Development and External Validation of an Interpretable Machine-Learning Model for HFpEF Comorbidity Risk in COPD Patients

preprint OA: closed
Full text JSON View at publisher

Abstract

Abstract BACKGROUND Chronic Obstructive Pulmonary Disease (COPD) and Heart Failure with preserved Ejection Fraction (HFpEF) frequently coexist, leading to increased hospitalization, mortality, and healthcare burden. Early identification of HFpEF risk in COPD patients is critical for timely intervention. AIM To develop and validate an interpretable machine learning (ML) model for predicting HFpEF risk in COPD patients and to identify key predictors using explainable artificial intelligence techniques. METHODS This retrospective study analyzed 1,550 COPD patients, divided into COPD-only and COPD-HFpEF groups. Feature selection was performed using LASSO regression, logistic regression, and Boruta random forest. Ten ML models were developed and evaluated on an internal test set, with the best model further validated on an external cohort (n = 69). Model interpretability was assessed using SHapley Additive exPlanations (SHAP). RESULTS Nine predictors were consistently selected: NT-proBNP, red blood cell count, fibrinogen, cholesterol, arterial PaO₂, inspiratory capacity (IC), IC% predicted, late diastolic mitral inflow velocity, and the COPD Assessment Test score. The XGBoost model achieved the best performance, with an AUC of 0.898 (95% CI: 0.867–0.929) on the internal test set and 0.851 (95% CI: 0.753–0.948) on external validation. SHAP analysis identified NT-proBNP as the most influential predictor. CONCLUSION The developed XGBoost model accurately predicts HFpEF risk in COPD patients and offers clinically interpretable insights into key risk factors, supporting early identification and stratified management.
Full text 29,504 characters · extracted from preprint-html · click to expand
Development and External Validation of an Interpretable Machine-Learning Model for HFpEF Comorbidity Risk in COPD Patients | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Development and External Validation of an Interpretable Machine-Learning Model for HFpEF Comorbidity Risk in COPD Patients Jing Cao, Boyu Kang, Shuangshuang Li, Yan Lei, Dan Liu, Chunmei Li, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7911218/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract BACKGROUND Chronic Obstructive Pulmonary Disease (COPD) and Heart Failure with preserved Ejection Fraction (HFpEF) frequently coexist, leading to increased hospitalization, mortality, and healthcare burden. Early identification of HFpEF risk in COPD patients is critical for timely intervention. AIM To develop and validate an interpretable machine learning (ML) model for predicting HFpEF risk in COPD patients and to identify key predictors using explainable artificial intelligence techniques. METHODS This retrospective study analyzed 1,550 COPD patients, divided into COPD-only and COPD-HFpEF groups. Feature selection was performed using LASSO regression, logistic regression, and Boruta random forest. Ten ML models were developed and evaluated on an internal test set, with the best model further validated on an external cohort (n = 69). Model interpretability was assessed using SHapley Additive exPlanations (SHAP). RESULTS Nine predictors were consistently selected: NT-proBNP, red blood cell count, fibrinogen, cholesterol, arterial PaO₂, inspiratory capacity (IC), IC% predicted, late diastolic mitral inflow velocity, and the COPD Assessment Test score. The XGBoost model achieved the best performance, with an AUC of 0.898 (95% CI: 0.867–0.929) on the internal test set and 0.851 (95% CI: 0.753–0.948) on external validation. SHAP analysis identified NT-proBNP as the most influential predictor. CONCLUSION The developed XGBoost model accurately predicts HFpEF risk in COPD patients and offers clinically interpretable insights into key risk factors, supporting early identification and stratified management. COPD HFpEF Machine Learning Risk Prediction Model Comorbidity Full Text Additional Declarations No competing interests reported. Supplementary Files supplymentary.docx Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7911218","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":542153439,"identity":"99777116-2d83-49dc-b2eb-1238f6d0aa85","order_by":0,"name":"Jing Cao","email":"","orcid":"","institution":"Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Cao","suffix":""},{"id":542153440,"identity":"72a27c17-cc83-4054-8078-94fb1f5dd90f","order_by":1,"name":"Boyu