[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124505-en":3,"doc-seo-124505-105":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},124505,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Explainable Transformer and Machine Learning Models in Predicting Tuberculosis Treatment Outcomes - A Systematic Review","Tuberculosis remains a major global health challenge, and accurately predicting treatment outcomes in real-world settings is difficult. This study conducts a systematic literature review of explainable transformer and machine learning models for TB prognosis. Using PRISMA-guided searches across ACM, IEEE Xplore, PubMed, and ScienceDirect, it identifies 17 peer-reviewed studies (2020–2025). Results compare predictive performance, explainability methods, and deployment considerations, highlighting generally stronger performance of transformer/deep learning on longitudinal and multimodal data, while tabular models stay competitive. Key adoption barriers include limited interpretability, fairness evaluation gaps, computational overhead, data scarcity, and weak fit to clinical workflows, leading to a conceptual ETAMTB adoption framework.","Explainable Transformer and Machine Learning Models in Predicting Tuberculosis Treatment Outcomes. A Systematic Review  \nShumirai S Sibanda 1*, Belinda Ndlovu 2*  \n* Informatics and Analytics Department, National University of Science and Technology, Bulawayo, Zimbabwe  \n[n02218035d@students.nust.ac.zw](n02218035d@students.nust.ac.zw1)[1](n02218035d@students.nust.ac.zw1), [belinda.ndlovu@nust.ac.zw](belinda.ndlovu@nust.ac.zw2)[2](belinda.ndlovu@nust.ac.zw2)  \nArticle history:  \nReceived 2025-11-24 Revised 2026-01-01 Accepted 2026-01-20  \nKeywords:  \nTuberculosis (TB), Treatment Outcomes, Transformer Models, Explainable AI, Machine Learning.  \nTuberculosis (TB) remains a major health challenge, and predicting treatment outcomes continues to be difficult in real-world settings. Recent advances in Artificial Intelligence (AI), particularly transformer-based models, have shown promise in modelling longitudinal, multimodal, and heterogeneous TB data. However, their clinical adoption is constrained by limited interpretability, fairness concerns, and deployment challenges. This study presents a systematic literature review of explainable transformer and machine learning models used for TB prognosis. Following PRISMA guidelines, searches across ACM, IEEE Xplore, PubMed, and ScienceDirect identified 17 peer-reviewed studies published between 2020 and 2025 that met the inclusion criteria. The review synthesises evidence on predictive performance, explainability techniques, and deployment considerations. Findings indicate that transformer-based and deep learning models generally outperform conventional machine learning approaches on longitudinal and multimodal data. In contrast, traditional models remain competitive for tabular clinical datasets. Explainability approaches are dominated by feature importance methods and SHAP, with limited use of intrinsic transformer interpretability mechanisms. Persistent challenges include data scarcity, limited generalisability, computational overhead, insufficient evaluation of fairness, and weak alignment with real-world TB care workflows. Building on these findings, the study proposes the Explainable Transformer Adoption Model for TB Prognosis (ETAMTB) as a conceptual clinical adoption framework integrating multimodal transformers, explainability layers, clinician-facing interfaces, and deployment enablers. Overall, the review concludes that effective AI adoption in TB care requires balancing predictive performance, interpretability, and equity, and that explainable transformers should currently be viewed as promising but largely experimental tools rather than deployment-ready solutions.  \nThis is an open access article under the CC–BY-SA license.  \nArticle Info ABSTRACT  \nI. INTRODUCTION  \nAs the leading infectious disease killer after COVID-19, tuberculosis (TB) continues to be a serious global health concern, accounting for more deaths than HIV/AIDS[1][2] . TB, which is caused by Mycobacterium tuberculosis, mainly affects the lungs but can also affect other organs like the brain or spine. [1], [3] . When an infected individual coughs or sneezes, airborne particles are released into the air, causing transmission[4] .TB can also be latent and asymptomatic,  \nwhile other cases can be active, presenting symptoms such as fever, night sweats, weakness, and loss of appetite[5] .  \nDrug-resistant strains (DR-TB) are also a big concern when dealing with TB because they have been linked to more complex diagnoses, lengthy and toxic therapies, and increased death rates[1], [9] . Moreover, TB is one of the contributing factors to deaths associated with HIV infections worldwide because comorbid conditions such as HIV can greatly enhance the progression of TB [7],[11] .  \nOne of the most crucial factors to measure the effectiveness of therapeutic efficacy in this case is to make a correct prediction about treatment outcomes, which can merely be classified into success or failure. [8], [12] . The emergence of da","cbCaimCFiyf9EKEd","https://ap.wps.com/l/cbCaimCFiyf9EKEd","pdf",780816,1,15,"English","en",105,"# Article history\n# Abstract\n## Introduction\n## Background and motivation\n## AI and machine learning approaches\n## Transformer models for TB prediction\n## Research gap and review approach","[{\"question\":\"What problem does the review address about tuberculosis care?\",\"answer\":\"It addresses the difficulty of predicting tuberculosis treatment outcomes in real-world settings, where prognosis modeling remains challenging.\"},{\"question\":\"How many studies were included, and what is the review period?\",\"answer\":\"The review identifies 17 peer-reviewed studies published between 2020 and 2025 using PRISMA-guided searches.\"},{\"question\":\"What explainability and adoption challenges limit clinical deployment?\",\"answer\":\"Explainability is dominated by feature-importance and SHAP methods, with limited intrinsic transformer interpretability, and adoption is constrained by data scarcity, limited generalisability, computational overhead, fairness evaluation gaps, and weak alignment with clinical workflows.\"}]","Explainable Transformer and Machine Learning Models in Predicting Tuberculosis Treatment Outcomes - A Systematic Review | PDF",1785822814,38,{"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},"explainable-transformer-and-machine-learning-models-in-predicting-tuberculosis-treatment-outcomes-a-systematic-review","",{"@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/explainable-transformer-and-machine-learning-models-in-predicting-tuberculosis-treatment-outcomes-a-systematic-review/124505/",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 problem does the review address about tuberculosis care?","Question",{"text":75,"@type":76},"It addresses the difficulty of predicting tuberculosis treatment outcomes in real-world settings, where prognosis modeling remains challenging.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How many studies were included, and what is the review period?",{"text":80,"@type":76},"The review identifies 17 peer-reviewed studies published between 2020 and 2025 using PRISMA-guided searches.",{"name":82,"@type":73,"acceptedAnswer":83},"What explainability and adoption challenges limit clinical deployment?",{"text":84,"@type":76},"Explainability is dominated by feature-importance and SHAP methods, with limited intrinsic transformer interpretability, and adoption is constrained by data scarcity, limited generalisability, computational overhead, fairness evaluation gaps, and weak alignment with clinical workflows.","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"]