Unveiling Population Heterogeneity in Health Risks Posed by Environmental Hazards Using Regression- Guided Neural Network

Unveiling Population Heterogeneity in Health Risks Posed by Environmental Hazards Using Regression- Guided Neural Network | 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 Unveiling Population Heterogeneity in Health Risks Posed by Environmental Hazards Using Regression- Guided Neural Network Jong Woo Nam, Eun Young Choi, Jennifer A. Ailshire, Yao-yi Chiang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8066259/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract As environmental hazards become more frequent, it is critically important to understand their health impacts and identify individuals at disproportionately higher risk. Moderated Multiple Regression (MMR) provides a straightforward approach for investigating population heterogeneity by incorporating interaction terms between hazard exposure and population characteristics into a regression model. However, when vulnerabilities are embedded within complex, high-dimensional covariate spaces, MMR often fails to adequately model complex population heterogeneity. Here, we introduce a hybrid method, Regression-Guided Neural Networks (ReGNN), which integrates the flexibility of artificial neural networks (ANNs) within the structural form of a regression model. Briefly, ReGNN embeds an ANN inside a regression equation to generate a latent representation that nonlinearly combines potential sources of heterogeneity and moderates the effect of an environmental hazard. Because the outer layer maintains a regression structure, the interpretability of standard regression analysis is preserved. Through extensive simulation studies, we demonstrate ReGNN’s effectiveness in modeling complex heterogeneous effects. We further illustrate its utility by applying it to investigate population heterogeneity in the health impacts of air pollution (PM2.5) on cognitive functioning scores. By comparing ReGNN’s results with those from traditional MMR models, we show that ReGNN can uncover patterns of heterogeneity that would otherwise remain hidden. Earth and environmental sciences/Environmental sciences Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 05 Jan, 2026 Reviews received at journal 05 Jan, 2026 Reviews received at journal 27 Dec, 2025 Reviewers agreed at journal 23 Dec, 2025 Reviewers agreed at journal 20 Dec, 2025 Reviewers agreed at journal 03 Dec, 2025 Reviewers invited by journal 18 Nov, 2025 Editor invited by journal 13 Nov, 2025 Editor assigned by journal 10 Nov, 2025 Submission checks completed at journal 10 Nov, 2025 First submitted to journal 08 Nov, 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-8066259","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":563645588,"identity":"fb03763f-c5a4-4834-a8b8-3a9f03dd8904","order_by":0,"name":"Jong Woo Nam","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAmklEQVRIiWNgGAWjYJACgw9QmngthjNI1sLMQ5IWc/bTCcW2bXXyDOzN2ySI0mLZk7vBOLftsGEDz7Ey4rQYHABrOZDAIJFjRqSW8283GFu21SUwyL8hVssNoC2MbcxAW3iI1vJ2g2HPucOGbTxpxRZEOix3m8GPsjp5fvbDG28QpQUI2MDxwUaschBgfkCK6lEwCkbBKBiBAADpcyo8reZ+MQAAAABJRU5ErkJggg==","orcid":"","institution":"University of Southern California","correspondingAuthor":true,"prefix":"","firstName":"Jong","middleName":"Woo","lastName":"Nam","suffix":""},{"id":563645605,"identity":"35539882-8596-43a8-b0ec-c13a36ce8141","order_by":1,"name":"Eun Young Choi","email":"","orcid":"","institution":"University of Southern California","correspondingAuthor":false,"prefix":"","firstName":"Eun","middleName":"Young","lastName":"Choi","suffix":""},{"id":563645606,"identity":"2bd53596-aff0-4b17-91b3-2a0524630a38","order_by":2,"name":"Jennifer A. Ailshire","email":"","orcid":"","institution":"University of Southern California","correspondingAuthor":false,"prefix":"","firstName":"Jennifer","middleName":"A.","lastName":"Ailshire","suffix":""},{"id":563645607,"identity":"fbb35cff-b47f-476f-bf91-25bf1e29d16a","order_by":3,"name":"Yao-yi Chiang","email":"","orcid":"","institution":"University of Minnesota","correspondingAuthor":false,"prefix":"","firstName":"Yao-yi","middleName":"","lastName":"Chiang","suffix":""}],"badges":[],"createdAt":"2025-11-08 22:38:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8066259/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8066259/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98771189,"identity":"9a497ca4-7f15-4367-9aa0-4b0c5013294e","added_by":"auto","created_at":"2025-12-22 10:40:20","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2426956,"visible":true,"origin":"","legend":"","description":"","filename":"mainfinal2025revised.docx","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/48fa3379db560b0875a5157f.docx"},{"id":98771185,"identity":"ddce989c-c1bb-4e29-a541-28806459c9ac","added_by":"auto","created_at":"2025-12-22 