Reducing False Negatives in Gastroesophageal Reflux Disease Diagnosis Through Multi-Feature Anomaly Detection of pH-Impedance Signals

Reducing False Negatives in Gastroesophageal Reflux Disease Diagnosis Through Multi-Feature Anomaly Detection of pH-Impedance Signals | 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 Article Reducing False Negatives in Gastroesophageal Reflux Disease Diagnosis Through Multi-Feature Anomaly Detection of pH-Impedance Signals Songho Lee, Junhyeong Lee, Donggeun Park, Sang Kil Lee, Kyoung G. Lee, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7626070/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract Gastroesophageal reflux disease (GERD) diagnosis traditionally relies on acid exposure time (AET) obtained from 24-h multichannel intraluminal impedance-pH (MII-pH) monitoring. However, such single-metric approaches often fail to capture borderline or transient reflux events, leading to false negatives (FNs) that impede timely and appropriate treatment. To address this limitation, we propose a machine learning-based framework that integrates statistical and waveform-derived features from pH signals to enhance anomaly detection. Using one-class support vector machine and support vector data description models trained on real-world MII-pH datasets, the framework achieved an \(\:{F}_{3}\) score of approximately 0.9 and identified nearly twice as many abnormal cases as the conventional AET criterion. Explainable AI techniques, using Shapley additive explanations values, showed that features such as kurtosis and peak-to-peak amplitude contributed significantly to the identification of subtle reflux patterns. Furthermore, several FN cases that were not detected by AET or the DeMeester score were retrospectively validated through expert review and correlated clinical indicators. This approach significantly improves the detection of potential FN cases overlooked by AET-based methods, thereby contributing to more effective GERD diagnosis and treatment in clinical practice. Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Health sciences/Gastroenterology Health sciences/Health care Health sciences/Medical research Gastroesophageal Reflux Disease (GERD) False Negative (FN) Anomaly Detection (AD) Feature Enhancement Shapley additive explanations (SHAP) Full Text Additional Declarations No competing interests reported. Supplementary Files SI.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 28 Oct, 2025 Reviews received at journal 27 Oct, 2025 Reviews received at journal 27 Oct, 2025 Reviewers agreed at journal 21 Oct, 2025 Reviewers agreed at journal 19 Oct, 2025 Reviews received at journal 17 Oct, 2025 Reviewers agreed at journal 16 Oct, 2025 Reviewers agreed at journal 15 Oct, 2025 Reviewers invited by journal 15 Oct, 2025 Editor assigned by journal 12 Oct, 2025 Submission checks completed at journal 11 Oct, 2025 First submitted to journal 16 Sep, 2025 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-7626070","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":536277654,"identity":"a9a70a2d-4f7d-4d39-9ece-8cfecf9e672d","order_by":0,"name":"Songho Lee","email":"","orcid":"","institution":"Korea Advanced Institute of Science and Technology (KAIST)","correspondingAuthor":false,"prefix":"","firstName":"Songho","middleName":"","lastName":"Lee","suffix":""},{"id":536277655,"identity":"7c186338-1618-44aa-b878-f1ee35740166","order_by":1,"name":"Junhyeong Lee","email":"","orcid":"","institution":"Korea Advanced Institute of Science and Technology (KAIST)","correspondingAuthor":false,"prefix":"","firstName":"Junhyeong","middleName":"","lastName":"Lee","suffix":""},{"id":536277656,"identity":"68ece4c0-c9c7-4013-8473-36a94d4309cb","order_by":2,"name":"Donggeun Park","email":"","orcid":"","institution":"Korea Advanced Institute of Science and Technology (KAIST)","correspondingAuthor":false,"prefix":"","firstName":"Donggeun","middleName":"","lastName":"Park","suffix":""},{"id":536277657,"identity":"9fa938a6-8bae-48c5-8897-410eb47c99bf","order_by":3,"name":"Sang Kil Lee","email":"","orcid":"","institution":"Yonsei University College of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Sang","middleName":"Kil","lastName":"Lee","suffix":""},{"id":536277658,"identity":"e78a8f97-651b-44fa-ad37-1608bc27fa1b","order_by":4,"name":"Kyoung G. Lee","email":"","orcid":"","institution":"National NanoFab Center","correspondingAuthor":false,"prefix":"","firstName":"Kyoung","middleName":"G.","lastName":"Lee","suffix":""},{"id":536277659,"identity":"94cacdd9-a560-4dbf-8877-44007f1a2fec","order_by":5,"name":"Hee Man Kim","email":"","orcid":"","institution":"Yonsei University of College