Recognizing and monitoring infectious sources of schistosomiasis by developing deep learning models with high-resolution remote sensing images

Background China is progressing towards the goal of schistosomiasis elimination,but there are still some problems,such as difficult management of infection source and snail control.This study aimed to develop deep learning models with high-resolution remote sensing images for recognizing and monitoring livestock bovine,which is an intermediate source of Schistosoma japonicum infection,and to evaluate the effectiveness of the models for real-world application.Methods The dataset of livestock bovine’s spatial distribution was collected from the Chinese National Platform for Common Geospatial Information Services.The high-resolution remote sensing images were further divided into training data,test data,and validation data for model development.Two recognition models based on deep learning methods(ENVINet5 and Mask R-CNN)were developed with reference to the training datasets.The performance of the developed models was evaluated by the performance metrics of precision,recall,and F1-score.Results A total of 50 typical image areas were selected,1125 bovine objectives were labeled by the ENVINet5 model and 1277 bovine objectives were labeled by the Mask R-CNN model.For the ENVINet5 model,a total of 1598 records of bovine distribution were recognized.The model precision and recall were 81.9%and 80.2%,respectively.The F1 score was 0.81.For the Mask R-CNN mode,1679 records of bovine objectives were identified.The model precision and recall were 87.3%and 85.2%,respectively.The F1 score was 0.87.When applying the developed models to real-world schistosomiasis-endemic regions,there were 63 bovine objectives in the original image,53 records were extracted using the ENVINet5 model,and 57 records were extracted using the Mask R-CNN model.The successful recognition ratios were 84.1%and 90.5%for the respectively developed models.Conclusion The ENVINet5 model is very feasible when the bovine distribution is low in structure with few samples.The Mask R-CNN model has a good framework design and runs highly efficiently.The livestock recognition models developed using deep learning methods with high-resolution remote sensing images accurately recognize the spatial distribution of livestock,which could enable precise control of schistosomiasis.

Towards a global One Health index: a potential assessment tool for One Health performance

Background:A One Health approach has been increasingly mainstreamed by the international community, as it provides for holistic thinking in recognizing the close links and inter-dependence of the health of humans, animals and the environment. However, the dearth of real-world evidence has hampered application of a One Health approach in shaping policies and practice. This study proposes the development of a potential evaluation tool for One Health performance, in order to contribute to the scientific measurement of One Health approach and the identification of gaps where One Health capacity building is most urgently needed.Methods:We describe five steps towards a global One Health index (GOHI), including (i) framework formulation;(ii) indicator selection;(iii) database building;(iv) weight determination;and (v) GOHI scores calculation. A cell-like framework for GOHI is proposed, which comprises an external drivers index (EDI), an intrinsic drivers index (IDI) and a core drivers index (CDI). We construct the indicator scheme for GOHI based on this framework after multiple rounds of panel discussions with our expert advisory committee. A fuzzy analytical hierarchy process is adopted to determine the weights for each of the indicators.Results:The weighted indicator scheme of GOHI comprises three first-level indicators, 13 second-level indicators, and 57 third-level indicators. According to the pilot analysis based on the data from more than 200 countries/territories the GOHI scores overall are far from ideal (the highest score of 65.0 out of a maximum score of 100), and we found considerable variations among different countries/territories (31.8–65.0). The results from the pilot analysis are consistent with the results from a literature review, which suggests that a GOHI as a potential tool for the assessment of One Health performance might be feasible.Conclusions:GOHI—subject to rigorous validation—would represent the world’s first evaluation tool that constructs the conceptual framework from a holistic perspective of One Health. Future application of GOHI might promote a common understanding of a strong One Health approach and provide reference for promoting effective measures to strengthen One Health capacity building. With further adaptations under various scenarios, GOHI, along with its technical protocols and databases, will be updated regularly to address current technical limitations, and capture new knowledge.