Oropouche, Dengue, and Chikungunya differential diagnosis. Development and validation of predictive models with surveillance data from Espirito Santo-Brazil.

There is an ongoing Oropouche Fever (OF) outbreak in Brazil since 2024. There are dengue and chikungunya prediction models available, but none to help discriminate dengue, chikungunya, and OF. ObjectiveThis study aims to develop and validate clinical prediction models for dengue, chikungunya, OF. MethodsThis study uses surveillance data from Espirito Santo state / Brazil, from 2023-2025. Epidemiological investigations and biological samples were used to conclude cases as either (a) clinical-epidemiologically confirmed, (b) laboratory confirmed, or (c) "discarded". The predictors were all data related to signs, symptoms, and comorbidities available in the notification forms. The analysis was performed using random forest regression models, one for each outcome, in development and validation datasets. ResultsA total of 465,280 observations were analyzed, 261,691 dengue cases (56.6%), 18,676 chikungunya cases (4.0%), 12,174 OF cases (2.6%), and 179,115 discarded cases (38.6%). All three models had good discrimination and moderate to good calibration after scaling prediction. The models retained from 26 to 16 predictors each. Leukopenia and vomiting were the most discriminatory predictors for dengue, arthritis, arthralgia, and rash were the most discriminatory for chikungunya, and epidemiological features were the most relevant for OF. The dengue, chikungunya, and OF models had ROC AUC of 0.726, 0.851, and 0.896 in the validation set, respectively. ConclusionThis research identified predictors most discriminative between dengue, chikungunya, and OF. We developed and validated predictive models, one for each condition, with moderate to very good performance available at https://pedrobrasil.shinyapps.io/INDWELL/. One may use them in diagnostic work-up and arbovirus surveillance. LAY SUMMARYO_LIDengue fever was by far the most common confirmed infection in the surveillance system (56.6%), followed by chikungunya cases (4.0%), oropouche cases (2.6%), zika cases (0.2%), with different seasonality. C_LIO_LIAlthough suspected dengue cases were more laboratory tested, laboratory confirmation was more frequent among oropouche fever cases. It was possible to develop and validate models for dengue, chikungunya, and oropouche diagnostic investigation, and their performance was from moderate to very good, with suggested decision limits to aid the users. All attempts to develop Zika models returned models with unacceptable performance. C_LIO_LIWe developed an instrument to predict the three conditions with the same predictors and made it available for users at https://pedrobrasil.shinyapps.io/INDWELL/. C_LI