{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:55:18Z","timestamp":1776056118187,"version":"3.50.1"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>The clinical differentiation of Chikungunya from other acute febrile illnesses poses a significant diagnostic challenge due to the substantial symptom overlap among co-circulating arboviruses such as Dengue and Zika, particularly in resource-constrained settings where laboratory confirmation is frequently delayed or unavailable. This study proposes an interpretable machine learning framework for the prediction of laboratory-confirmed Chikungunya cases versus suspected cases that were subsequently discarded after laboratory investigation, using a large-scale, nationally representative dataset of 12,709 notification records derived from Brazil's Information System for Notifiable Diseases (SINAN), spanning 2013 to 2020 and encompassing 26 clinical symptom, comorbidity, and sociodemographic features. Four supervised learning algorithms\u2014Logistic Regression, Random Forest, XGBoost, and LightGBM\u2014were systematically evaluated under 5-fold stratified cross-validation, with Random Forest achieving the highest discriminative performance (AUC = 0.785 \u00b1 0.005) and XGBoost demonstrating the best probability calibration reliability. Considering the trade-off between discrimination and calibration, XGBoost was identified as the most suitable model for potential clinical deployment. To ensure clinical transparency, a structured three-level SHapley Additive exPlanations (SHAP) interpretability analysis was conducted on both gradient boosting models, encompassing global feature importance ranking, feature-level directional and interaction effects, and local patient-level prediction decomposition. The SHAP analysis consistently identified arthralgia (mean |SHAP|: 0.7407 in XGBoost, 0.7489 in LightGBM) and fever (0.5043 and 0.4881, respectively) as the two dominant predictors of Chikungunya confirmation, followed by age, education level, and rash, while comorbidities contributed negligibly to case discrimination. Cross-model validation between XGBoost and LightGBM revealed highly concordant feature importance rankings and directional effect patterns, confirming that the identified clinical predictors are robust and independent of algorithmic choice. These findings demonstrate the practical value of combining machine learning with SHAP-based explainability for supporting clinical triage of suspected arboviral cases, providing a transparent, evidence-based diagnostic support tool that aligns data-driven insights with established clinical knowledge and enables personalized patient-level explanations at the point of care. Importantly, the model distinguishes confirmed Chikungunya from discarded suspected cases rather than from confirmed infections with other specific arboviruses, and its predictions should be interpreted within this operational context.<\/jats:p>","DOI":"10.3389\/fmed.2026.1814257","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:35:54Z","timestamp":1776054954000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Arthralgia and fever as dominant predictors of Chikungunya confirmation: an explainable artificial intelligence approach"],"prefix":"10.3389","volume":"13","author":[{"given":"Xinyu","family":"Lu","sequence":"first","affiliation":[{"name":"Health Management Research, Zhongshan Second People's Hospital","place":["Zhongshan, Guangdong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Yin","sequence":"additional","affiliation":[{"name":"Health Management Research, Zhongshan Second People's Hospital","place":["Zhongshan, Guangdong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics & Statistics, Stony Brook University","place":["Stony Brook, NY, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13071-024-06598-7","article-title":"Human migrations, anthropogenic changes, and insect-borne diseases in Latin America","volume":"18","author":"Wilke","year":"2025","journal-title":"Paras Vectors"},{"key":"B2","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1186\/s12916-015-0348-x","article-title":"Emergence and potential for spread of Chikungunya virus in Brazil","volume":"13","author":"Nunes","year":"2015","journal-title":"BMC Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"101153","DOI":"10.1016\/j.lana.2025.101153","article-title":"Introduction, establishment, and distribution of Aedes aegypti and dengue in a temperate capital of Brazil: a retrospective surveillance-based study.","volume":"48","author":"da Cruz Ferreira","year":"2025","journal-title":"Lancet Reg Health-Am"},{"key":"B4","doi-asserted-by":"publisher","first-page":"648","DOI":"10.3390\/diagnostics15050648","article-title":"The value of