10:40:20","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6670,"visible":true,"origin":"","legend":"","description":"","filename":"7e231f23792243acbbfd0b5fbe0c80ab.json","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/7e8ef7c6b673a047d58bc46b.json"},{"id":98779527,"identity":"5ad120b5-1f8b-45cb-98ab-de92f236d009","added_by":"auto","created_at":"2025-12-22 12:30:26","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":129247,"visible":true,"origin":"","legend":"","description":"","filename":"7e231f23792243acbbfd0b5fbe0c80ab1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/425fddc5ecb9c5f9f13b32ff.xml"},{"id":98780681,"identity":"5405a4d2-e3c3-46ed-a83e-f9eff56b5a17","added_by":"auto","created_at":"2025-12-22 12:31:33","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":286369,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/0fa83dd53fcc0e4eb70e5dda.png"},{"id":98771186,"identity":"e1ca7d58-826a-4132-97a4-ec002bd106ad","added_by":"auto","created_at":"2025-12-22 10:40:20","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":339415,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/3c20ed0641949b6eee6fe3b8.png"},{"id":98780707,"identity":"b2d5a03b-a713-4b8a-b618-f4f271506376","added_by":"auto","created_at":"2025-12-22 12:31:34","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":168639,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/763dc6116fafdadad30fcd0e.png"},{"id":98771191,"identity":"dce0a6eb-258d-4389-acd5-f78e1537124c","added_by":"auto","created_at":"2025-12-22 10:40:20","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":164644,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/cf26081873eccee42fc12d0a.png"},{"id":98771192,"identity":"5d7f1a1f-26fc-4ad1-98a4-aa411c1c2f75","added_by":"auto","created_at":"2025-12-22 10:40:20","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":327829,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/2b89772e2ea47a26fd3330b7.png"},{"id":98780490,"identity":"3c793c90-bdf1-450f-b4d7-2b102d0cc06d","added_by":"auto","created_at":"2025-12-22 12:31:23","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146821,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/7440f2870243c0b6716d542a.png"},{"id":98771194,"identity":"459100dd-65d2-4c82-a4a6-9c0d60bec89c","added_by":"auto","created_at":"2025-12-22 10:40:20","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":763473,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/02fa2a3ea42d5ab75fd0d07e.png"},{"id":98771196,"identity":"fb4c7816-7aa4-4beb-8a06-ee030e24478b","added_by":"auto","created_at":"2025-12-22 10:40:20","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":121014,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/22b975f17bb1e53250896b29.png"},{"id":98780948,"identity":"9c5b3803-fae2-40ce-85da-a9f6c72b05b6","added_by":"auto","created_at":"2025-12-22 12:31:51","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45712,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/759310f5b718137d94ca8d2b.png"},{"id":98780543,"identity":"bcbab68e-d336-4f48-bcc4-9d6b54aaaa9a","added_by":"auto","created_at":"2025-12-22 12:31:28","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70200,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/c1fff54e6689d471b4b30504.png"},{"id":98780603,"identity":"9892fa8d-1215-40ab-92f8-e6bf5193c1a5","added_by":"auto","created_at":"2025-12-22 12:31:30","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34214,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/fbbeeb5b5254181dc32db5dd.png"},{"id":98771198,"identity":"23563f6b-020e-4bb3-ba75-ecd4f8219121","added_by":"auto","created_at":"2025-12-22 10:40:20","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36631,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/d67a9579ee07be4af6ff55d7.png"},{"id":98771201,"identity":"19ef6604-842a-44ba-b9da-d23cc682b62e","added_by":"auto","created_at":"2025-12-22 10:40:20","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":60098,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/ca37c40d4c551cf860cc01aa.png"},{"id":98780929,"identity":"fd1864b4-0a1d-462c-a977-2943f5a439cd","added_by":"auto","created_at":"2025-12-22 12:31:50","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28563,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/ca684256a21cc6f93b58710b.png"},{"id":98780694,"identity":"68c441b7-f3a2-4ff6-bafa-5b1b0cc4f5c9","added_by":"auto","created_at":"2025-12-22 12:31:34","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":105955,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/fc907c83f0ee9e57c4f5b5ee.png"},{"id":98779461,"identity":"3f6399a7-c192-42ae-b50c-16a2602b3df7","added_by":"auto","created_at":"2025-12-22 