{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T20:26:13Z","timestamp":1792009573348,"version":"4.4.0"},"reference-count":43,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Despite advancements in detection and treatment, tuberculosis (TB), an infectious illness caused by the Mycobacterium TB bacteria, continues to pose a serious threat to world health. The TB diagnosis phase includes a patient\u2019s medical history, physical examination, chest X-rays, and laboratory procedures, such as molecular testing and sputum culture. In artificial intelligence (AI), machine learning (ML) is an advanced study of statistical algorithms that can learn from historical data and generalize the results to unseen data. There are not many studies done on the ML algorithm that enables the prediction of treatment success for patients with pulmonary TB (PTB). The objective of this study is to identify an effective and predictive ML algorithm to evaluate the detection of treatment success in PTB patients and to compare the predictive performance of the ML models. In this retrospective study, a total of 1236 PTB patients who were given treatment under a randomized controlled clinical trial at the ICMR-National Institute for Research in Tuberculosis, Chennai, India were considered for data analysis. The multiple ML models were developed and tested to identify the best algorithm to predict the sputum culture conversion of TB patients during the treatment period. In this study, decision tree (DT), random forest (RF), support vector machine (SVM) and na\u00efve bayes (NB) models were validated with high performance by achieving an area under the curve (AUC) of receiver operating characteristic (ROC) greater than 80%. The salient finding of the study is that the DT model was produced as a better algorithm with the highest accuracy (92.72%), an AUC (0.909), precision (95.90%), recall (95.60%) and F1-score (95.75%) among the ML models. This methodology may be used to study the precise ML model classification for predicting the treatment success of TB patients during the treatment period.<\/jats:p>","DOI":"10.1371\/journal.pone.0309151","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T17:27:30Z","timestamp":1729099650000},"page":"e0309151","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":27,"title":["Machine learning algorithms to predict treatment success for patients with pulmonary tuberculosis"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6650-3028","authenticated-orcid":true,"given":"Shaik","family":"Ahamed Fayaz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lakshmanan","family":"Babu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Loganathan","family":"Paridayal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahalingam","family":"Vasantha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Palaniyandi","family":"Paramasivam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1309-0439","authenticated-orcid":true,"given":"Karuppasamy","family":"Sundarakumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1762-6424","authenticated-orcid":true,"given":"Chinnaiyan","family":"Ponnuraja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,10,16]]},"reference":[{"key":"pone.0309151.ref001","unstructured":"Global tuberculosis report 2021. Geneva: World Health Organization; 2021. Licence: CC BY-NC-SA 3.0 IGO."},{"key":"pone.0309151.ref002","unstructured":"Global tuberculosis report 2023. Geneva: World Health Organization; 2023. Licence: CC BY-NC-SA 3.0 IGO."},{"key":"pone.0309151.ref003","doi-asserted-by":"crossref","unstructured":"Tackling poverty in tuberculosis control. (2005). Lancet (London, England), 366(9503), 2063.","DOI":"10.1016\/S0140-6736(05)67862-2"},{"key":"pone.0309151.ref004","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.tube.2017.01.005","article-title":"Machine learning and docking models for Mycobacterium tuberculosis topoisomerase I","volume":"103","author":"S Ekins","year":"2017","journal-title":"Tuberculosis"},{"issue":"5","key":"pone.0309151.ref005","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1016\/j.beth.2020.05.002","article-title":"Supervised machine learning: a brief primer","volume":"51","author":"T Jiang","year":"2020","journal-title":"Behavior Therapy"},{"key":"pone.0309151.ref006","unstructured":"Elkan C. Predictive analytics and data mining. San Diego: University of California; 2013 May 28."