of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Hee","middleName":"Man","lastName":"Kim","suffix":""},{"id":536277660,"identity":"054dd904-eeeb-46b8-8fc6-68c2cf81ce76","order_by":6,"name":"Seunghwa Ryu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYJACZoaKBAY2KMeASC1nQFqYSdHC2JYA1kmcFvMZOcafC+elyfPxnz/A8KOGwdi8gYAWmRs5ZtIzt+UYtkkkMzD2HGMwkzlAQIuERI4ZM++2CsY2CaDDeBsYbCQIOQyoxfgz75wK+zb+wwyMf4nUYiDN25CT2MaQzMAMtMWMsBaeZ2XSPMfSkoF+MTgsc0zCmLAW9uTNn3lqkm3n9x98+PBNjY3hDEJaGAQSEOwDQCMIamBg4D9AhKJRMApGwSgY2QAAjgQydGTk8L0AAAAASUVORK5CYII=","orcid":"","institution":"Korea Advanced Institute of Science and Technology (KAIST)","correspondingAuthor":true,"prefix":"","firstName":"Seunghwa","middleName":"","lastName":"Ryu","suffix":""}],"badges":[],"createdAt":"2025-09-16 05:23:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7626070/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7626070/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94748651,"identity":"0a5df23d-77e0-42af-b69b-897d7b688af6","added_by":"auto","created_at":"2025-10-30 10:03:19","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3133359,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptrevisedclean.docx","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/88ce93c3badbbce0ca88a218.docx"},{"id":94823882,"identity":"0eb619aa-7cee-4876-aa35-f0b10846e785","added_by":"auto","created_at":"2025-10-31 06:48:13","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8895,"visible":true,"origin":"","legend":"","description":"","filename":"a9c07afdccf845f0b499ff8a69b8e749.json","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/96c1c95c526e2b20008fbd53.json"},{"id":94824177,"identity":"7f44edf6-380b-40cb-ba1c-a6d366691278","added_by":"auto","created_at":"2025-10-31 06:48:36","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1814930,"visible":true,"origin":"","legend":"","description":"","filename":"SI.docx","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/2502812ca324313d89e514a2.docx"},{"id":94823128,"identity":"a61dd75d-ef5b-4891-bdbd-6b9f7ec5e800","added_by":"auto","created_at":"2025-10-31 06:46:15","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":116736,"visible":true,"origin":"","legend":"","description":"","filename":"a9c07afdccf845f0b499ff8a69b8e7491enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/f39d09c75e438d314e8fb353.xml"},{"id":94748639,"identity":"5d3aca81-dc9f-4cbc-96ed-cf4a48d679e7","added_by":"auto","created_at":"2025-10-30 10:03:19","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":96278,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/3e08981680d298228a8c6b24.png"},{"id":94823968,"identity":"ef1e947e-893b-45fc-b092-9bfa4d88df82","added_by":"auto","created_at":"2025-10-31 06:48:20","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":123588,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/c2afdaa0aee8331c60bbb583.png"},{"id":94823015,"identity":"304ceab5-f7bf-4d8c-b82b-0a2b252e58fa","added_by":"auto","created_at":"2025-10-31 06:45:48","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94390,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/798e25f212218512821187c8.png"},{"id":94748649,"identity":"568cdebd-b793-4159-babe-fc88b37e2c56","added_by":"auto","created_at":"2025-10-30 10:03:19","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":120215,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/c98fdd03e0872a13ce386a59.png"},{"id":94748644,"identity":"8f7506e8-1739-4793-852e-cb1d049b9c9e","added_by":"auto","created_at":"2025-10-30 10:03:19","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":108186,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/0fd3fa2dbd02068ed5c358db.png"},{"id":94748641,"identity":"19c42c23-a48f-4d26-b77d-ec38e0d8fe78","added_by":"auto","created_at":"2025-10-30 10:03:19","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":66276,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/ca01c65bfeb716605c8e7518.png"},{"id":94748650,"identity":"f1a2c1d6-826e-4e79-bbf0-531c1b430117","added_by":"auto","created_at":"2025-10-30 10:03:19","extension":"xml","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":115376,"visible":true,"origin":"","legend":"","description":"","filename":"a9c07afdccf845f0b499ff8a69b8e7491structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/1c44f770012037afff606757.xml"},{"id":94748647,"identity":"3814315b-5459-4bdd-8043-60d8f44eb974","added_by":"auto","created_at":"2025-10-30 10:03:19","extension":"html","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":135501,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/469cb48596f786b8e6b21bf9.html"},{"id":94827285,"identity":"296b49c6-7e3d-4964-9c0f-5faeec91a41b","added_by":"auto","created_at":"2025-10-31 06:56:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1860844,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptrevisedclean.