Integrating Machine Learning and Spatial Clustering for Malaria Case Prediction in Brazil's Legal Amazon

Integrating Machine Learning and Spatial Clustering for Malaria Case Prediction in Brazil's Legal Amazon | 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 Integrating Machine Learning and Spatial Clustering for Malaria Case Prediction in Brazil's Legal Amazon Kayo H. Monteiro, Elisson da Silva Rocha, Luis Augusto Morais Silva, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5975711/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 08 Jun, 2025 Read the published version in BMC Infectious Diseases → Version 1 posted 6 You are reading this latest preprint version Abstract Malaria remains a major global health challenge, particularly in Brazil's Legal Amazon region, where environmental and socioeconomic conditions foster favorable conditions for disease transmission. Traditional control measures have shown limited effectiveness, emphasizing the need for better predictive approaches to support timely and targeted public health interventions.This study evaluates the performance of six computational models—Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Support Vector Regression (SVR), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Autoregressive Integrated Moving Average (ARIMA)—for forecasting weekly malaria cases across multiple states in the Legal Amazon. The results demonstrate that the RF model consistently outperformed the other models, achieving the lowest Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) values in most cases, such as in cluster 02 of the state of Acre, with RMSE of 0.00203 and MAE of 0.00133. The integration of K-means clustering further improved the model predictive accuracy by accounting for spatial heterogeneity and capturing localized transmission dynamics. This hybrid modeling approach, combining machine learning models with spatial clustering, offers a promising tool for enhancing malaria surveillance and guiding more effective public health strategies, especially for malaria control efforts in high-risk regions. Malaria Prediction Machine Learning Spatial Clustering Time Series Forecasting Public Health Surveillance Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 08 Jun, 2025 Read the published version in BMC Infectious Diseases → Version 1 posted Editorial decision: Revision requested 20 May, 2025 Reviews received at journal 19 May, 2025 Reviewers agreed at journal 23 Apr, 2025 Reviewers invited by journal 21 Apr, 2025 Submission checks completed at journal 20 Apr, 2025 First submitted to journal 17 Apr, 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-5975711","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":444574330,"identity":"1c5aadb1-d616-45d5-b473-ac436e952657","order_by":0,"name":"Kayo H. Monteiro","email":"","orcid":"","institution":"Universidade de Pernambuco","correspondingAuthor":false,"prefix":"","firstName":"Kayo","middleName":"H.","lastName":"Monteiro","suffix":""},{"id":444574332,"identity":"941565cf-a3b5-4545-a0a2-ea17df938d14","order_by":1,"name":"Elisson da Silva Rocha","email":"","orcid":"","institution":"Universidade de Pernambuco","correspondingAuthor":false,"prefix":"","firstName":"Elisson","middleName":"da Silva","lastName":"Rocha","suffix":""},{"id":444574334,"identity":"890b419b-38bb-446f-8ec7-f3e5f6923f7f","order_by":2,"name":"Luis Augusto Morais Silva","email":"","orcid":"","institution":"Centro Universitário Unifavip Wyden","correspondingAuthor":false,"prefix":"","firstName":"Luis","middleName":"Augusto Morais","lastName":"Silva","suffix":""},{"id":444574335,"identity":"25c02f64-0128-4368-862d-2744a5cb9a5d","order_by":3,"name":"Elton Gino Santos","email":"","orcid":"","institution":"Centro Universitário Unifavip Wyden","correspondingAuthor":false,"prefix":"","firstName":"Elton","middleName":"Gino","lastName":"Santos","suffix":""},{"id":444574338,"identity":"fb8d7ecc-5e35-4ff9-91db-74bf74d22186","order_by":4,"name":"Sebastião Neto","email":"","orcid":"","institution":"Centro Universitário Unifavip Wyden","correspondingAuthor":false,"prefix":"","firstName":"Sebastião","middleName":"","lastName":"Neto","suffix":""},{"id":444574340,"identity":"acdb3334-6e00-4fa2-a0b1-15126111d149","order_by":5,"name":"Vanderson Sampaio","email":"","orcid":"","institution":"Instituto Todos pela Saúde","correspondingAuthor":false,"prefix":"","firstName":"Vanderson","middleName":"","lastName":"Sampaio","suffix":""},{"id":444574342,"identity":"e222c6b0-77af-40de-a531-21a36c4f02be","order_by":6,"name":"Patricia Takako Endo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4ElEQVRIiWNgGAWjYLCCBAYJMC3BUAGieAipZ0bWcoZYLTAgwdhGhBZz9vPHPjyosZBnYO89eOPjvMN5/Ay8xz7g02LZk8w8I+GYhGEDz7lky5nbDhdLNvAlz8CnxeBAMjNDYoMEY4NEjpk077bDiRsO8BjjdZjB+cdgLfYN8m+AWuYcTtxPUMsNiC1AxAPU0gC0hYGAFssZj40ZgH5JbuPJMbaccSy9WOIwXzJeLeb8iY8Zf9TU2faznzG88aHGOo+/vfcwfofBGGxQOgE5ovBrgYEEAhpGwSgYBaNgBAIA9xFBjYo05RUAAAAASUVORK5CYII=","orcid":"","institution":"Universidade