Rethinking Hyperparameter Optimization for Efficient and Explainable Machine Learning in Civic Health Decision-Making: Empirical Evidence from Malaria Diagnosis

Rethinking Hyperparameter Optimization for Efficient and Explainable Machine Learning in Civic Health Decision-Making: Empirical Evidence from Malaria Diagnosis | 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 Rethinking Hyperparameter Optimization for Efficient and Explainable Machine Learning in Civic Health Decision-Making: Empirical Evidence from Malaria Diagnosis Olushina Olawale Awe, Julia Soares de Souza, Anderson Kaue Bittencourt Cruz, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9172580/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Background: Malaria remains one of the most persistent infectious diseases worldwide, with hundreds of millions of cases annually. Machine learning has emerged as a promising tool for malaria diagnosis, but the practical deployment of these models is constrained by hyperparameter optimization complexity. This study provides a comprehensive comparison of stochastic and deterministic hyper-parameter optimization strategies for supervised machine learning models applied to malaria diagnosis. Methods: We evaluated five optimization strategies (Grid Search, Random Search, Bayesian Optimization, Genetic Algorithms, and Hyperband Racing) across six supervised learning algorithms (Random Forest, Neural Networks, Support Vector Machines, Logistic Regression, XGBoost, and K-Nearest Neighbors). Models were trained on synthetic datasets with varying complexity and a real clinical malaria dataset comprising 250 patients with 16 clinical features. Performance was assessed using 10-fold cross-validation repeated five times, with evaluation metrics including F1-score, accuracy, ROC AUC, Matthews Correlation Coefficient, and balanced accuracy. Class imbalance was addressed using SMOTE oversampling, and model interpretability was examined through LIME, SHAP, and Permutation Feature Importance analyses. Results: Stochastic and deterministic optimization strategies yielded statistically equivalent diagnostic performance, with mean F1-scores of 0.657 and 0.653 respectively (difference < 1%). Random Search demonstrated nearly three times higher computational efficiency than Bayesian Optimization. Algorithm selection and dataset characteristics dominated performance variability, accounting for 16.3% and 68.5% of total variance respectively, while optimization strategy contributed less than 5%. After class balancing and hyperparameter tuning, Random Forest achieved the highest performance (F1-score: 0.831, ROC AUC: 0.870). Explainability analyses consistently identified age, coca-cola urine, prostration, hyperpyrexia, and convulsions as key predictive features across multiple methods. Conclusions: Simple hyperparameter optimization strategies are sufficient for effective clinical deployment of malaria diagnostic models , achieving clinically acceptable performance with minimal computational requirements. The findings support a pragmatic modeling approach prioritizing data quality, algorithm selection, and computational efficiency over optimization complexity, particularly relevant for resource-constrained healthcare settings where malaria burden is highest. Malaria diagnosis Machine learning Hyperparameter optimization SMOTE Model explainability Full Text Additional Declarations No competing interests reported. Supplementary Files AIMMPaper1.zip AIMMPaper2.zip Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 29 Apr, 2026 Reviewers agreed at journal 29 Apr, 2026 Reviewers agreed at journal 26 Apr, 2026 Reviewers agreed at journal 25 Apr, 2026 Reviewers agreed at journal 24 Apr, 2026 Reviewers invited by journal 22 Apr, 2026 Editor assigned by journal 05 Apr, 2026 Editor invited by journal 01 Apr, 2026 Submission checks completed at journal 31 Mar, 2026 First submitted to journal 31 Mar, 2026 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-9172580","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":628167061,"identity":"66257a9e-4c7d-480d-8195-6e3215599f97","order_by":0,"name":"Olushina Olawale Awe","email":"","orcid":"","institution":"Federal University of Bahia","correspondingAuthor":false,"prefix":"","firstName":"Olushina","middleName":"Olawale","lastName":"Awe","suffix":""},{"id":628167062,"identity":"da9c1aac-c35d-4699-9767-c0a32ae57550","order_by":1,"name":"Julia Soares de Souza","email":"","orcid":"","institution":"State University of Campinas","correspondingAuthor":false,"prefix":"","firstName":"Julia","middleName":"Soares","lastName":"de Souza","suffix":""},{"id":628167063,"identity":"11ef9d6e-06ce-4000-b281-4f0d201560a0","order_by":2,"name":"Anderson Kaue Bittencourt Cruz","email":"","orcid":"","institution":"State University of Campinas","correspondingAuthor":false,"prefix":"","firstName":"Anderson","middleName":"Kaue Bittencourt","lastName":"Cruz","suffix":""},{"id":628167064,"identity":"7a7a7e42-e57f-45c0-8112-59decfa7b73b","order_by":3,"name":"Olukorede Olabanji Adekunle","email":"data:image/png;base64,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","orcid":"","institution":"University of Ilorin Teaching Hospital","correspondingAuthor":true,"prefix":"","firstName":"Olukorede","middleName":"Olabanji","lastName":"Adekunle","suffix":""},{"id":628167065,"identity":"c19ef5b2-45db-4369-8d43-4391be08ba6b","order_by":4,"name":"Paul J. Owolabi","email":"","orcid":"","institution":"Covenant University","correspondingAuthor":false,"prefix":"","firstName":"Paul","middleName":"J.","lastName":"Owolabi","suffix":""},{"id":628167066,"identity":"6115982a-99c6-4c05-ac0f-fdf8e6aa7993","order_by":5,"name":"Emmanuel Olusola Oladeji","email":"","orcid":"","institution":"Surgery Interest Group of Africa","correspondingAuthor":false,"prefix":"","firstName":"Emmanuel","middleName":"Olusola","lastName":"Oladeji","suffix":""}],"badges":[],"createdAt":"2026-03-19 19:38:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9172580/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9172580/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107707161,"identity":"49f4603d-953c-435c-8b40-da3b3e8ff3c3","added_by":"auto","created_at":"2026-04-24 