[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124337-en":3,"doc-seo-124337-105":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},124337,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Incidence and severity of aortic stenosis according to machine learning predicted risk of atrial fibrillation","Atrial fibrillation (AF) and aortic stenosis (AS) frequently co-occur in older adults and share disease pathways. This study assessed whether machine learning predicted risk of incident AF, generated from clinical health records using the FIND-AF algorithm, relates to AS severity and AS incidence. In a disease registry, higher FIND-AF risk aligned with worsening AS measures, though severe versus non-severe discrimination remained moderate. In over 400,000 primary care records, FIND-AF predicted incident AS with good performance and increasing cumulative incidence across risk strata; the AS hazard rose markedly at higher FIND-AF scores. ","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nIncidence and severity of aortic stenosis according to machine learning predicted risk of atrial fibrillation  \nAlhena Younis1,6, Harriet Larvin2,6, Khalid Kazi3, Rowan Hall1, Mohammad Haris3,4, Tobin Joseph3,4, Keerthenan Raveendra5, Umbreen Nadeem1, Daniel J. Blackman1,3, Dominik Schlosshan1, Jianhua Wu2, Ramesh Nadarajah1,3,4,7􀀍 & Chris P. Gale1,3,4,7  \nAtrial fibrillation (AF) and aortic stenosis (AS) are two common progressive conditions affecting older persons that share pathobiological pathways. Early detection of AS is critical for improving outcomes, but no prediction tool exists to inform decision making. In this study we evaluated the association between machine learning predicted risk of incident AF from clinical health records (using the FIND-AF algorithm) and severity and incidence of AS. In a disease registry we found that higher FIND-AF risk was correlated with parameters of increasing AS severity including smaller aortic valve area, and higher maximum velocity and peak pressure gradient but ability to differentiate severe from non-severe AS was moderate (sensitivity 0.545, specificity 0.770) . In over 400,000 primary care clinical health records, FIND-AF showed good prediction performance for incident AS (AUC 0.782, 95% CI 07.69–0.795), and the cumulative incidence increased with higher FIND-AF risk strata. The hazard of AS was over 40-fold higher in patients with FIND-AF risk scores of more than 0.05 compared to patients with FIND-AF risk scores of less than 0.005. Predicted risk of AF is associated with severity and incidence of AS, but predictive ability for AS may be improved by developing a machine learning model specifically for this outcome.  \nKeywords Aortic stenosis, Atrial fibrillation, Prediction, Screening, Machine learning, Clinical health records  \nAortic stenosis (AS) is the most common valvular disease requiring intervention, with approximately 5% of adults over the age of 65 affected1,2. It is invariably progressive, and once stenosis is severe, symptoms of breathlessness, angina and syncope follow. At this stage quality of life (QOL) declines and prognosis is poor, with 50% of patients dead within two years of symptom onset3. As the population globally ages the prevalence of AS has increased year-on-year4,5. Given the prognostic implications of late presentation with severe symptomatic AS, and the increasing success of transcatheter aortic valve implantation (TAVI), including in asymptomatic individuals6, there is renewed focus on early detection of AS7.  \nAtrial fibrillation (AF) frequently co-occurs with AS and both conditions share common risk factors including age, hypertension, and systemic inflammation2. The FIND-AF (Future Innovations in Novel Detection for Atrial Fibrillation) machine learning algorithm score predicts incident AF risk using community-based electronic health records, requiring only basic demographic and comorbidity data8. Our previous work has shown that higher predicted FIND-AF risk is also associated with incident AS9, with higher FIND-AF risk compared to lower FIND-AF risk being associated with a 10-fold increased hazard. We therefore hypothesised that FIND-AF risk, whilst developed to predict short-term AF, may also be useful to predict incident AS.  \nHowever, the specific FIND-AF score associated with severe AS remains unclear, partly because severity of valvular heart disease is often incompletely recorded in routine national datasets9. To address this gap, we  \n1Department of Cardiology, Leeds Teaching Hospitals NHS Trust, Leeds, UK. 2Wolfson Institute of Population Health, Queen Mary University of London, London, UK. 3Leeds Institute for Cardiovascular and Metabolic Medicine, Health Data Research UKFellow, University of Leeds, 6 Clarendon Way, Leeds LS2 9DA, UK. 4Leeds Institute of Data Analytics, University of Leeds, Leeds, UK. 5Faulty of Medicine and Health, University of Leeds, L","cbCaij0fX1tvr3L0","https://ap.wps.com/l/cbCaij0fX1tvr3L0","pdf",2325817,1,9,"English","en",105,"# Background\n## Need for early AS detection and lack of prediction tools\n## Shared risk factors and the FIND-AF algorithm\n# Methods\n## Cohorts and disease registry analysis\n## Nationwide primary care validation\n## Thresholding to distinguish severe vs non-severe AS\n# Results\n## Association between FIND-AF risk and AS severity measures\n## Prediction performance for incident AS\n## Risk-stratified cumulative incidence and hazard estimates\n# Implications\n## Improving AS prediction with outcome-specific models","[{\"question\":\"What is the main objective of the study regarding aortic stenosis and atrial fibrillation?\",\"answer\":\"To evaluate whether machine learning predicted risk of incident atrial fibrillation (from clinical health records using FIND-AF) is associated with the severity and incidence of aortic stenosis.\"},{\"question\":\"How is FIND-AF risk calculated and what data does it require?\",\"answer\":\"FIND-AF is a machine learning algorithm that predicts incident AF risk using community-based electronic health records, requiring only basic demographic and comorbidity data.\"},{\"question\":\"What did the study find about the relationship between FIND-AF risk and AS severity?\",\"answer\":\"Higher FIND-AF risk correlated with echocardiographic parameters indicating increasing AS severity (such as smaller valve area and higher maximum velocity and pressure gradient), with moderate ability to separate severe from non-severe AS.\"},{\"question\":\"How well did FIND-AF predict incident aortic stenosis in primary care records?\",\"answer\":\"FIND-AF showed good prediction performance for incident AS (AUC 0.782 with 95% CI 0.769–0.795), and cumulative incidence increased across higher FIND-AF risk strata, with markedly higher AS hazard at higher risk scores.\"}]","Incidence and severity of aortic stenosis according to machine learning predicted risk of atrial fibrillation | PDF",1785821673,23,{"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},"incidence-and-severity-of-aortic-stenosis-according-to-machine-learning-predicted-risk-of-atrial-fibrillation","",{"@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/incidence-and-severity-of-aortic-stenosis-according-to-machine-learning-predicted-risk-of-atrial-fibrillation/124337/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main objective of the study regarding aortic stenosis and atrial fibrillation?","Question",{"text":75,"@type":76},"To evaluate whether machine learning predicted risk of incident atrial fibrillation (from clinical health records using FIND-AF) is associated with the severity and incidence of aortic stenosis.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is FIND-AF risk calculated and what data does it require?",{"text":80,"@type":76},"FIND-AF is a machine learning algorithm that predicts incident AF risk using community-based electronic health records, requiring only basic demographic and comorbidity data.",{"name":82,"@type":73,"acceptedAnswer":83},"What did the study find about the relationship between FIND-AF risk and AS severity?",{"text":84,"@type":76},"Higher FIND-AF risk correlated with echocardiographic parameters indicating increasing AS severity (such as smaller valve area and higher maximum velocity and pressure gradient), with moderate ability to separate severe from non-severe AS.",{"name":86,"@type":73,"acceptedAnswer":87},"How well did FIND-AF predict incident aortic stenosis in primary care records?",{"text":88,"@type":76},"FIND-AF showed good prediction performance for incident AS (AUC 0.782 with 95% CI 0.769–0.795), and cumulative incidence increased across higher FIND-AF risk strata, with markedly higher AS hazard at higher risk scores.","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"]