Microscopic observation of mosquito species, which is the basis of morphological identification, is a time-consuming and challenging process, particularly owing to the different skills and experience of public health personnel. We present deep learning models based on the well-known you-only-look-once (YOLO) algorithm. This model can be used to simultaneously classify and localize the images to identify the species of the gender of field-caught mosquitoes. The results indicated that the concatenated two YOLO v3 model exhibited the optimal performance in identifying the mosquitoes, as the mosquitoes were relatively small objects compared with the large proportional environment image. The robustness testing of the proposed model yielded a mean average precision and sensitivity of 99% and 92.4%, respectively. The model exhibited high performance in terms of the specificity and accuracy, with an extremely low rate of misclassification. The area under the receiver operating characteristic curve (AUC) was 0.958 ± 0.011, which further demonstrated the model accuracy. Thirteen classes were detected with an accuracy of 100% based on a confusion matrix. Nevertheless, the relatively low detection rates for the two species were likely a result of the limited number of wild-caught biological samples available. The proposed model can help establish the population densities of mosquito vectors in remote areas to predict disease outbreaks in advance.
Background The comorbid presence of tuberculosis and diabetes mellitus has become an increasingly important public health threat to the prevention and control of both diseases. Thus, household contact investigation may serve a dual purpose of screening for both tuberculosis and diabetes mellitus among household contacts. We therefore aimed to evaluate the coverage of screening for tuberculosis and diabetes mellitus among household contacts of tuberculosis index cases and to determine predictors of tuberculosis screening. Methods A household-based survey was conducted in February 2019 in Muang district of Phatthalung Province, Thailand where 95 index tuberculosis patients were newly diagnosed with pulmonary or pleural tuberculosis between October 2017 and September 2018. Household contacts of the index patients were interviewed using a structured questionnaire to ascertain their past-year history of tuberculosis screening and, if appropriate, diabetes mellitus screening. For children, the household head or an adult household member was interviewed as a proxy. Coverage of tuberculosis screening at the household level was regarded as households having all contacts screened for tuberculosis. Logistic regression and mixed-effects logistic regression models were used to determine predictors of tuberculosis screening at the household and individual levels, respectively, with the strengths of association presented as adjusted odds ratios (AOR) and 95% confidence intervals (CI). Results Of 61 responding households (64%), complete coverage of tuberculosis screening at the household level was 34.4% and among the 174 household contacts was 46.6%. About 20% of contacts did not receive any recommendation for tuberculosis screening. Households were more likely to have all members screened for tuberculosis if they were advised to be screened by a healthcare professional rather than someone else. At the individual level, contacts aged ≥35 years (AOR: 30.6, 95% CI: 2.0–466.0), being an employee (AOR: 0.1, 95% CI: 0.0–0.8) and those who had lived more than 5 years in the same household (AOR: 0.1, 95% CI: 0.0–0.8) were independent predictors for tuberculosis screening. Coverage of diabetes mellitus screening was 80.6% with lack of awareness being the main reason for not being screened. Conclusions Compared to diabetes screening, the coverage of tuberculosis screening was low. A better strategy to improve coverage of tuberculosis contact screening is needed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.