clinical decision support in healthcare: a focus on screening and early detection","volume":"15","author":"Sch\u00e4fer","year":"2025","journal-title":"Diagnostics"},{"key":"B5","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1093\/clinchem\/hvab201","article-title":"Clinical decision support for laboratory testing","volume":"68","author":"Hughes","year":"2022","journal-title":"Clin Chem"},{"key":"B6","first-page":"226","article-title":"Revolutionizing healthcare with artificial intelligence: a machine learning-driven approach to precision medicine, predictive analytics, and automated clinical decision support","volume":"64","author":"Kandregula","year":"2024","journal-title":"Cineforum"},{"key":"B7","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1111\/joim.13640","article-title":"Precision medicine in complex diseases\u2013molecular subgrouping for improved prediction and treatment stratification","volume":"294","author":"Johansson","year":"2023","journal-title":"J Internal Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1007\/s13312-022-2561-y","article-title":"Multicenter studies: relevance, design and implementation","volume":"59","author":"Das","year":"2022","journal-title":"Indian Pediatr"},{"key":"B9","doi-asserted-by":"publisher","first-page":"e0326221","DOI":"10.1371\/journal.pone.0326221","article-title":"Advancing breast cancer prediction: comparative analysis of ML models and deep learning-based multi-model ensembles on original and synthetic datasets","volume":"20","author":"Ahmed","year":"2025","journal-title":"PLoS ONE"},{"key":"B10","doi-asserted-by":"publisher","first-page":"103169","DOI":"10.1016\/j.artmed.2025.103169","article-title":"From black box to clarity: strategies for effective AI informed consent in healthcare","volume":"167","author":"Chau","year":"2025","journal-title":"Artif Intell Med"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1101\/2025.07.11.664302","article-title":"XAI-based data visualization in multimodal medical data","author":"Sharma","year":"2025","journal-title":"bioRxiv"},{"key":"B12","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","article-title":"Assessing the performance of prediction models: a framework for some traditional and novel measures","volume":"21","author":"Steyerberg","year":"2010","journal-title":"Epidemiology"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e0010061","DOI":"10.1371\/journal.pntd.0010061","article-title":"Machine learning and deep learning techniques to support clinical diagnosis of arboviral diseases: a systematic review","volume":"16","author":"da Silva Neto","year":"2022","journal-title":"PLoS Negl Trop Dis"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e0429","DOI":"10.1590\/0037-8682-0429-2025","article-title":"et al. Forecasting and early warning systems for dengue outbreaks: updated narrative review","volume":"59","author":"Costa","year":"2026","journal-title":"Rev Soc Bras Med Trop"},{"key":"B15","doi-asserted-by":"publisher","first-page":"102200","DOI":"10.1016\/j.eclinm.2023.102200","article-title":"An interpretable AI model for recurrence prediction after surgery in gastrointestinal stromal tumour: an observational cohort study","volume":"64","author":"Bertsimas","year":"2023","journal-title":"EClinicalMedicine"},{"key":"B16","doi-asserted-by":"publisher","first-page":"4974","DOI":"10.1016\/j.acra.2024.06.036","article-title":"Sub-regional CT radiomics for the prediction of Ki-67 proliferation index in gastrointestinal stromal tumors: a multi-center study","volume":"31","author":"Cai","year":"2024","journal-title":"Acad Radiol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"26733","DOI":"10.1038\/s41598-025-12356-1","article-title":"Predicting high dengue incidence in municipalities of Brazil using path signatures","volume":"15","author":"Villela","year":"2025","journal-title":"Sci Rep"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e70714","DOI":"10.1002\/hsr2.70714","article-title":"Comparison of deep learning and gradient boosting: ANN versus XGBoost for climate-based dengue prediction in Bangladesh","volume":"8","author":"Chowdhury","year":"2025","journal-title":"Health Sci Rep"},{"key":"B19","doi-asserted-by":"publisher","first-page":"241870","DOI":"10.1098\/rsos.241870","article-title":"Multi-model approach to understand and predict past and future dengue epidemic dynamics","volume":"12","author":"Mills","year":"2025","journal-title":"Royal Soc Open Sci"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3645264","article-title":"Digital twin-empowered comprehensive framework for Chikungunya outspread control","author":"Kaur","year":"2025","journal-title":"IEEE Internet Things J"},{"key":"B21","doi-asserted-by":"publisher","first-page":"e00206","DOI":"10.1590\/0037-8682-0334-2024","article-title":"Dengue