[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-439092-105":59,"doc-detail-439092-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","adaptive-modelling-approach-for-predicting-causes-of-death-insights-from-verbal-autopsy-data-in-tanzania","Adaptive modelling approach for predicting causes of death: insights from verbal autopsy data in Tanzania","","A study develops and tests an adaptive Bayesian networks machine learning model to predict out-of-hospital causes of death using verbal autopsy (VA) data in Tanzania. Using the 2016 WHO questionnaire, Iringa data were augmented via SMOTE to increase nominal-feature coverage and reduce bias in cause-of-death class assignment. Model development was guided by a decision-flow integrating essential factors for accurate prediction.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/adaptive-modelling-approach-for-predicting-causes-of-death-insights-from-verbal-autopsy-data-in-tanzania/439092/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/adaptive-modelling-approach-for-predicting-causes-of-death-insights-from-verbal-autopsy-data-in-tanzania/439092.png","ImageObject",300,407,{"name":92,"@type":93},"Margaret","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-06","2026-09-29",true,{"@type":102,"interactionType":103,"userInteractionCount":29},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What verbal autopsy–based data source and questionnaire were used for the study?","Question",{"text":112,"@type":113},"The 2016 WHO questionnaire was used to collect VA data from Iringa, Tanzania.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How did the study address class imbalance and improve dataset quality?",{"text":117,"@type":113},"Data augmentation was performed using SMOTE for nominal features to increase dataset size and reduce bias in cause-of-death classification.",{"name":119,"@type":110,"acceptedAnswer":120},"How was the proposed model evaluated and how did it compare with other models?",{"text":121,"@type":113},"Performance was measured using accuracy, sensitivity, specificity, and F1 score, and it was compared with Support Vector Machine and Naïve Bayesian models, achieving an average accuracy of 97% and strong F1 and sensitivity results.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},439092,1791516140,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":29,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":44,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":4},137451207643,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","International Health 2026; 18: 125–133  \n[https://doi.org/10.1093/inthealth/ihaf123](https://doi.org/10.1093/inthealth/ihaf123)  \nAdvance Access publication 17 November 2025  \nAdaptive modelling approach for predicting causes of death: insights  \nfrom verbal autopsy data in Tanzania  \nMahadia Tunga ∗, James Chambua and Juma Lungo  \nDepartment of Computer Science and Engineering, College of Information and Communication Technologies, University ofDar es  \nSalaam, P.O. Box 33335 Dar es Salaam, Tanzania  \n∗ Corresponding author: Tel: +255752190018; [E-mail:](E-mail: mahadiatunga@udsm.ac.tz)[ mahadiatunga@udsm.ac.tz](E-mail: mahadiatunga@udsm.ac.tz)  \nReceived 9 January 2025; revised 12 May 2025; accepted 3 October 2025  \nBackground: The World Health Organization (WHO) has approved the use of a verbal autopsy (VA), a surveybased approach to generate out-of-hospital causes of death (CoDs) . Through this study, an adaptive Bayesian networks machine learning model was developed and tested. The model is scalable and adaptable for predicting new causes as the dataset expands.  \nMethods: The 2016 WHO questionnaire was used to collect data from Iringa, Tanzania, and data augmentation was performed using the Synthetic Minority Oversampling Technique for nominal features to increase the datasetsize and reduce bias in the CoD classification. The model development was guided by a CoD decision flow that integrates essential factors and steps for accurate CoD prediction. To our knowledge, no previous study has provided this operational guide for VA cause of death prediction.  \nResults: The model was evaluated using accuracy, sensitivity, specificity and F1 score metrics and compared with Support Vector Machine and Naïve Bayesian models. Results indicated an average accuracy of 97%, specificity of 97%, sensitivity of 94% and F1 score of 94%, which are superior compared with Naïve Bayesian and Support Vector Machine models.  \nConclusions: The reported performance of the developed model demonstrates the potential for this model to enhance VA-based CoD data by integrating a machine learning approach with physician expertise. The results highlight the effectiveness of combining Bayesian networks with physician Symptom Cause Information as a valuable tool in advancing the performance of CoD predictions.  \nKeywords: Bayesian model, cause of death prediction, VA machine learning model, VA model, verbal autopsy, WHO VA questionnaire.  \nIntroduction  \nAccording to the World Health Organisation (WHO),1 globally only 50% of deaths are certified with known causes of death (CoDs) . However, 50% is insufficient to reflect society’s morbidity conditions. To improve the CoD statistics, the WHO has devised a survey-based verbal autopsy (VA) method.2 As a WHO tool, the VA is already being administered in >45 low-and middle-income countries (LMICs) . Data generated through VAs are already regarded as useful in determining CoD and helps in making datadriven, informed policy and healthcare interventions.3 In practice, the VA is administered to relatives or those aware of the recent death to describe the deceased’s medical history.4  \nSince theVA is being administered in different countries, a gold standard is required to guide its use and ensure accurate de-  \ntermination of CoD.5 A gold standard is a database comprising multifarious deaths whose causes have been certified by medical professionals.6 Even though this gold standard database does exist, it is inaccessible to LMICs, where most deaths occur without medical care. In most cases, only one-third of deaths in LMICshave a medically certified CoD, and only half of those have a CoD record that can be used for health policy development and planning.3 , 6 These challenges have motivated CoD prediction automation through computer-coded verbal autopsy (CCVA) .2 , 8–11  \nThe CCVA approaches use statistical and machine learning (ML) algorithms to determine CoD and thus do not require extensive use of gold standards or medical","cbCaikLwI2UAHiV2","https://ap.wps.com/l/cbCaikLwI2UAHiV2","pdf",743531,"English","# Background\n# Methods\n# Results\n# Conclusions\n# Introduction\n# VA CoD computation algorithms\n## InterVA model\n## InSilicoVA algorithm","[{\"question\":\"What verbal autopsy–based data source and questionnaire were used for the study?\",\"answer\":\"The 2016 WHO questionnaire was used to collect VA data from Iringa, Tanzania.\"},{\"question\":\"How did the study address class imbalance and improve dataset quality?\",\"answer\":\"Data augmentation was performed using SMOTE for nominal features to increase dataset size and reduce bias in cause-of-death classification.\"},{\"question\":\"How was the proposed model evaluated and how did it compare with other models?\",\"answer\":\"Performance was measured using accuracy, sensitivity, specificity, and F1 score, and it was compared with Support Vector Machine and Naïve Bayesian models, achieving an average accuracy of 97% and strong F1 and sensitivity results.\"}]","Adaptive modelling approach for predicting causes of death: insights from verbal autopsy data in Tanzania | PDF",1790687434,23]