Kang","email":"","orcid":"","institution":"Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Boyu","middleName":"","lastName":"Kang","suffix":""},{"id":542153441,"identity":"7de9dc9a-9f77-41af-ab1f-30785fdbbe8c","order_by":2,"name":"Shuangshuang Li","email":"","orcid":"","institution":"Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Shuangshuang","middleName":"","lastName":"Li","suffix":""},{"id":542153442,"identity":"44148c34-0ea4-415c-ba4c-763904039856","order_by":3,"name":"Yan Lei","email":"","orcid":"","institution":"Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yan","middleName":"","lastName":"Lei","suffix":""},{"id":542153443,"identity":"2b483b29-9c25-48f1-bd23-07ac7cb4886b","order_by":4,"name":"Dan Liu","email":"","orcid":"","institution":"Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Dan","middleName":"","lastName":"Liu","suffix":""},{"id":542153444,"identity":"ee5fe9ba-cdd9-45a6-9ee7-d75c0994e6d3","order_by":5,"name":"Chunmei Li","email":"","orcid":"","institution":"The Third Affiliated Hospital of Xi’an Medical University","correspondingAuthor":false,"prefix":"","firstName":"Chunmei","middleName":"","lastName":"Li","suffix":""},{"id":542153445,"identity":"6484c767-0b9d-4bde-86ff-22328d701ca0","order_by":6,"name":"Wei Guo","email":"","orcid":"","institution":"Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Guo","suffix":""},{"id":542153446,"identity":"7ff3db33-f6c6-40dc-b1d9-8d8e55d4fa34","order_by":7,"name":"Binghua Zhang","email":"","orcid":"","institution":"Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Binghua","middleName":"","lastName":"Zhang","suffix":""},{"id":542153447,"identity":"5ec7684b-421e-4499-8d02-ddf54770cae5","order_by":8,"name":"Xiaoyan Xie","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2ElEQVRIiWNgGAWjYBACeYbzzz9I/GCr52dmPkCcFsPGM2wMlj18CZLtbAlEWnMYqKWCTS7B4DyPAXE6GNvOHntwg8csj+Ewz8cbbxjs5HQbCGhh5zmXbjjDIq2YsZl3s+UchmRjswOEbJlxwEBagucYYzMz7zZpHoYDidsIaWG4/8BA+g/bf8Y2Zp5nRGo5cMZMQoKNLbGHmYeNOC2GDceSDSR72IwlmNmMLecYEOEXeYbDBx8Ao1LO/vzhhzfeVNjJEdSCAiSIjRpkLaTqGAWjYBSMghEBALNOQWQlgSQ0AAAAAElFTkSuQmCC","orcid":"","institution":"Fourth Military Medical University","correspondingAuthor":true,"prefix":"","firstName":"Xiaoyan","middleName":"","lastName":"Xie","suffix":""}],"badges":[],"createdAt":"2025-10-21 06:38:44","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7911218/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7911218/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95553766,"identity":"bef96fb0-6ec9-4fcd-bed7-e4b4cdf86f53","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2747572,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/0ee64755062010e1ad3214f4.docx"},{"id":95654373,"identity":"513ab858-0555-465f-8a38-70c9eca14edf","added_by":"auto","created_at":"2025-11-11 16:11:23","extension":"tif","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":921804,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/94ada25273c3b671c34ab6c5.tif"},{"id":95654815,"identity":"0a1492df-9f5f-49ea-88f8-aafcd759be2f","added_by":"auto","created_at":"2025-11-11 16:13:14","extension":"tif","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19136660,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/5355b68628246e4c990ec252.tif"},{"id":95553763,"identity":"b0429631-e711-4486-9991-c7e9c6af6eaa","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"docx","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20088,"visible":true,"origin":"","legend":"","description":"","filename":"Table1.docx","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/958f27621c6819875efca83b.docx"},{"id":95655811,"identity":"36773716-e078-475f-b1c4-3c92d87a7c03","added_by":"auto","created_at":"2025-11-11 16:17:00","extension":"tif","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19881664,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/fc5bd5d25a460a7ece8d5d66.tif"},{"id":95553771,"identity":"6eeaaf52-cbe4-4a34-a8a9-e8ef5e41f178","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"tif","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8277392,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/d8ba3d7443b52c9aa03f06b0.tif"},{"id":95553764,"identity":"e8db122d-ff59-4fb7-9756-04300495efe1","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"docx","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20618,"visible":true,"origin":"","legend":"","description":"","filename":"Table2.docx","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/1794d9fa2d4f8552d106ba27.docx"},{"id":95553783,"identity":"cfce578c-c9f5-4144-a858-e284b29cfd64","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"tif","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29048196,"visible":true,"origin":"","legend":"","description":"","filename":"Figure5.