[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120205-en":3,"doc-seo-120205-105":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":20,"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},120205,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Towards Explainable Machine Learning for Prediction of Disease Progression - Research article abstract","This research addresses interpretability challenges in machine learning for predicting disease progression, where predictive systems often function as opaque “black boxes.” It reviews current approaches to disease progression modeling and develops an end-to-end pipeline covering data preparation, prediction, and post-hoc explanation. A deep recurrent neural network produces predictions, followed by LIME-based explanations for each case. The pipeline is evaluated through case studies on diabetes and Parkinson’s disease, and three data imputation methods are compared for predictive performance. No statistically significant performance differences are found across imputation techniques. The results support transparent, more interpretable disease progression prediction and outline directions for future work.","Applied Artificial Intelligence  \nAn International Journal  \nISSN: (Print) (Online) Journal [homepage: ](homepage: www.tandfonline.com/journals/uaai20)[www.tandfonline.com/journals/uaai20](homepage: www.tandfonline.com/journals/uaai20)  \nTowards Explainable Machine Learning for Prediction of Disease Progression  \nStijn Berendse, Johannes Krabbe, Jonas Klaus & Faizan Ahmed  \nTo cite this article: Stijn Berendse, Johannes Krabbe, Jonas Klaus & Faizan Ahmed (2024) Towards Explainable Machine Learning for Prediction of Disease Progression, Applied Artificia l Intelligence, 38:1, 2423510, DOI: 10.1080/08839514.2024.2423510  \nTo link to this article: [https://doi.org/10.1080/08839514.2024.2423510](https://doi.org/10.1080/08839514.2024.2423510)  \n© 2024 The Author(s) . Published with license by Taylor & Francis Group, LLC.  \n\n|  View supplementary material  |\n| --- |\n|  Published online: 07 Nov 2024. |\n|  Submit your article to this journal  |\n|  Article views: 431 |\n|  View related articles  |\n|  View Crossmark data |\n\nFull Terms & Conditions of access and use can be found at [https://www.tandfonline.com/action/journalInformation?journalCode=uaai20](https://www.tandfonline.com/action/journalInformation?journalCode=uaai20)  \nAPPLIED ARTIFICIAL INTELLIGENCE  \n2024, VOL. 38, NO. 1, e2423510 (44 pages) [https://doi.org/10.1080/08839514.2024.2423510](https://doi.org/10.1080/08839514.2024.2423510)  \nTowards Explainable Machine Learning for Prediction of Disease Progression  \nStijn Berendsea, Johannes Krabbeb, Jonas Klausc, and Faizan Ahmed a  \naDepartment of Computer Science, University of Twente, Enschede, The Netherlands; bUnilabs/Medisch Spectrum Twente Enschede, The Netherlands; cAsklepios Klinik Barmbek Hamburg, Germany  \nABSTRACT  \nThis research focuses on addressing the challenges surrounding interpretability of machine learning techniques in the field of prediction of disease progression. This paper summarizes the state-of-the-art in machine learning for disease progression modeling and challenges related to this context. Based on this state-of-the-art, we design and develop a pipeline consisting of data preparation, prediction, and explanation. Predictions are made using a deep recurrent neural network-based model which is followed by an integration of the LIME framework to provide explanations for each prediction. We demonstrate our pipeline by applying it to two diverse case studies on diabetes and Parkinson’s disease. Besides this, we compare the influence of three data imputation methods on predictive performance. Results of the comparison show that there is no statistically significant difference in performance due to different data imputation techniques. Furthermore, we provide a number of concrete recommendations and directions for future research, such as improving input flexibility of the prediction model and improving the visualization of generated explanations. Based on the results of this research, we conclude that the proposed pipeline achieves the goal of integrating a state-of-the-art prediction model and the LIME framework to make prediction of disease progression more transparent and interpretable.  \nARTICLE HISTORY  \nReceived 17 June 2024 Revised 12 September 2024 Accepted 19 October 2024  \nIntroduction  \nAs machine learning and artificial intelligence (AI) have become widespread in their use Jordan and Mitchell (2015) and are reaching ever more sensitive domains such as healthcare, the need for responsible AI has arisen Vayena, Blasimme, and Glenn Cohen (2018); Hunter and Holmes (2023) . AI systems work like a “black box:” they receive input data, train a model, and then use that model to make predictions.  \nHowever, this nontransparent approach has major drawbacks, including limited or missing insight into the reasoning behind the prediction which  \nCONTACT Faizan Ahmed,  [faizan.ahmed@utwente.nl](faizan.ahmed@utwente.nl)  Department of Computer Science, University of Twente Enschede, Hallenweg 19, Enschede 7522","cbCail6KkyayilUm","https://ap.wps.com/l/cbCail6KkyayilUm","pdf",8540781,1,45,"English","en",105,"# ABSTRACT\n# Introduction\n## Interpretability challenges in healthcare AI\n## Disease progression modeling background\n## Need for transparency and explainability","[{\"question\":\"What problem does the paper target in disease progression prediction?\",\"answer\":\"It targets the lack of interpretability in machine learning models used to predict disease progression, where the reasoning behind predictions is often unclear for clinicians.\"},{\"question\":\"How does the proposed pipeline generate predictions and explanations?\",\"answer\":\"Predictions are produced using a deep recurrent neural network, and each prediction is followed by explanations using the LIME framework.\"},{\"question\":\"What did the authors find when comparing different data imputation methods?\",\"answer\":\"The comparison across three imputation methods shows no statistically significant difference in predictive performance.\"}]","Towards Explainable Machine Learning for Prediction of Disease Progression - Research article abstract | PDF",1785728716,113,{"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},"towards-explainable-machine-learning-for-prediction-of-disease-progression-research-article-abstract","",{"@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/towards-explainable-machine-learning-for-prediction-of-disease-progression-research-article-abstract/120205/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper target in disease progression prediction?","Question",{"text":75,"@type":76},"It targets the lack of interpretability in machine learning models used to predict disease progression, where the reasoning behind predictions is often unclear for clinicians.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed pipeline generate predictions and explanations?",{"text":80,"@type":76},"Predictions are produced using a deep recurrent neural network, and each prediction is followed by explanations using the LIME framework.",{"name":82,"@type":73,"acceptedAnswer":83},"What did the authors find when comparing different data imputation methods?",{"text":84,"@type":76},"The comparison across three imputation methods shows no statistically significant difference in predictive performance.","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"]