[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121074-en":3,"doc-seo-121074-105":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},121074,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Medical informed machine learning - A scoping review and future research directions","Combining domain knowledge (DK) with machine learning addresses explainability limits, data scarcity, and robustness issues in medical AI. The review maps the status of informed machine learning (IML) in medicine using an existing taxonomy, identifying 177 papers and analyzing the DK sources, DK structure, the ML models used, and the motives driving IML adoption. Findings highlight the major influence of expert knowledge and image data. The study summarizes recent approaches and proposes five directions for future research, supporting researchers in selecting and extending existing solutions.","Medical informed machine learning: A scoping review and future research directions  \nFlorian Leiser, Sascha Rank, Manuel Schmidt-Kraepelin, Scott Thiebes, Ali Sunyaev  \nDepartment of Economics and Management, Karlsruhe Institute of Technology, Karlsruhe, Germany  \n*  \nA R T I C L E I N F O  \nKeywords:  \nInformed machine learning Scoping literature review Medical informatics Domain knowledge Machine learning  \nA B S T R A C T  \nCombining domain knowledge (DK) and machine learning is a recent research stream to overcome multiple issues like limited explainability, lack of data, and insufficient robustness. Most approaches applying informed machine learning (IML), however, are customized to solve one specific problem. This study analyzes the status of IML in medicine by conducting a scoping literature review based on an existing taxonomy. We identified 177 papers and analyzed them regarding the used DK, the implemented machine learning model, and the motives for performing IML. We find an immense role of expert knowledge and image data in medical IML. We then provide an overview and analysis of recent approaches and supply five directions for future research. This review can help develop future medical IML approaches by easily referencing existing solutions and shaping future research directions.  \n1. Introduction  \nDespite the broad use of machine learning (ML) across applications, there are still limitations and challenges in the adoption of ML in medical practice [1]. Sufficient data availability and quality are essential for accurate predictions of ML models. In the medical domain, data gathering is difficult and expensive since diseases are constantly evolving [2], digitalization in medical institutions lags behind [3], and legal requirements need to be met for sensitive medical data [4].  \nData availability, however, is not the only factor that hinders the adoption of ML in medicine. Whenever the decisions of ML models are in doubt, we refer to the decisions made by domain experts. Expert-based decisions can be more elaborate and take care of the specifics of each patient. Therefore, emerging research on explainable and interpretable ML provides explanations of the decisions made by ML approaches [5]. These improvements in explainability and specificity are often achieved by integrating experts’ domain knowledge (DK) into ML models. This is called informed ML (IML) which “describes learning from a hybrid information source that consists of data and prior knowledge” [6]. Such hybrid learning can provide the benefits of both, expert-based and datadriven decisions [6].  \nCombining expert-based and data-driven decisions, however, results in customized solutions regarding the ML models used, the DK included in the models, or the step of applying the DK to achieve the benefits of  \novercoming a specific problem. Every customization solves a specific problem, but we currently lack a general understanding of frequent combinations, which could benefit practitioners to apply existing solutions to their related problems.  \nPrevious works already investigated the current status of ML in medicine and argued that an improved inclusion of computers in clinical practice “may allow radiologists to further integrate their knowledge”[7,8]. Based on these results, first approaches were conducted summarizing the inclusion of DK into medical imaging algorithms [9]. However, in the study at hand, we do not limit ourselves to imaging applications but investigate the inclusion of DK in a broader sense. We refer to an existing taxonomy to assess and categorize the inclusion of DK by analyzing the three dimensions source of DK, structure of DK, and application step [6].  \nIn addition to the inclusion-related dimensions, we also gather an overview of the motives for performing IML. All approaches conduct IML for a multitude of reasons, which range from improving the explainability of the approaches by including DK [10], over reducing the effort requir","cbCailBtmZ2G5qEv","https://ap.wps.com/l/cbCailBtmZ2G5qEv","pdf",1383908,1,11,"English","en",105,"# Introduction\n## Challenges of applying machine learning in medical practice\n## Informed machine learning and the role of domain knowledge\n## Research questions and review method\n## Overview of paper selection and analysis approach","[{\"question\":\"What problem does informed machine learning aim to address in medicine?\",\"answer\":\"It combines domain knowledge with machine learning to mitigate limited explainability, insufficient robustness, and data availability challenges in medical settings.\"},{\"question\":\"How does the scoping review evaluate informed machine learning approaches?\",\"answer\":\"It follows a scoping study method and uses an existing taxonomy to analyze DK sources, DK structure, the ML models applied, and the motives for performing IML across 177 papers.\"},{\"question\":\"What future research directions are proposed by the review?\",\"answer\":\"The review synthesizes recent approaches, identifies clusters in DK-structure and model combinations, and derives five directions to guide future work on medical informed machine learning.\"}]","Medical informed machine learning - A scoping review and future research directions | PDF",1785733595,28,{"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},"medical-informed-machine-learning-a-scoping-review-and-future-research-directions","",{"@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/medical-informed-machine-learning-a-scoping-review-and-future-research-directions/121074/",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 informed machine learning aim to address in medicine?","Question",{"text":75,"@type":76},"It combines domain knowledge with machine learning to mitigate limited explainability, insufficient robustness, and data availability challenges in medical settings.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the scoping review evaluate informed machine learning approaches?",{"text":80,"@type":76},"It follows a scoping study method and uses an existing taxonomy to analyze DK sources, DK structure, the ML models applied, and the motives for performing IML across 177 papers.",{"name":82,"@type":73,"acceptedAnswer":83},"What future research directions are proposed by the review?",{"text":84,"@type":76},"The review synthesizes recent approaches, identifies clusters in DK-structure and model combinations, and derives five directions to guide future work on medical informed machine learning.","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"]