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/12bfee40b5dff26218ccf2a8.tif"},{"id":95654960,"identity":"ac2420a0-4f1c-426f-bca8-2b7a7b4c3bf1","added_by":"auto","created_at":"2025-11-11 16:13:54","extension":"docx","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19709,"visible":true,"origin":"","legend":"","description":"","filename":"Table3.docx","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/baf3fbdc6d143f3b43651543.docx"},{"id":95654932,"identity":"f0cc6e66-8430-4dde-b5e6-2aae910204a4","added_by":"auto","created_at":"2025-11-11 16:13:51","extension":"tif","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14187188,"visible":true,"origin":"","legend":"","description":"","filename":"Figure6.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/53f69901aad997d8d2accb0a.tif"},{"id":95553767,"identity":"48ddee73-f826-4dae-b46f-a7855df1f65f","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"json","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9575,"visible":true,"origin":"","legend":"","description":"","filename":"3dfbf5c0bd6e4b67acaa5ef92f83675d.json","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/f48cb540e76b86ec90899f4f.json"},{"id":95553774,"identity":"04300644-bcdd-45e9-8327-2a31533f9f7d","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"docx","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":463682,"visible":true,"origin":"","legend":"","description":"","filename":"supplymentary.docx","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/e96a0839dde8aa8c89d1f20b.docx"},{"id":95553772,"identity":"0b78ab9e-9dc9-4014-8afd-2d68658f885f","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"xml","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142145,"visible":true,"origin":"","legend":"","description":"","filename":"3dfbf5c0bd6e4b67acaa5ef92f83675d1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/a1afd368bc5e4f6a76f42da1.xml"},{"id":95654655,"identity":"86b3d408-e475-41ca-a7da-98ca94600f48","added_by":"auto","created_at":"2025-11-11 16:12:40","extension":"tif","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":921804,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/13c298323c9a90959e88a236.tif"},{"id":95553799,"identity":"555103fe-1e1b-4bae-843d-43c066075631","added_by":"auto","created_at":"2025-11-10 14:01:25","extension":"tif","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19136660,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/303527f10232d66de87f1143.tif"},{"id":95553797,"identity":"8423372a-444b-4251-8819-033aeeb2a08c","added_by":"auto","created_at":"2025-11-10 14:01:25","extension":"tif","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19881664,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/e07cfc8626a8b021857be1e6.tif"},{"id":95655314,"identity":"0f199df4-9c28-4244-bf6b-e93b6c0e062e","added_by":"auto","created_at":"2025-11-11 16:15:19","extension":"tif","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8277392,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/9e7d2199d147aeeeb2dc5ae2.tif"},{"id":95654454,"identity":"fd9e7cce-6197-4db2-ad37-9ea851c6e510","added_by":"auto","created_at":"2025-11-11 16:12:03","extension":"tif","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29048196,"visible":true,"origin":"","legend":"","description":"","filename":"Figure5.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/8a3f3d533e8a21a91e8dcbb1.tif"},{"id":95553786,"identity":"d6da24e3-741b-46e5-8725-385182f80d8c","added_by":"auto","created_at":"2025-11-10 14:01:25","extension":"tif","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14187188,"visible":true,"origin":"","legend":"","description":"","filename":"Figure6.tif","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/c570c55d646b21246855c844.tif"},{"id":95654934,"identity":"2cf3a4fc-4098-498b-8396-e343de9b4c56","added_by":"auto","created_at":"2025-11-11 16:13:51","extension":"jpeg","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1750044,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/66ac47a60354ccfa262e66a2.jpeg"},{"id":95553777,"identity":"8b24a0dd-d057-4cf0-b471-9ecb016b4f7e","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"jpeg","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":921804,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/86e996f9c2419857a15ca76e.jpeg"},{"id":95655293,"identity":"846d87c2-f2fb-47d5-937c-18afe13ec38d","added_by":"auto","created_at":"2025-11-11 