Journal of Medical Systems"},{"issue":"12","key":"10.7717\/peerj-cs.2397\/ref-7","doi-asserted-by":"publisher","first-page":"7648","DOI":"10.1016\/j.eswa.2010.04.078","article-title":"Chest diseases diagnosis using artificial neural networks","volume":"37","author":"Er","year":"2010","journal-title":"Expert Systems with Applications"},{"issue":"2","key":"10.7717\/peerj-cs.2397\/ref-8","doi-asserted-by":"publisher","first-page":"1862","DOI":"10.1016\/j.eswa.2011.08.064","article-title":"Diagnosis of chest diseases using artificial immune system","volume":"39","author":"Er","year":"2012","journal-title":"Expert Systems with Applications"},{"key":"10.7717\/peerj-cs.2397\/ref-9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-319-50478-0_1","article-title":"Machine learning for health informatics","volume-title":"Machine Learning for Health Informatics. Lecture Notes in Computer Science()","volume":"9605","author":"Holzinger","year":"2016"},{"key":"10.7717\/peerj-cs.2397\/ref-10","doi-asserted-by":"publisher","first-page":"97852W-1","DOI":"10.1117\/12.2216198","article-title":"A novel approach for tuberculosis screening based on deep convolutional neural networks","volume":"9785","author":"Hwang","year":"2016","journal-title":"Medical Imaging"},{"issue":"10","key":"10.7717\/peerj-cs.2397\/ref-11","doi-asserted-by":"publisher","first-page":"e898","DOI":"10.7717\/peerj-cs.898","article-title":"Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study","volume":"8","author":"Islam","year":"2022","journal-title":"PeerJ Computer Science"},{"issue":"6","key":"10.7717\/peerj-cs.2397\/ref-12","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.12785\/ijcds\/0906017","article-title":"Taxonomy on healthcare system based on machine learning","volume":"9","author":"Karmani","year":"2020","journal-title":"International Journal of Computing and Digital Systems"},{"key":"10.7717\/peerj-cs.2397\/ref-13","first-page":"50","article-title":"A review of machine learning for healthcare informatics specifically tuberculosis disease diagnostics","author":"Karmani","year":"2018"},{"key":"10.7717\/peerj-cs.2397\/ref-14","volume-title":"Kumar and clark\u2019s clinical medicine e-book","author":"Kumar","year":"2012"},{"issue":"2","key":"10.7717\/peerj-cs.2397\/ref-15","doi-asserted-by":"publisher","first-page":"162326","DOI":"10.1148\/radiol.2017162326","article-title":"Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks","volume":"284","author":"Lakhani","year":"2017","journal-title":"Radiology"},{"issue":"1","key":"10.7717\/peerj-cs.2397\/ref-16","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/s00330-022-08997-9","article-title":"Machine learning and radiomics for the prediction of multidrug resistance in cavitary pulmonary tuberculosis: a multicentre study","volume":"33","author":"Li","year":"2023","journal-title":"European Radiology"},{"issue":"7639","key":"10.7717\/peerj-cs.2397\/ref-17","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.compbiomed.2017.08.001","article-title":"Pre-trained convolutional neural networks as feature extractors for tuberculosis detection","volume":"89","author":"Lopes","year":"2017","journal-title":"Computers in Biology and Medicine"},{"issue":"1","key":"10.7717\/peerj-cs.2397\/ref-18","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.aci.2015.06.001","article-title":"A Genetic-Neuro-Fuzzy inferential model for diagnosis of tuberculosis","volume":"13","author":"Omisore","year":"2017","journal-title":"Applied Computing and Informatics"},{"key":"10.7717\/peerj-cs.2397\/ref-19","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1007\/978-3-642-30574-0_34","article-title":"Health informatics","volume-title":"Springer Handbook of Bio-\/Neuroinformatics","author":"Parry","year":"2014"},{"issue":"5","key":"10.7717\/peerj-cs.2397\/ref-20","doi-asserted-by":"publisher","first-page":"508","DOI":"10.7150\/ijms.8249","article-title":"Tuberculosis disease diagnosis using artificial immune recognition system","volume":"11","author":"Shahaboddin","year":"2014","journal-title":"International Journal of Medical Sciences"},{"issue":"22","key":"10.7717\/peerj-cs.2397\/ref-21","doi-asserted-by":"publisher","first-page":"15541","DOI":"10.1007\/s00521-021-06177-2","article-title":"A voting-based ensemble deep learning method focusing on image augmentation and preprocessing variations for tuberculosis detection","volume":"33","author":"Tasci","year":"2021","journal-title":"Neural Computing and Applications"},{"key":"10.7717\/peerj-cs.2397\/ref-22","article-title":"Tuberculosis profile: Afghanistan","author":"The World Health Organization","year":"2024a"},{"key":"10.7717\/peerj-cs.2397\/ref-23","article-title":"World health organization\u2014Eastern Mediterranean region","author":"The World Health Organization","year":"2024b"},{"issue":"9","key":"10.7717\/peerj-cs.2397\/ref-24","first-page":"4208","article-title":"A new method of automatic recognition for tuberculosis disease diagnosis using support vector machines","volume":"28","author":"Yahiaoui","year":"2017","journal-title":"Biomedical Research"},{"issue":"1","key":"10.7717\/peerj-cs.2397\/ref-25","doi-asserted-by":"publisher","first-page":"e1280","DOI":"10.7717\/peerj-cs.1280","article-title":"Classification and prediction of spinal disease based on the SMOTE-RFE-XGBoost model","volume":"9","author":"Zhang","year":"2023","journal-title":"PeerJ Computer Science"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-2397.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2397.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2397.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2397.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T09:01:57Z","timestamp":1729069317000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-2397"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":25,"alternative-id":["10.7717\/peerj-cs.2397"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.2397","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]},"article-number":"e2397"}}