[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122384-en":3,"doc-seo-122384-105":29,"detail-sidebar-cat-0-en-105":82},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},122384,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",7,"Healthcare","Quality Assurance for Home Spirometry using Machine Learning","Spirometry is essential for evaluating lung function, supporting lung-health assessment and monitoring treatment effectiveness. Machine Learning methods can rival expert performance in spirometry classification, yet many solutions rely on heavy custom pre-processing and complex architectures. This work uses efficient time-series classifiers to rapidly and reliably verify home spirometry signal quality, enabling real-time deployment. Seven models classify curves as acceptable or not acceptable, benchmarked against related studies.","Quality Assurance for Home Spirometry using  \nMachine Learning  \n1st Darcey Gardiner School of Computing Sciences University of East Anglia Norwich, UK [darcey.gardiner@uea.ac.uk](darcey.gardiner@uea.ac.uk)  \n2nd Harry Rogers Department of Engineering Science University of Oxford Oxford, UK [harry.rogers@eng.ox.ac.uk](harry.rogers@eng.ox.ac.uk)  \n3rd Jason Lines School of Computing Science University of East Anglia Norwich, UK [j.lines@uea.ac.uk](j.lines@uea.ac.uk)  \n4th Andrew Wilson Norwich Medical School University of East Anglia Norwich, UK[a.m.wilson@uea.ac.uk](a.m.wilson@uea.ac.uk)  \n5th Min Hane Aung School of Computing Science University of East Anglia  \nNorwich, UK [min.aung@uea.ac.uk](min.aung@uea.ac.uk)  \nAbstract—Spirometry is used for evaluating lung function, playing a crucial role in assessing lung health and monitoring treatment effectiveness. Numerous studies demonstrate the potential of Machine Learning algorithms to match human experts in spirometry classification, although most approaches depend on custom data pre-processing and complex model architectures. Therefore, we apply efficient Time Series (TS) classifiers to quickly and computationally assure spirometry signal quality, enabling realtime deployment. Seven classifiers were implemented to classify spirometry curves as ‘Acceptable’ or ‘Not Acceptable’, with performance referenced against results from similar studies. The bestperforming classifier was FreshPRINCE, a TS method combining TSFresh feature extraction with Rotation Forest classifier. The FreshPRINCE model achieved an accuracy of 0.9449, precision, recall and F1 Score of 0.9745, 0.9586 and 0.9665, consistently matching and sometimes outperforming more complex models. These findings suggest models, such as FreshPRINCE, could streamline spirometry analysis, reducing computational burden, whilst maintaining classification performance.  \nIndex Terms—spirometry, pulmonary function, machine learning, time series, classification  \nI. INTRODUCTION  \nSpirometry tests measure the flow and volume of air an individual can exhale after maximal inspiration, displayed in FlowVolume and Volume-Time curves. It is predominantly used to diagnose and manage pulmonary diseases. Traditionally, qualified respiratory physiologists analyse spirometry results, but this process is costly and time-consuming, limiting access to testing. There is a healthcare need for rapid, reliable and affordable community-based spirometry. With the rising global burden of Chronic Respiratory Diseases (CRDs) and pressure on healthcare systems, automating this process providesan opportunity to improve diagnostic efficiency and patient outcomes. Many healthcare professionals struggle with the lack of diagnostic tools, leading to misdiagnosis or delayed diagnoses and higher CRD mortality [1] . Widespread access to spirometry and improved automated quality assurance could  \nreduce mortality by enabling earlier diagnosis and treatment [2] .  \nMachine Learning (ML) techniques offer new approaches to analysing spirometry data, reducing the complexities inherent in lung function testing. Classifying spirometry curve quality, which requires expert knowledge, is prone to human error, something ML can address. A recent study used pre-built Convolutional Neural Networks (CNNs) to classify spirometry curves into three categories: acceptable, early termination, and non-acceptable results, with the VGG16 model achieving 0.939 accuracy but only 0.877 precision (proportion of all the positive classifications that are actually positive) [3] . Other research, such as Das et al. [4], used a custom CNN architecture, yielding 0.87 accuracy for acceptable curves, with a sensitivity of 0.90 (the ability to correctly identify positives) and specificity of 0.85 (the ability to correctly identify negatives [5]) . Bonthada et al. [6] used CNNs to detect and classify use-errors, achieving 0.94 accuracy with only 100 samples. This approach is valuable for identifyin","cbCaibqBrEqx65q6","https://ap.wps.com/l/cbCaibqBrEqx65q6","pdf",424655,1,"English","en",105,"# Introduction\n## Spirometry and its clinical importance\n## Machine Learning for spirometry analysis\n## Related classification tasks and ML methods\n## Clinical Decision Support and time-series classification","[{\"question\":\"What classification outcome does the system produce for spirometry curves?\",\"answer\":\"The system classifies each spirometry curve as either “Acceptable” or “Not Acceptable,” using multiple time-series classifier models whose performance is compared with results from similar studies.\"}]","Quality Assurance for Home Spirometry using Machine Learning | PDF",1785810354,18,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":77,"head_meta":79,"extra_data":81,"updated_unix":27},"quality-assurance-for-home-spirometry-using-machine-learning","",{"@graph":35,"@context":76},[36,53,67],{"@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/healthcare/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/quality-assurance-for-home-spirometry-using-machine-learning/122384/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70],{"name":71,"@type":72,"acceptedAnswer":73},"What classification outcome does the system produce for spirometry curves?","Question",{"text":74,"@type":75},"The system classifies each spirometry curve as either “Acceptable” or “Not Acceptable,” using multiple time-series classifier models whose performance is compared with results from similar studies.","Answer","https://schema.org",{"og:url":51,"og:type":78,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":80,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":83},[84,88,92,96,101,106,109,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":45,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":107,"slug":108},40,"healthcare",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},8,"Research & Report",30,"research-report",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general"]