16:15:12","extension":"jpeg","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3388690,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/7ce6b4d4dd62176d8197e871.jpeg"},{"id":95553802,"identity":"bc6c84c2-aaa5-4954-89c2-4a09e128d122","added_by":"auto","created_at":"2025-11-10 14:01:25","extension":"jpeg","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19881664,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/f1c83cad18e75497c1668b9d.jpeg"},{"id":95553781,"identity":"41e90fad-22c2-4ef1-939a-595e9ed413be","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"jpeg","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6820792,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/da843bec7e0c2f9ebf567139.jpeg"},{"id":95655317,"identity":"6e0981d7-53b4-4b69-bbcd-975067b65229","added_by":"auto","created_at":"2025-11-11 16:15:20","extension":"jpeg","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2047788,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/b70069f526e0c5bb8f08cb0a.jpeg"},{"id":95654372,"identity":"ccc17c27-dd0b-485b-b9d1-466e0a48e249","added_by":"auto","created_at":"2025-11-11 16:11:23","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":52875,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/182449060e9082db6dfc4f8c.png"},{"id":95553793,"identity":"518dca84-e4cf-4142-ad68-31acf35b3cb7","added_by":"auto","created_at":"2025-11-10 14:01:25","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":143725,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure3.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/0b81c6c30c1b7259b2761b97.png"},{"id":95553789,"identity":"938a9465-4575-43bf-af55-c7ddc03a31b4","added_by":"auto","created_at":"2025-11-10 14:01:25","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":171892,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure4.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/3f85cba350f14a0d70185671.png"},{"id":95553790,"identity":"7004ec85-2467-4439-a305-7b45522cc876","added_by":"auto","created_at":"2025-11-10 14:01:25","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":598783,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/255fc588e795167ee3efbad6.png"},{"id":95654662,"identity":"e058e23b-411a-4d9e-a083-df5d644c0fe1","added_by":"auto","created_at":"2025-11-11 16:12:41","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124054,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure5.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/8cbdd68f3bb55640a069f22b.png"},{"id":95655310,"identity":"4f788431-0a4b-4a92-8735-a05efc03ae07","added_by":"auto","created_at":"2025-11-11 16:15:19","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70872,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure6.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/76f66b09161e583c10e1e943.png"},{"id":95654866,"identity":"47882bb0-13bd-4dcf-b52d-4913c2e660f6","added_by":"auto","created_at":"2025-11-11 16:13:29","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51604,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/39433d5739aaff398bded05e.png"},{"id":95553795,"identity":"ccc1bf02-2e62-42f4-b9e8-fb52e4d90b91","added_by":"auto","created_at":"2025-11-10 14:01:25","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":52875,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/1ca8b8232f6d2288c49d57f7.png"},{"id":95553791,"identity":"4c5704be-1a82-450a-8db7-4e5b03ac12ef","added_by":"auto","created_at":"2025-11-10 14:01:25","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":58463,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/2c24dfc441fa77255ffc2780.png"},{"id":95655498,"identity":"b4884032-16c9-4d80-8e4b-0ee81a94a5e1","added_by":"auto","created_at":"2025-11-11 16:16:20","extension":"png","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":171892,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/d77eab0eb2a7c29e319afbb5.png"},{"id":95553782,"identity":"67389664-2eef-4f8d-9c70-109a209c0c82","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"png","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":57915,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/9ff779807a7f454b7d8fb153.png"},{"id":95553794,"identity":"c556a91f-7a8f-4d86-bc2e-5a1a2d6468a0","added_by":"auto","created_at":"2025-11-10 