[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125785-en":3,"doc-seo-125785-105":30,"detail-sidebar-cat-0-en-105":95},{"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":4,"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},125785,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Comparison of machine learning approaches for positive airway pressure adherence prediction in a veteran cohort - Research study","Positive airway pressure (PAP) adherence for sleep apnea remains suboptimal, especially in veterans, limiting the effectiveness of a therapy that is otherwise proven to reverse obstructive sleep apnea pathophysiology. Using electronic health record data from a VA cohort, multiple machine learning algorithms were trained to forecast 90-day adherence based on 4-hour nightly use. Model quality was assessed with validation performance, including root mean square error, and was improved by incorporating 30-day PAP data and more granular diagnoses and medications.","TYPE Original Research PUBLISHED 16 February 2024 DOI 10. 3389/frsle.2024.1278086  \nOPEN ACCESS  \nEDITED BY  \nStuart F. Quan,  \nHarvard Medical School, United States  \nREVIEWED BY  \nSamuel Huang,  \nVirginia Commonwealth University, United States  \nAlyssa Hu􀀀,  \nSeattle Children’s Research Institute, United States  \n*CORRESPONDENCE  \nAnna M. May  \n [drannamay@gmail.com](drannamay@gmail.com)  \nRECEIVED 15 August 2023  \nACCEPTED 29 January 2024  \nPUBLISHED 16 February 2024  \nCITATION  \nMay AM and Dalton JE (2024) Comparison of machine learning approaches for positive airway pressure adherence prediction in a veteran cohort. Front. Sleep 3:1278086 .  \ndoi: 10.3389/frsle.2024.1278086  \nCOPYRIGHT  \n© 2024 May and Dalton. This is an  \nopen-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nComparison of machine learning approaches for positive airway pressure adherence prediction ina veteran cohort  \nAnna M. May1,2* and Jarrod E. Dalton3  \n1 Geriatric Research Education and Clinical Center and Sleep Medicine Section, Louis Stokes Cleveland VA Medical Center, Cleveland, OH, United States, 2 School of Medicine, Case Western Reserve University, Cleveland, OH, United States, 3 Department of Quantitative Sciences, Lerner Research Institute Cleveland Clinic, Cleveland, OH, United States  \nBackground: Adherence to positive airway pressure (PAP) therapy for sleep apnea is suboptimal, particularly in the veteran population. Accurately identifying those best suited for other therapy or additional interventions may improve adherence. We evaluated various machine learning algorithms to predict 90-day adherence.  \nMethods: The cohort of VA Northeast Ohio Health Care system patients who were issued a PAP machine (January 1, 2010–June 30, 2015) had demographics, comorbidities, and medications at the time of polysomnography obtained from the electronic health record. The data were split 60:20:20 into training, calibration, and validation data sets, with no use of validation data for model development. We constructed models for the first 90-day adherence period (% nights ≥4h use) using the following algorithms: linear regression, least absolute shrinkage and selection operator, elastic net, ridge regression, gradient boosted machines, support vector machine regression, Bayes-based models, and neural nets. Prediction performance was evaluated in the validation data set using root mean square error (RMSE) .  \nResults: The 5,047 participants were 38 .3 ± 11.9 years old, and 96 . 1% male, with 36 .8% having coronary artery disease and 52 .6% with depression. The median adherence was 36 . 7%(interquartile range: 0%, 86 . 7%) . The gradient boosted machine was superior to other machine learning techniques (RMSE 37. 2) . However, the performance was similar and not clinically useful for all models without 30-day data. The 30-day PAP data and using raw diagnoses and medications (vs. grouping by type) improved the RMSE to 24 .27.  \nConclusion: Comparing multiple prediction algorithms using electronic medical record information, we found that none has clinically meaningful performance. Better adherence predictive measures may o􀀀er opportunities for personalized tailoring of interventions.  \nKEYWORDS  \nsleep apnea, machine learning, adherence, positive airway pressure, compliance  \n1 Introduction  \nObstructive sleep apnea (OSA) a􀀓ects an estimated 26% of the U.S. population and 47% of veterans with sleep disorders (Peppard et al., 2013; Alexander et al., 2016) . OSA causes daytime dysfunction, decreased quality of life, and increased rates of morbidity and mortality, particularly in t","cbCain8zo2wCnzAk","https://ap.wps.com/l/cbCain8zo2wCnzAk","pdf",497060,1,9,"English","en",105,"# Introduction\n## Methods\n## Results\n## Conclusion","[{\"question\":\"What was the main goal of this study?\",\"answer\":\"To compare multiple machine learning approaches for predicting 90-day positive airway pressure adherence in a veteran cohort.\"},{\"question\":\"Which patient data sources were used for model development?\",\"answer\":\"Demographics, comorbidities, and medications from electronic health records at the time of polysomnography were used to build prediction models.\"},{\"question\":\"What modeling approach performed best, and was it clinically useful?\",\"answer\":\"A gradient boosted machine showed the lowest validation RMSE among tested methods, but overall performance was not clinically meaningful, particularly without 30-day PAP data.\"},{\"question\":\"How did adding 30-day PAP information affect prediction performance?\",\"answer\":\"Including 30-day PAP data, along with using raw diagnoses and medications rather than grouped categories, improved RMSE substantially.\"}]","Comparison of machine learning approaches for positive airway pressure adherence prediction in a veteran cohort - Research study | PDF",1785901188,23,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"comparison-of-machine-learning-approaches-for-positive-airway-pressure-adherence-prediction-in-a-veteran-cohort-research-study","",{"@graph":36,"@context":89},[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/comparison-of-machine-learning-approaches-for-positive-airway-pressure-adherence-prediction-in-a-veteran-cohort-research-study/125785/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What was the main goal of this study?","Question",{"text":75,"@type":76},"To compare multiple machine learning approaches for predicting 90-day positive airway pressure adherence in a veteran cohort.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which patient data sources were used for model development?",{"text":80,"@type":76},"Demographics, comorbidities, and medications from electronic health records at the time of polysomnography were used to build prediction models.",{"name":82,"@type":73,"acceptedAnswer":83},"What modeling approach performed best, and was it clinically useful?",{"text":84,"@type":76},"A gradient boosted machine showed the lowest validation RMSE among tested methods, but overall performance was not clinically meaningful, particularly without 30-day PAP data.",{"name":86,"@type":73,"acceptedAnswer":87},"How did adding 30-day PAP information affect prediction performance?",{"text":88,"@type":76},"Including 30-day PAP data, along with using raw diagnoses and medications rather than grouped categories, improved RMSE substantially.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,131,134,138],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":129,"slug":130},"Religion & Spirituality",20,"religion-spirituality",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":129,"slug":133},"World Cup","world-cup",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":135,"slug":137},10,"Lifestyle","lifestyle",{"id":139,"doc_module":4,"doc_module_name":46,"category_name":140,"show_sort_weight":110,"slug":141},19,"General","general"]