mimickers: which clinical conditions can resemble dengue fever?","volume":"57","author":"Farias","year":"2024","journal-title":"Rev Soc Bras Med Trop"},{"key":"B22","doi-asserted-by":"publisher","first-page":"618","DOI":"10.4103\/singaporemedj.SMJ-2025-084","article-title":"A practical approach to joint pain in primary care","volume":"66","author":"Lim","year":"2025","journal-title":"Singapore Med J"},{"key":"B23","doi-asserted-by":"publisher","first-page":"e1786","DOI":"10.1371\/journal.pntd.0001786","article-title":"Simple clinical and laboratory predictors of Chikungunya versus dengue infections in adults","volume":"6","author":"Lee","year":"2012","journal-title":"PLoS Negl Trop Dis"},{"key":"B24","doi-asserted-by":"publisher","first-page":"107226","DOI":"10.1016\/j.ijid.2024.107226","article-title":"Prevalence of dengue, Zika, and Chikungunya virus infections among mosquitoes in Asia: a systematic review and meta-analysis","volume":"148","author":"Maneerattanasak","year":"2024","journal-title":"Int J Inf Dis"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40860-024-00240-0","article-title":"The performance-interpretability trade-off: a comparative study of machine learning models","volume":"11","author":"Assis","year":"2025","journal-title":"J Reliable Intell Environ"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2588","DOI":"10.3390\/healthcare13202588","article-title":"Interpretable machine learning framework for diabetes prediction: integrating SMOTE balancing with SHAP explainability for clinical decision support","volume":"13","author":"Netayawijit","year":"2025","journal-title":"Healthcare"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4637897","author":"Rane","year":"2023","journal-title":"Explainable artificial intelligence (XAI) in healthcare: interpretable models for clinical decision support"},{"key":"B28","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-030-65965-3_28","article-title":"Interpretable machine learning-a brief history, state-of-the-art and challenges","volume":"1323","author":"Molnar","year":"2020","journal-title":"Commun Comput Inf Sci"},{"key":"B29","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/s44196-025-01011-2","article-title":"Game-theoretic explainable AI for ensemble-boosting models in early malware prediction for computer systems","volume":"18","author":"Henna","year":"2025","journal-title":"Int J Comput Intell Syst"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.38124\/ijisrt\/26jan131","article-title":"Machine learning for predicting diagnostic test discordance in malaria surveillance: a gradient boosting approach with SHAP interpretation","author":"Stow","year":"2025","journal-title":"Int J Innov Sci Res Technol"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1543","DOI":"10.1039\/D4NP00009A","article-title":"Advances, opportunities, and challenges in methods for interrogating the structure activity relationships of natural products","volume":"41","author":"Ancajas","year":"2024","journal-title":"Natural Product Rep"},{"key":"B32","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1111\/deci.12642","article-title":"An interpretable machine learning methodology to generate interaction effect hypotheses from complex datasets","volume":"55","author":"Nasir","year":"2024","journal-title":"Decis Sci"},{"key":"B33","author":"Zheng","year":"2025","journal-title":"A multitask deep learning framework for clinical decision-making in assisted reproductive technology"},{"key":"B34","unstructured":"Messai\n              A\n            \n          \n          Automatic medical decision for diagnosis of infectious diseases based on artificial intelligence approaches\n          \n          2025"},{"key":"B35","first-page":"4765","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B36","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"B37","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1186\/s12916-019-1466-7","article-title":"Calibration: the Achilles heel of predictive analytics","volume":"17","author":"Van Calster","year":"2019","journal-title":"BMC Med"},{"key":"B38","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","volume":"21","author":"Chicco","year":"2020","journal-title":"BMC Genomics"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1814257\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:36:06Z","timestamp":1776054966000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1814257\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":38,"alternative-id":["10.3389\/fmed.2026.1814257"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1814257","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,13]]},"article-number":"1814257"}}