09:19:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":822090,"visible":true,"origin":"","legend":"","description":"","filename":"AIMMPaper3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9172580/v1_covered_c5a4619d-18e4-47d2-b17e-d7712f612961.pdf"},{"id":107686276,"identity":"16611131-f596-4e0a-a148-fadd478495f8","added_by":"auto","created_at":"2026-04-24 04:31:27","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":1366412,"visible":true,"origin":"","legend":"","description":"","filename":"AIMMPaper1.zip","url":"https://assets-eu.researchsquare.com/files/rs-9172580/v1/ed32ad6dc1a4d4dd278d6ad7.zip"},{"id":107686277,"identity":"e5023118-7644-42dd-a9f6-272f7f48f259","added_by":"auto","created_at":"2026-04-24 04:31:27","extension":"zip","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1366488,"visible":true,"origin":"","legend":"","description":"","filename":"AIMMPaper2.zip","url":"https://assets-eu.researchsquare.com/files/rs-9172580/v1/43231e1a7e5f75e65e000fdf.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"Rethinking Hyperparameter Optimization for Efficient and Explainable Machine Learning in Civic Health Decision-Making: Empirical Evidence from Malaria Diagnosis","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Malaria diagnosis, Machine learning, Hyperparameter optimization, SMOTE, Model explainability","lastPublishedDoi":"10.21203/rs.3.rs-9172580/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9172580/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground:\u003c/strong\u003e Malaria remains one of the most persistent infectious diseases worldwide, with hundreds of millions of cases annually. Machine learning has emerged as a promising tool for malaria diagnosis, but the practical deployment of these models is constrained by hyperparameter optimization complexity. This study provides a comprehensive comparison of stochastic and deterministic hyper-parameter optimization strategies for supervised machine learning models applied to malaria diagnosis.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods:\u003c/strong\u003e We evaluated five optimization strategies (Grid Search, Random Search, Bayesian Optimization, Genetic Algorithms, and Hyperband Racing) across six supervised learning algorithms (Random Forest, Neural Networks, Support Vector Machines, Logistic Regression, XGBoost, and K-Nearest Neighbors). Models were trained on synthetic datasets with varying complexity and a real clinical malaria dataset comprising 250 patients with 16 clinical features. Performance was assessed using 10-fold cross-validation repeated five times, with evaluation metrics including F1-score, accuracy, ROC AUC, Matthews Correlation Coefficient, and balanced accuracy. Class imbalance was addressed using SMOTE oversampling, and model interpretability was examined through LIME, SHAP, and Permutation Feature Importance analyses.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e Stochastic and deterministic optimization strategies yielded statistically equivalent diagnostic performance, with mean F1-scores of 0.657 and 0.653 respectively (difference \u0026lt; 1%). Random Search demonstrated nearly three times higher computational efficiency than Bayesian Optimization. Algorithm selection and dataset characteristics dominated performance variability, accounting for 16.3% and 68.5% of total variance respectively, while optimization strategy contributed less than 5%. After class balancing and hyperparameter tuning, Random Forest achieved the highest performance (F1-score: 0.831, ROC AUC: 0.870). Explainability analyses consistently identified age, coca-cola urine, prostration, hyperpyrexia, and convulsions as key predictive features across multiple methods.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions:\u003c/strong\u003e Simple hyperparameter optimization strategies are sufficient for effective clinical deployment of malaria diagnostic models , achieving clinically acceptable performance with minimal computational requirements. The findings support a pragmatic modeling approach prioritizing data quality, algorithm selection, and computational efficiency over optimization complexity, particularly relevant for resource-constrained healthcare settings where malaria burden is highest.\u003c/p\u003e","manuscriptTitle":"Rethinking Hyperparameter Optimization for Efficient and Explainable Machine Learning in Civic Health Decision-Making: Empirical Evidence from Malaria Diagnosis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-24 04:31:23","doi":"10.21203/rs.3.rs-9172580/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-04-30T00:42:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"15551999505362148522149263137261795931","date":"2026-04-29T08:31:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"7276084386914046560731744295714661506","date":"2026-04-26T15:19:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"282429236510685268886560595161063794849","date":"2026-04-25T06:13:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"25955834032005589805297341181901850991","date":"2026-04-25T03:09:14+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-22T22:44:44+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-05T09:51:47+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-01T09:45:21+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-31T21:48:29+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2026-03-31T21:45:40+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"13364b1c-ab96-462c-a2b6-6e66133d5cc6","owner":[],"postedDate":"April 24th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-04-30T00:42:59+00:00","index":49,"fulltext":""},{"type":"reviewerAgreed","content":"15551999505362148522149263137261795931","date":"2026-04-29T08:31:25+00:00","index":48,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-24T04:31:23+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-24 04:31:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9172580","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9172580","identity":"rs-9172580","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}