[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122974-en":3,"doc-seo-122974-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122974,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Predictive Analysis of Tuberculosis Treatment Outcomes Using Machine Learning - A Karnataka TB Data Study at a Scale","Tuberculosis (TB) remains a major cause of mortality worldwide, and the study investigates how machine learning can improve prediction of TB treatment outcomes. The work reframes outcome prediction as a binary classification task and derives patient risk scores from NIKSHAY data from India’s national TB control program, using more than 500,000 records. Preprocessing is emphasized as a critical step, with validation performance reaching 98% recall and 0.95 AUC-ROC. Natural language processing is also examined, supported by metrics and ablation studies.","Predictive Analysis of Tuberculosis Treatment Outcomes Using Machine Learning : A Karnataka TB Data Study at a Scale  \narXiv :2403 .08834v1 [ cs .LG] 13 Mar 2024  \nSeshaSai Nath Chinagudaba  \nDepartment of Mathematics and Computer Sciences Sri Sathya Sai Institute of Higher Learning Prasanthi Nilayam, Andhra Pradesh, INDIA [seshasainath.ch@gmail.com](seshasainath.ch@gmail.com)  \nDr. Darshan Gera  \nDepartment of Mathematics and Computer Sciences Sri Sathya Sai Institute of Higher Learning Prasanthi Nilayam, Andhra Pradesh, INDIA [darshangera@sssihl.edu.in](darshangera@sssihl.edu.in)  \nDr. Krishna Kiran Vamsi Dasu[1]  \nDepartment of Mathematics and Computer Sciences Sri Sathya Sai Institute of Higher Learning Prasanthi Nilayam, Andhra Pradesh, INDIA [dkkvamsi@sssihl.edu.in](dkkvamsi@sssihl.edu.in)  \nDr. Uma Shankar S  \nDivisional Head, Epidemiology and Research  \nNational Tuberculosis Institute(NTI) Bengaluru, Karnataka, INDIA [ushankars.2017@gmail.com](ushankars.2017@gmail.com)  \nDr. Kiran K  \nNTEP Medical Consultant  \nWHO  \nBengaluru, Karnataka, INDIA [kiranks24@gmail.com](kiranks24@gmail.com)  \nDr. Anil Singarajpure  \nState TB Officer Bengaluru, Karnataka, INDIA [dadranil@gmail.com](dadranil@gmail.com)  \nDr. Shivayogappa.U  \nMBBS, D.Ortho Joint Director (TB), STO Bengaluru, Karnataka, INDIA [stoka@rntcp.org](stoka@rntcp.org)  \nDr. Somashekar N  \nDirector  \nNational Tuberculosis Institute(NTI) Bengaluru, Karnataka, INDIA [tbsoma@gmail.com](tbsoma@gmail.com)  \nDr. Vineet Kumar Chadda  \nEX-Advisor  \nNational Tuberculosis Institute(NTI) Bengaluru, Karnataka, INDIA [vineet2chadha@gmail.com](vineet2chadha@gmail.com)  \nDr. Sharath B N.  \nProfessor of Community Medicine ESI Medical College Bengaluru, Karnataka, INDIA[sharath.burug@gmail.com](sharath.burug@gmail.com)  \nABSTRACT  \nTuberculosis (TB) remains a global health threat, ranking among the leading causes of mortality worldwide. In this context, machine learning (ML) has emerged as a transformative force, providing innovative solutions to the complexities associated with TB treatment.This study exploreshow machine learning, especially with tabular data, can be used to predict Tuberculosis (TB) treatment outcomes more accurately. It transforms this prediction task into a binary classification problem, generating risk scores from patient data sourced from NIKSHAY, India’s national TB control program, which includes over 500,000 patient records.  \nData preprocessing is a critical component of the study, and the model achieved an recall of 98% and an AUC-ROC score of 0.95 on the validation set, which includes 20,000 patient records.We also explore the use of Natural Language Processing (NLP) for improved model learning. Our results,  \n1Corresponding author  \ncorroborated by various metrics and ablation studies, validate the effectiveness of our approach. The study concludes by discussing the potential ramifications of our research on TB eradication efforts and proposing potential avenues for future work. This study marks a significant stride in the battle against TB, showcasing the potential of machine learning in healthcare.  \nKeywords: Machine Learning(ML), Tuberculosis (TB), Models, Binary Classification, Data Cleaning , Ensemble Learning, Performance Metrics, Evaluation.  \nI. INTRODUCTION  \nTuberculosis (TB), caused by the bacterium Mycobacterium tuberculosis, remains a persistent and significant global health threat, ranking among the leading causes of mortality worldwide. In 2023, India achieved a record in TB notifications with 25,37,235 reported TB cases. This includes cases reported in both the public sector, which totaled 16,99,119, and the private sector, which was 8,38,161 [8] . Despite being preventable and curable,TB continues to have a significant impact. Complex  \ntreatment procedures and the looming challenge of drug resistance pose significant obstacles to effective management.  \nThe severity of TB is determined not only by its prevalence but also by the variabilit","cbCaitdi7ywkdYml","https://ap.wps.com/l/cbCaitdi7ywkdYml","pdf",646958,1,13,"English","en",105,"# Abstract\n# Introduction\n## TB burden and variability of outcomes\n## Role of machine learning in TB management\n# Problem Statement","[{\"question\":\"What does the study aim to predict for TB patients?\",\"answer\":\"It predicts TB treatment outcomes by formulating the task as a binary classification problem and producing risk scores from patient data.\"},{\"question\":\"Which dataset and scale are used in the analysis?\",\"answer\":\"Patient data are sourced from NIKSHAY, India’s national TB control program, including over 500,000 patient records.\"},{\"question\":\"How well did the machine learning model perform on validation?\",\"answer\":\"On the validation set, the study reports 98% recall and an AUC-ROC score of 0.95 using a subset of about 20,000 records.\"}]","Predictive Analysis of Tuberculosis Treatment Outcomes Using Machine Learning - A Karnataka TB Data Study at a Scale | PDF",1785813968,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"predictive-analysis-of-tuberculosis-treatment-outcomes-using-machine-learning-a-karnataka-tb-data-study-at-a-scale","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predictive-analysis-of-tuberculosis-treatment-outcomes-using-machine-learning-a-karnataka-tb-data-study-at-a-scale/122974/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does the study aim to predict for TB patients?","Question",{"text":75,"@type":76},"It predicts TB treatment outcomes by formulating the task as a binary classification problem and producing risk scores from patient data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which dataset and scale are used in the analysis?",{"text":80,"@type":76},"Patient data are sourced from NIKSHAY, India’s national TB control program, including over 500,000 patient records.",{"name":82,"@type":73,"acceptedAnswer":83},"How well did the machine learning model perform on validation?",{"text":84,"@type":76},"On the validation set, the study reports 98% recall and an AUC-ROC score of 0.95 using a subset of about 20,000 records.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]