14:01:25","extension":"png","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24628,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/a18b262646f29afed8f1b7e0.png"},{"id":95655092,"identity":"03abac33-093b-474e-acaa-9479a28268ad","added_by":"auto","created_at":"2025-11-11 16:14:18","extension":"xml","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142434,"visible":true,"origin":"","legend":"","description":"","filename":"3dfbf5c0bd6e4b67acaa5ef92f83675d1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/b7f9da2f7c1b5606708aa661.xml"},{"id":95553788,"identity":"7c9c85a5-fc67-4406-aba2-dc6bd6a2ec40","added_by":"auto","created_at":"2025-11-10 14:01:25","extension":"html","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":150454,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/6ce00b5f86942a932a62579b.html"},{"id":100548125,"identity":"166093d3-0875-48ea-9b95-778d3415410b","added_by":"auto","created_at":"2026-01-19 08:17:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":931222,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1_covered_7a842b8a-e0d1-4fa7-a050-61927c8e34f0.pdf"},{"id":95553765,"identity":"3c9c2ed8-2720-42e1-9012-92fb6d657b19","added_by":"auto","created_at":"2025-11-10 14:01:24","extension":"docx","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":463682,"visible":true,"origin":"","legend":"","description":"","filename":"supplymentary.docx","url":"https://assets-eu.researchsquare.com/files/rs-7911218/v1/a064f62a7c69231ebee56efa.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Development and External Validation of an Interpretable Machine-Learning Model for HFpEF Comorbidity Risk in COPD Patients","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"COPD, HFpEF, Machine Learning, Risk Prediction Model, Comorbidity","lastPublishedDoi":"10.21203/rs.3.rs-7911218/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7911218/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBACKGROUND\u003c/h2\u003e\u003cp\u003eChronic Obstructive Pulmonary Disease (COPD) and Heart Failure with preserved Ejection Fraction (HFpEF) frequently coexist, leading to increased hospitalization, mortality, and healthcare burden. Early identification of HFpEF risk in COPD patients is critical for timely intervention.\u003c/p\u003e\u003ch2\u003eAIM\u003c/h2\u003e\u003cp\u003eTo develop and validate an interpretable machine learning (ML) model for predicting HFpEF risk in COPD patients and to identify key predictors using explainable artificial intelligence techniques.\u003c/p\u003e\u003ch2\u003eMETHODS\u003c/h2\u003e\u003cp\u003eThis retrospective study analyzed 1,550 COPD patients, divided into COPD-only and COPD-HFpEF groups. Feature selection was performed using LASSO regression, logistic regression, and Boruta random forest. Ten ML models were developed and evaluated on an internal test set, with the best model further validated on an external cohort (n\u0026thinsp;=\u0026thinsp;69). Model interpretability was assessed using SHapley Additive exPlanations (SHAP).\u003c/p\u003e\u003ch2\u003eRESULTS\u003c/h2\u003e\u003cp\u003eNine predictors were consistently selected: NT-proBNP, red blood cell count, fibrinogen, cholesterol, arterial PaO₂, inspiratory capacity (IC), IC% predicted, late diastolic mitral inflow velocity, and the COPD Assessment Test score. The XGBoost model achieved the best performance, with an AUC of 0.898 (95% CI: 0.867\u0026ndash;0.929) on the internal test set and 0.851 (95% CI: 0.753\u0026ndash;0.948) on external validation. SHAP analysis identified NT-proBNP as the most influential predictor.\u003c/p\u003e\u003ch2\u003eCONCLUSION\u003c/h2\u003e\u003cp\u003eThe developed XGBoost model accurately predicts HFpEF risk in COPD patients and offers clinically interpretable insights into key risk factors, supporting early identification and stratified management.\u003c/p\u003e","manuscriptTitle":"Development and External Validation of an Interpretable Machine-Learning Model for HFpEF Comorbidity Risk in COPD Patients","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-10 14:01:19","doi":"10.21203/rs.3.rs-7911218/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d90551c3-8646-441b-9797-1aeb6b5f1849","owner":[],"postedDate":"November 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-17T13:09:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-10 14:01:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7911218","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7911218","identity":"rs-7911218","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00