Spatial Machine Learning Models to Predict Healthcare Decision Making Autonomy among Women in Sub-Saharan Africa: A DHS-Based Study

Spatial Machine Learning Models to Predict Healthcare Decision Making Autonomy among Women in Sub-Saharan Africa: A DHS-Based Study | 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 Spatial Machine Learning Models to Predict Healthcare Decision Making Autonomy among Women in Sub-Saharan Africa: A DHS-Based Study Henok Addisu, Lakew Asmare, Fetlewerk Gubena This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9356902/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: Women’s healthcare decision-making autonomy is a global burden, with nearly half of them unable to make decisions about sexual relationships and contraceptive use. The problem was more severe in low- and middle-income countries especially in Sub-Saharan Africa. A lack of autonomy in healthcare decision-making increases maternal mortality and morbidity; and lowers child survival rates. This study aimed to predict women’s healthcare decision-making autonomy and identify top predictors via a spatial machine learning algorithm. Methods: Community-based cross-sectional study including 205,684 weighted samples from eighteen selected sub -Saharan African countries from the Demographic and Health Surveys of 2016 to 2023 was conducted. The outcome variable was women’s healthcare decision-making autonomy categorized as autonomous or nonautonomous. The data were managed, and multiple machine learning algorithms were developed via Python version 3.11 on Google Colab. Models were evaluated via metrics such as the area under the curve (AUC), accuracy, recall, precision and F1-score, and SHapley Additive exPlanation analysis was performed to identify key predictors. Results were presented using figures, tables and texts. Results: Nearly one-third of Sub-Saharan African women had no decision-making autonomy regarding their healthcare. The spatial extreme gradient boosting model was found to perform better. Having occupation, being old in age, attending secondary or higher education, having higher household income, opposing the justification of beating, the absence of distance-related barriers to healthcare and being single increased the likelihood of the model being able to predict autonomous class. Conclusion and recommendation: Our study suggested that ML algorithms, specifically the spatial XGBoost model, show promise for predicting women’s healthcare decision-making autonomy. World health organizations, in collaboration with the governments of sub- Saharan African countries; Burkina Faso, Senegal and Cot- devourshould invest in economic empowerment, and community education to address harmful social norms and awareness gaps. Future researchers should also conduct qualitative and longitudinal research to understand the in-depth scenario. Women’s healthcare decision sub-Saharan-Africa spatial machine learning Full Text Additional Declarations No competing interests reported. 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-9356902","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":619644676,"identity":"62b9a60a-06ae-455f-8d06-f9086c453675","order_by":0,"name":"Henok Addisu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+ElEQVRIiWNgGAWjYBACAyBmbGBg5mFgYD5w4AOQx8ZOvBa2xIMzQFqYidQCpHiMD/OAhAhpMWfvPfhwRo21jPyMBIPDNr+2yfMxMzB++JiDW4tlz7lkww3H0nkMbiQkHM7tu23YxszALDlzGx6H3cgxk3zAdpjHQCLhwOHcntuMQC1szLz4tNx/A9Ty7zCP/IzEhsOWPbftCWu5wWMmubEN6PEbyQyHGX7cTiSs5UyOseHMPqBfzjxjONjbcDu5jZmxGb9fjp8xfNjzzdpevj3/84cff27bzm9vPvjhIx4tqICxDUw2EKseBP6QongUjIJRMApGCgAAPaFVV6kD1KsAAAAASUVORK5CYII=","orcid":"","institution":"University of Gondar","correspondingAuthor":true,"prefix":"","firstName":"Henok","middleName":"","lastName":"Addisu","suffix":""},{"id":619644677,"identity":"851103e4-0c1d-45ec-a111-937e1989695e","order_by":1,"name":"Lakew Asmare","email":"","orcid":"","institution":"University of Gondar","correspondingAuthor":false,"prefix":"","firstName":"Lakew","middleName":"","lastName":"Asmare","suffix":""},{"id":619644678,"identity":"d7a7b559-2547-4566-87f5-952ad6dade20","order_by":2,"name":"Fetlewerk Gubena","email":"","orcid":"","institution":"University of Gondar","correspondingAuthor":false,"prefix":"","firstName":"Fetlewerk","middleName":"","lastName":"Gubena","suffix":""}],"badges":[],"createdAt":"2026-04-08 12:23:38","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-9356902/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9356902/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108803456,"identity":"d19764bb-05d5-41e3-8211-a0594c1d376a","added_by":"auto","created_at":"2026-05-08 14:55:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1226120,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptHenok.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9356902/v1_covered_f30acd4d-84de-4f70-bd68-86ccfe4ed277.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Spatial Machine Learning Models to Predict Healthcare Decision Making Autonomy among Women in Sub-Saharan Africa: A DHS-Based Study","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"Women’s healthcare decision, sub-Saharan-Africa, spatial machine learning","lastPublishedDoi":"10.21203/rs.3.rs-9356902/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9356902/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBackground: Women’s healthcare decision-making autonomy is a global burden, with nearly half of them unable to make decisions about sexual relationships and contraceptive use. The problem was more severe in low- and middle-income countries especially in Sub-Saharan Africa. A lack of autonomy in healthcare decision-making increases maternal mortality and morbidity; and lowers child survival rates. This study aimed to predict women’s healthcare decision-making autonomy and identify top predictors via a spatial machine learning algorithm.\u003c/p\u003e\n\u003cp\u003eMethods:\u003cstrong\u003e \u003c/strong\u003eCommunity-based cross-sectional study including 205,684 weighted samples from eighteen selected sub -Saharan African countries from the Demographic and Health Surveys of 2016 to 2023 was conducted. The outcome variable was women’s healthcare decision-making autonomy categorized as autonomous or nonautonomous. The data were managed, and multiple machine learning algorithms were developed via Python version 3.11 on Google Colab. Models were evaluated via metrics such as the area under the curve (AUC), accuracy, recall, precision and F1-score, and SHapley Additive exPlanation analysis was performed to identify key predictors. Results were presented using figures, tables and texts.\u003c/p\u003e\n\u003cp\u003eResults: Nearly one-third of Sub-Saharan African women had no decision-making autonomy regarding their healthcare. The spatial extreme gradient boosting model was found to perform better. Having occupation, being old in age, attending secondary or higher education, having higher household income, opposing the justification of beating, the absence of distance-related barriers to healthcare and being single increased the likelihood of the model being able to predict autonomous class.\u003c/p\u003e\n\u003cp\u003eConclusion and recommendation:\u003cstrong\u003e \u003c/strong\u003eOur study suggested that ML algorithms, specifically the spatial XGBoost model, show promise for predicting women’s healthcare decision-making autonomy. World health organizations, in collaboration with the governments of sub- Saharan African countries; Burkina Faso, Senegal and Cot- devourshould invest in economic empowerment, and community education to address harmful social norms and awareness gaps. Future researchers should also conduct qualitative and longitudinal research to understand the in-depth scenario.\u003c/p\u003e","manuscriptTitle":"Spatial Machine Learning Models to Predict Healthcare Decision Making Autonomy among Women in Sub-Saharan Africa: A DHS-Based Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-09 16:57:06","doi":"10.21203/rs.3.rs-9356902/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":"82c67ba7-5691-4cab-ba38-68e45a19710b","owner":[],"postedDate":"April 9th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-27T22:08:51+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-09 16:57:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9356902","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9356902","identity":"rs-9356902","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}