de Pernambuco","correspondingAuthor":true,"prefix":"","firstName":"Patricia","middleName":"Takako","lastName":"Endo","suffix":""}],"badges":[],"createdAt":"2025-02-06 18:08:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5975711/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5975711/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12879-025-11193-x","type":"published","date":"2025-06-08T15:57:53+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":84242652,"identity":"9ba13481-3aa3-4d49-bc24-8d2505b2e3d3","added_by":"auto","created_at":"2025-06-09 16:10:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2552573,"visible":true,"origin":"","legend":"","description":"","filename":"BMCInfectiousDiseasesMalariaKayo.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5975711/v1_covered_afe50ad0-4d10-446d-9abc-acb12accdac9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Integrating Machine Learning and Spatial Clustering for Malaria Case Prediction in Brazil's Legal Amazon","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"bmc-infectious-diseases","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"infd","sideBox":"Learn more about [BMC Infectious Diseases](http://bmcinfectdis.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/infd","title":"BMC Infectious Diseases","twitterHandle":"#bmcinfectdis","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Malaria Prediction, Machine Learning, Spatial Clustering, Time Series Forecasting, Public Health Surveillance","lastPublishedDoi":"10.21203/rs.3.rs-5975711/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5975711/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Malaria remains a major global health challenge, particularly in Brazil's Legal Amazon region, where environmental and socioeconomic conditions foster favorable conditions for disease transmission. Traditional control measures have shown limited effectiveness, emphasizing the need for better predictive approaches to support timely and targeted public health interventions.This study evaluates the performance of six computational models—Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Support Vector Regression (SVR), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Autoregressive Integrated Moving Average (ARIMA)—for forecasting weekly malaria cases across multiple states in the Legal Amazon. The results demonstrate that the RF model consistently outperformed the other models, achieving the lowest Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) values in most cases, such as in cluster 02 of the state of Acre, with RMSE of 0.00203 and MAE of 0.00133. The integration of K-means clustering further improved the model predictive accuracy by accounting for spatial heterogeneity and capturing localized transmission dynamics. This hybrid modeling approach, combining machine learning models with spatial clustering, offers a promising tool for enhancing malaria surveillance and guiding more effective public health strategies, especially for malaria control efforts in high-risk regions.","manuscriptTitle":"Integrating Machine Learning and Spatial Clustering for Malaria Case Prediction in Brazil's Legal Amazon","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-21 01:35:46","doi":"10.21203/rs.3.rs-5975711/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-20T09:05:34+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-19T14:06:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"134397147098467949151568611114122311747","date":"2025-04-23T14:18:53+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-21T16:53:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-21T02:04:08+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Infectious Diseases","date":"2025-04-17T20:09:03+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-infectious-diseases","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"infd","sideBox":"Learn more about [BMC Infectious Diseases](http://bmcinfectdis.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/infd","title":"BMC Infectious Diseases","twitterHandle":"#bmcinfectdis","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"34c6d4fd-a1b2-4583-bff2-58a94a60518e","owner":[],"postedDate":"April 21st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-06-09T16:04:40+00:00","versionOfRecord":{"articleIdentity":"rs-5975711","link":"https://doi.org/10.1186/s12879-025-11193-x","journal":{"identity":"bmc-infectious-diseases","isVorOnly":false,"title":"BMC Infectious Diseases"},"publishedOn":"2025-06-08 15:57:53","publishedOnDateReadable":"June 8th, 2025"},"versionCreatedAt":"2025-04-21 01:35:46","video":"","vorDoi":"10.1186/s12879-025-11193-x","vorDoiUrl":"https://doi.org/10.1186/s12879-025-11193-x","workflowStages":[]},"version":"v1","identity":"rs-5975711","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5975711","identity":"rs-5975711","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}