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1_covered_46acebee-ea39-4aaf-bbdb-58fa7879b965.pdf"},{"id":94824131,"identity":"4ac65660-7a8c-4129-a1e8-87c3498bfca8","added_by":"auto","created_at":"2025-10-31 06:48:31","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":1814930,"visible":true,"origin":"","legend":"","description":"","filename":"SI.docx","url":"https://assets-eu.researchsquare.com/files/rs-7626070/v1/ffe247b2882a92afee18b643.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Reducing False Negatives in Gastroesophageal Reflux Disease Diagnosis Through Multi-Feature Anomaly Detection of pH-Impedance Signals","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Gastroesophageal Reflux Disease (GERD), False Negative (FN), Anomaly Detection (AD), Feature Enhancement, Shapley additive explanations (SHAP)","lastPublishedDoi":"10.21203/rs.3.rs-7626070/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7626070/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eGastroesophageal reflux disease (GERD) diagnosis traditionally relies on acid exposure time (AET) obtained from 24-h multichannel intraluminal impedance-pH (MII-pH) monitoring. However, such single-metric approaches often fail to capture borderline or transient reflux events, leading to false negatives (FNs) that impede timely and appropriate treatment. To address this limitation, we propose a machine learning-based framework that integrates statistical and waveform-derived features from pH signals to enhance anomaly detection. Using one-class support vector machine and support vector data description models trained on real-world MII-pH datasets, the framework achieved an \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{F}_{3}\\)\u003c/span\u003e\u003c/span\u003e score of approximately 0.9 and identified nearly twice as many abnormal cases as the conventional AET criterion. Explainable AI techniques, using Shapley additive explanations values, showed that features such as kurtosis and peak-to-peak amplitude contributed significantly to the identification of subtle reflux patterns. Furthermore, several FN cases that were not detected by AET or the DeMeester score were retrospectively validated through expert review and correlated clinical indicators. This approach significantly improves the detection of potential FN cases overlooked by AET-based methods, thereby contributing to more effective GERD diagnosis and treatment in clinical practice.\u003c/p\u003e","manuscriptTitle":"Reducing False Negatives in Gastroesophageal Reflux Disease Diagnosis Through Multi-Feature Anomaly Detection of pH-Impedance Signals","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-30 10:03:14","doi":"10.21203/rs.3.rs-7626070/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-28T13:53:35+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-27T08:44:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-27T07:10:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"286501178486569193185588799947724923422","date":"2025-10-22T03:21:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"159245560341479706547712506600156957746","date":"2025-10-19T07:26:10+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-17T18:03:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"199441776570669265609370551307775485071","date":"2025-10-16T21:46:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"207126738065602744335150485638122929847","date":"2025-10-16T03:52:13+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-16T03:47:53+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-12T23:56:41+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-11T08:35:49+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Medicine","date":"2025-09-16T05:12:41+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"5e9f9735-7cf8-4868-a91c-c993362f1fbc","owner":[],"postedDate":"October 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":57013823,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":57013824,"name":"Health sciences/Diseases"},{"id":57013825,"name":"Health sciences/Gastroenterology"},{"id":57013826,"name":"Health sciences/Health care"},{"id":57013827,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-05-15T16:08:30+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-30 10:03:14","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7626070","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7626070","identity":"rs-7626070","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}