[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121941-en":3,"doc-seo-121941-105":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},121941,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Application of an Ontology for Model Cards - To Generate Computable Artifacts for Linking Machine Learning Information from Biomedical Research","Model card reports provide transparent documentation of machine learning models, including evaluation results, limitations, and intended use. This work addresses growing interest from federal health agencies in applying model-card reporting to biomedical studies using AI, aligned with FAIR principles and ethical disclosure needs. The paper introduces a Java-based publishing approach that uses a previously developed ontology and OWL API tooling to generate computable, machine-readable model card artifacts, enabling semantic linking and future FAIR-supporting use cases.","Author Manuscript Author Manuscript Author Manuscript Author Manuscript  \n\n|  | HHS Public Access\u003Cbr>Author manuscript\u003Cbr>Proc Int World Wide Web Conf. Author manuscript; available in PMC 2024 February 07. |\n| --- | --- |\n\nPublished in final edited form as:  \nProc Int World Wide Web Conf. 2023 April ; 2023(Companion): 820–825.  \ndoi:10 . 1145/3543873 .3587601.  \nApplication of an ontology for model cards to generate computable artifacts for linking machine learning information from biomedical research  \nMUHAMMAD “TUAN” AMITH, University of North Texas, USA  \nLICONG CUI,  \nThe University of Texas Health Science Center at Houston, USA  \nKIRK ROBERTS,  \nThe University of Texas Health Science Center at Houston, USA CUI TAO*  \nThe University of Texas Health Science Center at Houston, USA  \nAbstract  \nModel card reports provide a transparent description of machine learning models which includes information about their evaluation, limitations, intended use, etc. Federal health agencies have expressed an interest in model cards report for research studies using machine-learning based AI. Previously, we have developed an ontology model for model card reports to structure and formalize these reports. In this paper, we demonstrate a Java-based library (OWL API, FaCT++) that leverages our ontology to publish computable model card reports. We discuss future directionsand other use cases that highlight applicability and feasibility of ontology-driven systems to support FAIR challenges.  \nKeywords  \nmodel card reports; ontology; semantic web; machine learning; FAIR; transparency; document engineering; inference; description logic; artificial intelligence  \n1 INTRODUCTION  \nThe National Institutes of Health has expressed interest in applying FAIR principles to the growing number of biomedical research involving machine learning-based artificial intelligence (AI) resources [12]. In addition, the initiative also involves disclosing some transparent ethical information for these AI models. To accomplish this, there needs to be standards, software, and datasets to support FAIR principles [16] and accommodating the aforementioned ethics. One of the suggested tools are model card reports which are static  \n*corresponding author.  \nAuthor Manuscript Author Manuscript Author Manuscript Author Manuscript  \nAMITH et al. Page 2  \ndocuments that outline features and associated information about machine learning models  \n[10] .  \nModel card reports were introduced as a type of report to accompany the release of a machine learning model to document various aspects of the model. This short document of one to two pages would detail performance information, limitations, intended uses and information about the evaluation of the datasets used to train and test the model. This form of documentation intends to help standardize the practice of transparency for machine learning models for stakeholders.  \nIn our previous work [1], we developed an ontology (Model Card Report Ontology) to represent a model card report with the intent that the ontology can be used as a framework for computable digital representation of the model card. This was demonstrated by translating samples of model card report from experimental bioinformatics studies to show how a static model card report would map to our ontology framework. One of the challenging tasks of producing this computable linked version of the model card report was the arduous effort in using Protégé authoring tool [11] to encode the model card information. This is also compounded that novice users would find difficulty in using Protégé [13] .  \nThis work aims to circumvent the challenges and make the process of generating an ontology-based model card report accessible. We also introduce an ontology-driven publishing engine that would be part of an information processing pipeline to produce ontology-based model card reports for distribution and sharing. The goal is to demonstrate the applicability of ontologies in docum","cbCailBkPQngu9PK","https://ap.wps.com/l/cbCailBkPQngu9PK","pdf",1947957,1,16,"English","en",105,"# Introduction\n## Model Card Reports and FAIR Motivation\n## Goal and Proposed Approach\n# Methods\n## Model Card Report Ontology","[{\"question\":\"What problem does the paper address regarding model card reports for biomedical AI?\",\"answer\":\"It targets the difficulty of making model cards computable and linked for machine processing, especially when encoding information using authoring tools is burdensome for researchers.\"},{\"question\":\"How does the proposed method generate computable model card artifacts?\",\"answer\":\"It uses a Java-based library (OWL API, FaCT++) that leverages an existing model card report ontology to publish ontology-driven, machine-readable artifacts.\"},{\"question\":\"What role do ontologies play in supporting FAIR and transparency goals?\",\"answer\":\"Ontologies structure model card content so machines can interpret and link information, helping satisfy FAIR-aligned transparency and enabling future reasoning and reuse.\"}]","Application of an Ontology for Model Cards - To Generate Computable Artifacts for Linking Machine Learning Information from Biomedical Research | PDF",1785807856,40,{"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},"application-of-an-ontology-for-model-cards-to-generate-computable-artifacts-for-linking-machine-learning-information-from-biomedical-research","",{"@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/application-of-an-ontology-for-model-cards-to-generate-computable-artifacts-for-linking-machine-learning-information-from-biomedical-research/121941/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address regarding model card reports for biomedical AI?","Question",{"text":75,"@type":76},"It targets the difficulty of making model cards computable and linked for machine processing, especially when encoding information using authoring tools is burdensome for researchers.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method generate computable model card artifacts?",{"text":80,"@type":76},"It uses a Java-based library (OWL API, FaCT++) that leverages an existing model card report ontology to publish ontology-driven, machine-readable artifacts.",{"name":82,"@type":73,"acceptedAnswer":83},"What role do ontologies play in supporting FAIR and transparency goals?",{"text":84,"@type":76},"Ontologies structure model card content so machines can interpret and link information, helping satisfy FAIR-aligned transparency and enabling future reasoning and reuse.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]