Explainable AI for Maternal Health Risk Prediction in Bangladesh: A Hybrid Fuzzy-XGBoost Framework with Clinician Validation

Explainable AI for Maternal Health Risk Prediction in Bangladesh: A Hybrid Fuzzy-XGBoost Framework with Clinician Validation | 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 Explainable AI for Maternal Health Risk Prediction in Bangladesh: A Hybrid Fuzzy-XGBoost Framework with Clinician Validation Farjana Yesmin, Nusrat Shirmin, Suraiya Shabnam Bristy This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8584734/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 Bangladesh faces a maternal mortality ratio of 156 per 100,000 live births, with 2,459 maternal deaths reported in 2022. While machine learning shows promise in risk prediction, black-box models limit clinical adoption in resource-constrained settings where explainability is crucial. This study develops a hybrid fuzzy-XGBoost framework combining ante-hoc fuzzy logic interpretability with post-hoc SHAP explanations, validated through clinician feedback. We trained the model on 1,014 maternal health records with clinical parameters (age, blood pressure, blood sugar) augmented with synthetic regional features based on Bangladesh health data. The hybrid model achieved 88.67% accuracy with ROC-AUC of 0.9703, outperforming the best baseline (Gradient Boosting: 86.21%) by 2.46 percentage points. SHAP analysis identified healthcare access score (most important), blood sugar, and fuzzy risk score as primary predictors. Clinician validation (N=14) showed strong preference for hybrid explanations (71.4% across cases) with 54.8% expressing trust in clinical practice. Fairness analysis revealed equitable performance across regions (σ=0.0766), with better accuracy in underserved areas (r=-0.876 correlation with healthcare access), highlighting potential to address disparities. Maternal & Fetal Medicine Health Economics & Outcomes Research Computer Architecture and Engineering Explainable AI Maternal Health Fuzzy Logic Clinical Decision Support Healthcare Fairness Bangladesh Full Text Additional Declarations The authors declare no competing interests. Supplementary Files ExplainabilityEvaluationforMaternalHealthAISystemResponsesFormResponses1.csv ExplainabilityEvaluationforMaternalHealthAISystemResponses.xlsx ExplainabilityEvaluationforMaternalHealthAISystemResponsesFormResponses1.csv finalfuzzyxgboostmodel.json maternalhealth.py resultssummary.csv modelcomparisonresults.csv 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-8584734","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":573475290,"identity":"42fd0fb8-4e32-464e-89a4-03357125bb93","order_by":0,"name":"Farjana Yesmin","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0003-0650-5133","institution":"Independent Researcher","correspondingAuthor":true,"prefix":"","firstName":"Farjana","middleName":"","lastName":"Yesmin","suffix":""},{"id":573475419,"identity":"2613b20c-a43f-4b40-b27b-9e984159d887","order_by":1,"name":"Nusrat Shirmin","email":"","orcid":"https://orcid.org/0009-0003-7620-1204","institution":"Independent Researcher","correspondingAuthor":false,"prefix":"","firstName":"Nusrat","middleName":"","lastName":"Shirmin","suffix":""},{"id":573475420,"identity":"1ba6712e-8775-4362-9e0a-8f219adfc4a3","order_by":2,"name":"Suraiya Shabnam Bristy","email":"","orcid":"https://orcid.org/0009-0007-7707-156X","institution":"Medical Officer, Sonargaon Sheba General Hospital, Narayanganj, Bangladesh","correspondingAuthor":false,"prefix":"","firstName":"Suraiya","middleName":"Shabnam","lastName":"Bristy","suffix":""}],"badges":[],"createdAt":"2026-01-12 18:44:28","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8584734/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8584734/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100382688,"identity":"29deccc1-29c9-4dd5-8518-d85611f01a41","added_by":"auto","created_at":"2026-01-16 10:43:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2480962,"visible":true,"origin":"","legend":"","description":"","filename":"ICAIHE2026.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8584734/v1_covered_00647f36-1de1-4f2a-a71f-ff58aaff5909.pdf"},{"id":100227388,"identity":"91fcd426-d81c-44d1-aed4-df6f60ef79ac","added_by":"auto","created_at":"2026-01-14 10:48:42","extension":"csv","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":7373,"visible":true,"origin":"","legend":"","description":"","filename":"ExplainabilityEvaluationforMaternalHealthAISystemResponsesFormResponses1.csv","url":"https://assets-eu.researchsquare.com/files/rs-8584734/v1/97c714be4e7f7c87f7c80955.csv"},{"id":100227390,"identity":"ee21ae3d-f9a2-4544-8b55-6a4274ed81cf","added_by":"auto","created_at":"2026-01-14 10:48:42","extension":"xlsx","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":8927,"visible":true,"origin":"","legend":"","description":"","filename":"ExplainabilityEvaluationforMaternalHealthAISystemResponses.