},{"issue":"1","key":"pone.0309151.ref007","doi-asserted-by":"crossref","first-page":"e011580","DOI":"10.1136\/bmjopen-2016-011580","article-title":"Predicting patient \u2018cost blooms\u2019 in Denmark: a longitudinal population-based study","volume":"7","author":"S Tamang","year":"2017","journal-title":"BMJ open"},{"issue":"6","key":"pone.0309151.ref008","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1016\/j.medj.2021.04.006","article-title":"Machine learning in clinical decision making","volume":"2","author":"L Adlung","year":"2021","journal-title":"Med"},{"issue":"1","key":"pone.0309151.ref009","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.gltp.2021.01.004","article-title":"Machine learning and deep learning applications-a vision","volume":"2","author":"N Sharma","year":"2021","journal-title":"Global Transitions Proceedings"},{"issue":"2","key":"pone.0309151.ref010","first-page":"66","article-title":"Deep machine learning and neural networks: An overview","volume":"6","author":"C Mishra","year":"2017","journal-title":"IAES international journal of artificial intelligence"},{"issue":"1","key":"pone.0309151.ref011","first-page":"1","article-title":"Comparative analysis of linear, non-linear and ensemble machine learning algorithms for credit worthiness of consumers","volume":"1","author":"DO Oyewola","year":"2019","journal-title":"Computational Intelligence & Wireless Sensor Networks"},{"issue":"3","key":"pone.0309151.ref012","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1007\/s42979-021-00592-x","article-title":"Machine learning: Algorithms, real-world applications and research directions","volume":"2","author":"IH Sarker","year":"2021","journal-title":"SN computer science"},{"issue":"2","key":"pone.0309151.ref013","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1080\/17538157.2018.1433676","article-title":"Predicting treatment outcome of drug-susceptible tuberculosis patients using machine-learning models","volume":"44","author":"OA Hussain","year":"2019","journal-title":"Informatics for Health and Social Care"},{"issue":"7","key":"pone.0309151.ref014","doi-asserted-by":"crossref","first-page":"e0001466","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","volume":"3","author":"HW Gichuhi","year":"2023","journal-title":"PLOS Global Public Health"},{"issue":"03","key":"pone.0309151.ref015","doi-asserted-by":"crossref","first-page":"184","DOI":"10.4236\/jilsa.2013.53020","article-title":"Evaluation and comparison of different machine learning methods to predict outcome of tuberculosis treatment course","volume":"5","author":"SR Kalhori","year":"2013","journal-title":"Journal of Intelligent Learning Systems and Applications"},{"issue":"7","key":"pone.0309151.ref016","first-page":"89","article-title":"Effective classification algorithms to predict the accuracy of tuberculosis-A machine learning approach","volume":"9","author":"T Asha","year":"2011","journal-title":"International Journal of Computer Science and Information Security"},{"issue":"1","key":"pone.0309151.ref017","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12911-019-1004-8","article-title":"Comparing different supervised machine learning algorithms for disease prediction","volume":"19","author":"S Uddin","year":"2019","journal-title":"BMC medical informatics and decision making"},{"issue":"3","key":"pone.0309151.ref018","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1148\/radiol.2015151516","article-title":"STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies","volume":"277","author":"PM Bossuyt","year":"2015","journal-title":"Radiology"},{"issue":"12","key":"pone.0309151.ref019","doi-asserted-by":"crossref","first-page":"e323","DOI":"10.2196\/jmir.5870","article-title":"Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view","volume":"18","author":"W Luo","year":"2016","journal-title":"Journal of medical Internet research"},{"key":"pone.0309151.ref020","doi-asserted-by":"crossref","unstructured":"Tuberculosis Research Centre (Indian Council of Medical Research), Chennai, India. Split-drug regimens for the treatment of patients with sputum smear\u2010positive pulmonary tuberculosis\u2013a unique approach. Tropical Medicine & International Health. 2004 May;9(5):551\u20138.","DOI":"10.1111\/j.1365-3156.2004.01229.x"},{"key":"pone.0309151.ref021","first-page":"23","article-title":"Using Decision Tree for Diagnosing Heart Disease Patients","volume":"11","author":"M Shouman","year":"2011","journal-title":"AusDM"},{"key":"pone.0309151.ref022","first-page":"117693510600200030","article-title":"Applications of machine learning in cancer prediction and prognosis","volume":"2","author":"JA Cruz","year":"2006","journal-title":"Cancer informatics"},{"key":"pone.0309151.ref023","first-page":"60","article-title":"Controlling the sensitivity of support vector machines","volume":"55","author":"K Veropoulos","year":"1999","journal-title":"InProceedings of the international joint conference on AI"},{"key":"pone.0309151.ref024","first-page":"3540","article-title":"Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification","volume":"79","author":"I Nitze","year":"2012","journal-title":"Proceedings of the 4th GEOBIA, Rio de Janeiro, Brazil"},{"key":"pone.0309151.ref025","article-title":"Comparison of the C4. 5 and a Na\u00efve Bayes classifier for the prediction of lung cancer survivability","author":"G Dimitoglou","year":"2012","journal-title":"arXiv preprint arXiv"},{"key":"pone.0309151.ref026","first-page":"233","author":"J Davis","year":"2006","journal-title":"The relationship between Precision-Recall and ROC curves. InProceedings of the 23rd international conference on Machine learning"},{"key":"pone.0309151.ref027","doi-asserted-by":"crossref","unstructured":"Forbes C, Evans M, Hastings N, Peacock B. Statistical Distributions, John Wiley&Sons. Inc., Publication, fourth Edition, New Jersey. 