Aedes aegypti and Aedes albopictus vector dengue, chikungunya and Zika viruses. With both species expanding their global distributions at alarming rates, developing effective surveillance equipment is a continuing priority for public health researchers. Sound traps have been shown, in limited testing, to be highly species-specific when emitting a frequency corresponding to a female mosquito wingbeat. Determining male mosquito capture rates in sound traps based on lure frequencies in endemic settings is the next step for informed deployment of these surveillance tools. We field-evaluated Male Aedes Sound Traps (MASTs) set to either 450 Hz, 500 Hz, 550 Hz or 600 Hz for sampling Aedes aegypti and/or Aedes albopictus and compared catch rates to BG-Sentinel traps within Pacific (Madang, Papua New Guinea) and Latin American (Molas, Mexico and Orange Walk Town, Belize) locations. MASTs set to 450–550 Hz consistently caught male Ae. aegypti at rates comparable to BG-Sentinel traps in all locations. A peak in male Ae. albopictus captures in MASTs set at 550 Hz was observed, with the lowest mean abundance recorded in MASTs set to 450 Hz. While significantly higher abundances of male Culex were sampled in MASTs emitting lower relative frequencies in Molas, overall male Culex were captured in significantly lower abundances in the MASTs, relative to BG-Sentinel traps within all locations. Finally, significant differences in rates at which male Aedes and Culex were positively detected in trap-types per weekly collections were broadly consistent with trends in abundance data per trap-type. MASTs at 550 Hz effectively captured both male Ae. aegypti and Ae. albopictus while greatly reducing bycatch, especially male Culex, in locations where dengue transmission has occurred. This high species-specificity of the MAST not only reduces staff-time required to sort samples, but can also be exploited to develop an accurate smart-trap system—both outcomes potentially reducing public health program expenses.

Background: Sepsis is a life-threatening condition frequently observed in patients with intracerebral hemorrhage (ICH) who are critically ill. Early and accurate identification and prediction of sepsis are crucial. Machine learning (ML)–based predictive models exhibit promising sepsis prediction capabilities in emergency settings. However, their application in predicting sepsis among patients with ICH is still limited. Objective: The aim of the study is to develop an ML-driven risk calculator for early prediction of sepsis in patients with ICH who are critically ill and to clarify feature importance and explain the model using the Shapley Additive Explanations method. Methods: Patients with ICH admitted to the intensive care unit (ICU) from the Medical Information Mart for Intensive Care IV database between 2008 and 2022 were divided into training and internal test sets. The external test was performed using the eICU Collaborative Research Database, which includes over 200,000 ICU admissions across the United States between 2014 and 2015. Sepsis following ICU admission was identified using Sepsis-3.0 through clinical diagnosis combining elevation of the Sequential Organ Failure Assessment by ≥2 points with suspected infection. The Boruta algorithm was used for feature selection, confirming 29 features. Nine ML algorithms were used to construct the prediction models. Predictive performance was compared using several evaluation metrics, including the area under the receiver operating characteristic curve (AUC). The Shapley Additive Explanations technique was used to interpret the final model, and a web-based risk calculator was constructed for clinical practice. Results: Overall, 2414 patients with ICH were enrolled from the Medical Information Mart for Intensive Care IV database, with 1689 and 725 patients assigned to the training and internal test sets, respectively. An external test set of 2806 patients with ICH from the eICU database was used. Among the 9 ML models tested, the categorical boosting (CatBoost) model demonstrated the best discriminative ability. After reducing features based on their importance, an explainable final CatBoost model was developed using 8 features. The final model accurately predicted sepsis in internal (AUC=0.812) and external (AUC=0.771) tests. Conclusions: We constructed a web-based risk calculator with 8 features based on the CatBoost model to assist clinicians in identifying people at high risk for sepsis in patients with ICH who are critically ill.