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-8584734/v1/c87af2daaa80dd1e8eb1fd37.xlsx"},{"id":100227389,"identity":"d21330d5-b869-49a4-96ab-79b2388935e5","added_by":"auto","created_at":"2026-01-14 10:48:42","extension":"csv","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":7373,"visible":true,"origin":"","legend":"","description":"","filename":"ExplainabilityEvaluationforMaternalHealthAISystemResponsesFormResponses1.csv","url":"https://assets-eu.researchsquare.com/files/rs-8584734/v1/b5f8b56c2559840c5c99fd1f.csv"},{"id":100227394,"identity":"dbb51db4-2662-484d-b306-48e7be2f7b89","added_by":"auto","created_at":"2026-01-14 10:48:42","extension":"json","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":1595429,"visible":true,"origin":"","legend":"","description":"","filename":"finalfuzzyxgboostmodel.json","url":"https://assets-eu.researchsquare.com/files/rs-8584734/v1/9226127b57ead3c16e8f05a4.json"},{"id":100227391,"identity":"e3a04d05-9cf6-4e91-a16a-abf401c9c712","added_by":"auto","created_at":"2026-01-14 10:48:42","extension":"py","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":41784,"visible":true,"origin":"","legend":"","description":"","filename":"maternalhealth.py","url":"https://assets-eu.researchsquare.com/files/rs-8584734/v1/5edf07a8b63780c976112318.py"},{"id":100227392,"identity":"2ef50735-d7f5-4775-990a-7121969f53c1","added_by":"auto","created_at":"2026-01-14 10:48:42","extension":"csv","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":356,"visible":true,"origin":"","legend":"","description":"","filename":"resultssummary.csv","url":"https://assets-eu.researchsquare.com/files/rs-8584734/v1/712004a761b666406f5e6179.csv"},{"id":100370043,"identity":"7a515f42-91a7-4bcb-9210-b52bdaa05dbf","added_by":"auto","created_at":"2026-01-16 07:59:51","extension":"csv","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":405,"visible":true,"origin":"","legend":"","description":"","filename":"modelcomparisonresults.csv","url":"https://assets-eu.researchsquare.com/files/rs-8584734/v1/d4bd5ea14f3165bb066d50aa.csv"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eExplainable AI for Maternal Health Risk Prediction in Bangladesh: A Hybrid Fuzzy-XGBoost Framework with Clinician Validation\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Independent research ","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":"Explainable AI, Maternal Health, Fuzzy Logic, Clinical Decision Support, Healthcare Fairness, Bangladesh","lastPublishedDoi":"10.21203/rs.3.rs-8584734/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8584734/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBangladesh faces a maternal mortality ratio of 156 per 100,000 live births, with 2,459 maternal deaths reported in 2022. While machine learning shows promise in risk prediction, black-box models limit clinical adoption in resource-constrained settings where explainability is crucial. This study develops a hybrid fuzzy-XGBoost framework combining ante-hoc fuzzy logic interpretability with post-hoc SHAP explanations, validated through clinician feedback. We trained the model on 1,014 maternal health records with clinical parameters (age, blood pressure, blood sugar) augmented with synthetic regional features based on Bangladesh health data. The hybrid model achieved 88.67% accuracy with ROC-AUC of 0.9703, outperforming the best baseline (Gradient Boosting: 86.21%) by 2.46 percentage points. SHAP analysis identified healthcare access score (most important), blood sugar, and fuzzy risk score as primary predictors. Clinician validation (N=14) showed strong preference for hybrid explanations (71.4% across cases) with 54.8% expressing trust in clinical practice. Fairness analysis revealed equitable performance across regions (σ=0.0766), with better accuracy in underserved areas (r=-0.876 correlation with healthcare access), highlighting potential to address disparities.\u003c/p\u003e","manuscriptTitle":"Explainable AI for Maternal Health Risk Prediction in Bangladesh: A Hybrid Fuzzy-XGBoost Framework with Clinician Validation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-14 10:48:38","doi":"10.21203/rs.3.rs-8584734/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":"c0ae2c07-bead-4d62-a5b5-664e24bd1114","owner":[],"postedDate":"January 14th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":61019954,"name":"Maternal \u0026 Fetal Medicine"},{"id":61019955,"name":"Health Economics \u0026 Outcomes Research"},{"id":61019956,"name":"Computer Architecture and Engineering"}],"tags":[],"updatedAt":"2026-01-14T10:48:38+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-14 10:48:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8584734","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8584734","identity":"rs-8584734","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}