12:30:22","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30459,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/ff089e38a32f9c041e8b8473.png"},{"id":98771203,"identity":"2c77e717-adb0-46b2-a428-677bd87ec24a","added_by":"auto","created_at":"2025-12-22 10:40:20","extension":"xml","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":127170,"visible":true,"origin":"","legend":"","description":"","filename":"7e231f23792243acbbfd0b5fbe0c80ab1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/17a2c0b47503c69e31e1bbd5.xml"},{"id":98771206,"identity":"a93cebeb-9db2-4640-9ec7-1de05ecb8b2b","added_by":"auto","created_at":"2025-12-22 10:40:20","extension":"html","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":150317,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1/cabec6725e1b42164c3b7944.html"},{"id":98784103,"identity":"87d4ca0e-d12f-4645-8dd4-c19aa2020a88","added_by":"auto","created_at":"2025-12-22 12:42:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1218923,"visible":true,"origin":"","legend":"","description":"","filename":"mainfinal2025revised.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8066259/v1_covered_76ca3eaf-b24c-4f29-b9d6-d330b6d9e55d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Unveiling Population Heterogeneity in Health Risks Posed by Environmental Hazards Using Regression- Guided Neural Network","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8066259/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8066259/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAs environmental hazards become more frequent, it is critically important to understand their health impacts and identify individuals at disproportionately higher risk. Moderated Multiple Regression (MMR) provides a straightforward approach for investigating population heterogeneity by incorporating interaction terms between hazard exposure and population characteristics into a regression model. However, when vulnerabilities are embedded within complex, high-dimensional covariate spaces, MMR often fails to adequately model complex population heterogeneity. Here, we introduce a hybrid method, Regression-Guided Neural Networks (ReGNN), which integrates the flexibility of artificial neural networks (ANNs) within the structural form of a regression model. Briefly, ReGNN embeds an ANN inside a regression equation to generate a latent representation that nonlinearly combines potential sources of heterogeneity and moderates the effect of an environmental hazard. Because the outer layer maintains a regression structure, the interpretability of standard regression analysis is preserved. Through extensive simulation studies, we demonstrate ReGNN\u0026rsquo;s effectiveness in modeling complex heterogeneous effects. We further illustrate its utility by applying it to investigate population heterogeneity in the health impacts of air pollution (PM2.5) on cognitive functioning scores. By comparing ReGNN\u0026rsquo;s results with those from traditional MMR models, we show that ReGNN can uncover patterns of heterogeneity that would otherwise remain hidden.\u003c/p\u003e","manuscriptTitle":"Unveiling Population Heterogeneity in Health Risks Posed by Environmental Hazards Using Regression- Guided Neural Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-22 10:40:15","doi":"10.21203/rs.3.rs-8066259/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-05T11:41:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-05T08:58:57+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-27T05:19:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"201208198647716371275416637905948235149","date":"2025-12-23T05:54:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"109906908576413827995774083409564545678","date":"2025-12-20T06:02:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"179985236109385604263237401897114098982","date":"2025-12-03T20:25:03+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-18T15:48:42+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-11-13T05:03:10+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-11T01:56:33+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-11T01:55:53+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-11-08T22:29:26+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6e90fd06-e5ef-4c94-8afa-3f43a0a4c03c","owner":[],"postedDate":"December 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":60019932,"name":"Earth and environmental sciences/Environmental sciences"},{"id":60019933,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-18T19:54:47+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-22 10:40:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8066259","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8066259","identity":"rs-8066259","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}