[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82227-en":3,"doc-seo-82227-105":29,"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":13,"seo_description":14,"update_tm":27,"read_time":28},82227,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","A Personalized Computational Framework for Assessing the Sufficiency of Partially Observed Data in Healthcare AI Models","Achieving early diagnosis and timely treatment remains a major medical challenge. Machine-learning models trained on complete patient data can enable reliable prediction of disease evolution and risk stratification, yet real-world deployments often face missing clinical variables at prediction time. The framework defines full-feature-capacity (FFC) and proposes Feature Sufficiency Analysis (FSA) using Monte Carlo estimation of missing-variable distributions conditioned on available features. FSA yields patient-specific sufficiency, enabling immediate risk prediction when FFC is reached. Case studies for postoperative ventilation and 10-year mortality show most patients achieve FFC with less than half the training features, plus interpretable feature ranking and cost-aware acquisition optimization.","Title: A Personalized Computational Framework for Assessing the Sufficiency of Partially Observed Data in Healthcare AI models.  \nQingchu Jin1,2, Felistas Mazhude3, Jamie B. Rabb3, Robert S. Kramer3, Douglas B. Sawyer2,3, Raimond L. Winslow1,4,5,6,7  \n1. Roux Institute, Northeastern University, ME USA  \n2. MaineHealth Institute for Research, ME USA  \n3. MaineHealth, ME USA  \n4. College of Engineering, Northeastern University, MA USA  \n5. Khoury College of Computer Sciences, Northeastern University, MA USA  \n6. Bouvé College of Health Sciences, Northeastern University, MA USA  \nContact information of corresponding author:  \nRaimond L. Winslow, PhD  \nEmail: [r.winslow@northeastern.edu](r.winslow@northeastern.edu)  \nAbstract  \nAchieving early and timely diagnosis and treatment for disease is a major challenge in medicine. Recent applications of machine learning (ML) algorithms trained on patient data have shown promise in many different settings for predicting the time-evolution of patient health state, thereby enabling more reliable patient risk stratification. A challenge often faced when applying these ML algorithms is that at any given time, not all clinical variables (features) needed as input to perform prediction tasks are available. We define the concept of full-feature-capacity (FFC) to refer to prediction performance when such algorithms make use of all features on which they were trained. We then introduce Feature Sufficiency Analysis (FSA) -a computational approach for determining whether a subset of all clinical features needed by an AI model is sufficient to achieve FFC. FSA applies Monte Carlo methods to estimate the underlying distributions of missing variables conditioned on features that are available. FSA provides a patient-specific assessment of whether the existing set of measured features achieves FFC. If yes, then there is no need to acquire further inputs and a ML-based prediction or risk stratification may be generated immediately. We provide two case studies: prediction of need for postoperative prolonged ventilation in patients recovering from heart surgery; 10-year mortality prediction in an outpatient cohort. We show that 86% of patients in the heart surgery cohort and 91% of subjects in the outpatient cohort achieved FFC when using fewer than half of the total number of features on which the learners were trained. We also demonstrate that FSA also provides a clinically interpretable feature-ranking methodology based on prediction sufficiency, identifies intrinsically hard-to-predict patient populations, and has the potential to perform cost-aware optimization for clinical data acquisition. FSA provides a generic computational approach for determining whether incomplete clinical information is  \nsufficient to support trustworthy AI-assisted clinical decision-making, thereby facilitating the prospective deployment of healthcare AI systems across diverse clinical settings.  \nIntroduction  \nEarly and timely diagnosis and treatment for diseases is one of the major challenges in medicine. From children acute appendicitis 1 to sepsis2, from acute trauma3 to lung cancer4, studies have shown that delayed diagnosis leads to an increase of complications and/or mortality.  \nThere is an emerging body of work on the use of machine-learning (ML) and other methods to learn models from patient data that make early prediction of disease onset or disease progression, improve accuracy of disease diagnosis, and better inform timely choice of therapy 5–8. Many studies show the impressive extent to which models can help improve disease diagnosis, prediction and treatment5,6,8–22, including using images to classify cancer20, using longitudinal ICU data to predict septic shock 15, using waveform data to predict neurological outcome 10, using clinical codes to predict the 3-month risk of pancreatic cancer occurrence, using lab result data to diagnose ovarian cancer23 and use of multimodal data to predict severity of COVID-19 ","cbCaifb1edqP8HRI","https://ap.wps.com/l/cbCaifb1edqP8HRI","pdf",1705113,1,47,"English","en",105,"# Abstract\n# Introduction\n## Early diagnosis challenges and ML promise\n## Missing features in real-world clinical deployment\n## Need for a patient-specific reliability framework","[{\"question\":\"What problem does the framework address in healthcare AI models?\",\"answer\":\"It addresses the gap between ML models that assume complete inputs and real-world prediction times when some required clinical variables may be missing.\"},{\"question\":\"How does Feature Sufficiency Analysis (FSA) determine whether available features are enough?\",\"answer\":\"FSA defines full-feature-capacity (FFC) and uses Monte Carlo methods to estimate distributions of missing variables conditioned on features that are available, producing a patient-specific sufficiency assessment.\"},{\"question\":\"What do the case studies show about using fewer features?\",\"answer\":\"In the heart surgery cohort and outpatient mortality cohort, 86% and 91% of patients respectively achieved FFC using fewer than half of the total features used for training.\"}]",1784178982,118,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"a-personalized-computational-framework-for-assessing-the-sufficiency-of-partially-observed-data-in-healthcare-ai-models","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/a-personalized-computational-framework-for-assessing-the-sufficiency-of-partially-observed-data-in-healthcare-ai-models/82227/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",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 framework address in healthcare AI models?","Question",{"text":75,"@type":76},"It addresses the gap between ML models that assume complete inputs and real-world prediction times when some required clinical variables may be missing.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Feature Sufficiency Analysis (FSA) determine whether available features are enough?",{"text":80,"@type":76},"FSA defines full-feature-capacity (FFC) and uses Monte Carlo methods to estimate distributions of missing variables conditioned on features that are available, producing a patient-specific sufficiency assessment.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the case studies show about using fewer features?",{"text":84,"@type":76},"In the heart surgery cohort and outpatient mortality cohort, 86% and 91% of patients respectively achieved FFC using fewer than half of the total features used for training.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"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":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]