2011.","DOI":"10.1002\/9780470627242"},{"key":"pone.0309151.ref028","first-page":"345","article-title":"A probabilistic interpretation of precision, recall and F-score, with implication for evaluation","author":"C Goutte","year":"2005","journal-title":"InEuropean conference on information retrieval"},{"key":"pone.0309151.ref029","author":"G James","year":"2013"},{"key":"pone.0309151.ref030","article-title":"Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation","author":"DM Powers","year":"2020","journal-title":"arXiv preprint arXiv"},{"issue":"11","key":"pone.0309151.ref031","first-page":"223","article-title":"A survey of machine learning algorithms in health care","volume":"8","author":"ES Bakyarani","year":"2019","journal-title":"Int J Sci Technol Res"},{"key":"pone.0309151.ref032","doi-asserted-by":"crossref","first-page":"100247","DOI":"10.1016\/j.health.2023.100247","article-title":"The stratified K-folds cross-validation and class-balancing methods with high-performance ensemble classifiers for breast cancer classification","volume":"4","author":"TR Mahesh","year":"2023","journal-title":"Healthcare Analytics"},{"key":"pone.0309151.ref033","unstructured":"R Core Team (2023). _R: A Language and Environment for Statistical Computing_. R Foundation for Statistical Computing, Vienna, Austria."},{"key":"pone.0309151.ref034","author":"SD Ahuja","journal-title":"Multidrug resistant pulmonary tuberculosis treatment regimens and patient outcomes: an individual patient data meta-analysis of 9,153 patients"},{"issue":"1","key":"pone.0309151.ref035","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1086\/524017","article-title":"Extensively drug\u2010resistant tuberculosis in South Korea: risk factors and treatment outcomes among patients at a tertiary referral hospital","volume":"46","author":"CY Jeon","year":"2008","journal-title":"Clinical infectious diseases"},{"issue":"4","key":"pone.0309151.ref036","doi-asserted-by":"crossref","first-page":"e93206","DOI":"10.1371\/journal.pone.0093206","article-title":"Predictors of two months culture conversion in multidrug-resistant tuberculosis: findings from a retrospective cohort study","volume":"9","author":"A Basit","year":"2014","journal-title":"PloS one"},{"issue":"10","key":"pone.0309151.ref037","doi-asserted-by":"crossref","first-page":"e142","DOI":"10.1093\/cid\/ciu550","article-title":"Sputum culture conversion with moxifloxacin-containing regimens in the treatment of patients with newly diagnosed sputum-positive pulmonary tuberculosis in South India","volume":"59","author":"BV Velayutham","year":"2014","journal-title":"Clinical Infectious Diseases"},{"issue":"68","key":"pone.0309151.ref038","doi-asserted-by":"crossref","first-page":"104","DOI":"10.4114\/intartif.vol24iss68pp104-122","article-title":"An Accurate Integrated System to detect Pulmonary and Extra Pulmonary Tuberculosis using Machine Learning Algorithms","volume":"24","author":"R Kaur","year":"2021","journal-title":"Inteligencia Artificial"},{"issue":"5","key":"pone.0309151.ref039","doi-asserted-by":"crossref","first-page":"e0000249","DOI":"10.1371\/journal.pdig.0000249","article-title":"Machine learning to predict bacteriologic confirmation of Mycobacterium tuberculosis in infants and very young children","volume":"2","author":"JP Smith","year":"2023","journal-title":"PLOS Digital Health"},{"issue":"2","key":"pone.0309151.ref040","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1016\/j.jksuci.2023.01.014","article-title":"A comprehensive review on ensemble deep learning: Opportunities and challenges","volume":"35","author":"A Mohammed","year":"2023","journal-title":"Journal of King Saud University-Computer and Information Sciences"},{"key":"pone.0309151.ref041","doi-asserted-by":"crossref","first-page":"1003347","DOI":"10.3389\/fimmu.2022.1003347","article-title":"A deep belief network-based clinical decision system for patients with osteosarcoma","volume":"13","author":"W Li","year":"2022","journal-title":"Frontiers in Immunology"},{"key":"pone.0309151.ref042","doi-asserted-by":"crossref","first-page":"832108","DOI":"10.3389\/fmed.2022.832108","article-title":"A machine learning-based predictive model for predicting lymph node metastasis in patients with ewing\u2019s sarcoma","volume":"9","author":"W Li","year":"2022","journal-title":"Frontiers in Medicine"},{"issue":"17","key":"pone.0309151.ref043","doi-asserted-by":"crossref","first-page":"2634","DOI":"10.3390\/electronics11172634","article-title":"Evolution of machine learning in tuberculosis diagnosis: a review of deep learning-based medical applications","volume":"11","author":"M Singh","year":"2022","journal-title":"Electronics"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0309151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T17:27:46Z","timestamp":1729099666000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0309151"}},"subtitle":[],"editor":[{"given":"Selvakumar","family":"Subbian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":43,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0309151","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]}}}