Реферат
Objective To investigate the feasibility of developing a grading diagnostic model for schistosomiasis-induced liver fibrosis based on B-mode ultrasonographic images and clinical laboratory indicators. Methods Ultrasound images and clinical laboratory testing data were captured from schistosomiasis patients admitted to the Second People’s Hospital of Duchang County, Jiangxi Province from 2018 to 2022. Patients with grade I schistosomiasis-induced liver fibrosis were enrolled in Group 1, and patients with grade II and III schistosomiasis-induced liver fibrosis were enrolled in Group 2. The machine learning binary classification tasks were created based on patients’radiomics and clinical laboratory data from 2018 to 2021 as the training set, and patients’radiomics and clinical laboratory data in 2022 as the validation set. The features of ultrasonographic images were labeled with the ITK-SNAP software, and the features of ultrasonographic images were extracted using the Python 3.7 package and PyRadiomics toolkit. The difference in the features of ultrasonographic images was compared between groups with t test or Mann-Whitney U test, and the key imaging features were selected with the least absolute shrinkage and selection operator (LASSO) regression algorithm. Four machine learning models were created using the Scikit-learn repository, including the support vector machine (SVM), random forest (RF), linear regression (LR) and extreme gradient boosting (XGBoost). The optimal machine learning model was screened with the receiver operating characteristic curve (ROC), and features with the greatest contributions to the differentiation features of ultrasound images in machine learning models with the SHapley Additive exPlanations (SHAP) method. Results The ultrasonographic imaging data and clinical laboratory testing data from 491 schistosomiasis patients from 2019 to 2022 were included in the study, and a total of 851 radiomics features and 54 clinical laboratory indicators were captured. Following statistical tests (t = −5.98 to 4.80, U = 6 550 to 20 994, all P values < 0.05) and screening of key features with LASSO regression, 44 features or indicators were included for the subsequent modeling. The areas under ROC curve (AUCs) were 0.763 and 0.611 for the training and validation sets of the SVM model based on clinical laboratory indicators, 0.951 and 0.892 for the training and validation sets of the SVM model based on radiomics, and 0.960 and 0.913 for the training and validation sets of the multimodal SVM model. The 10 greatest contributing features or indicators in machine learning models included 2 clinical laboratory indicators and 8 radiomics features. Conclusions The multimodal machine learning models created based on ultrasound-based radiomics and clinical laboratory indicators are feasible for intelligent identification of schistosomiasis-induced liver fibrosis, and are effective to improve the classification effect of one-class data models.
Реферат
Objective: To determine the spatiotemporal distribution of Schistosoma (S.) japonicum infections in humans, livestock, and Oncomelania (O.) hupensis across the endemic foci of China. Methods: Based on multi-stage continuous downscaling of sentinel monitoring, county-based schistosomiasis surveillance data were captured from the national schistosomiasis surveillance sites of China from 2005 to 2019. The data included S. japonicum infections in humans, livestock, and O. hupensis. The spatiotemporal trends for schistosomiasis were detected using a Joinpoint regression model, with a standard deviational ellipse (SDE) tool, which determined the central tendency and dispersion in the spatial distribution of schistosomiasis. Further, more spatiotemporal clusters of S. japonicum infections in humans, livestock, and O. hupensis were evaluated by the Poisson model. Results: The prevalence of S. japonicum human infections decreased from 2.06% to zero based on data of the national schistosomiasis surveillance sites of China from 2005 to 2019, with a reduction from 9.42% to zero for the prevalence of S. japonicum infections in livestock, and from 0.26% to zero for the prevalence of S. japonicum infections in O. hupensis. Analysis using an SDE tool showed that schistosomiasis-affected regions were reduced yearly from 2005 to 2014 in the endemic provinces of Hunan, Hubei, Jiangxi, and Anhui, as well as in the Poyang and Dongting Lake regions. Poisson model revealed 11 clusters of S. japonicum human infections, six clusters of S. japonicum infections in livestock, and nine clusters of S. japonicum infections in O. hupensis. The clusters of human infection were highly consistent with clusters of S. japonicum infections in livestock and O. hupensis. They were in the 5 provinces of Hunan, Hubei, Jiangxi, Anhui, and Jiangsu, as well as along the middle and lower reaches of the Yangtze River. Humans, livestock, and O. hupensis infections with S. japonicum were mainly concentrated in the north of the Hunan Province, south of the Hubei Province, north of the Jiangxi Province, and southwestern portion of Anhui Province. In the 2 mountainous provinces of Sichuan and Yunnan, human, livestock, and O. hupensis infections with S. japonicum were mainly concentrated in the northwestern portion of the Yunnan Province, the Daliangshan area in the south of Sichuan Province, and the hilly regions in the middle of Sichuan Province. Conclusions: A remarkable decline in the disease prevalence of S. japonicum infection was observed in endemic schistosomiasis in China between 2005 and 2019. However, there remains a long-term risk of transmission in local areas, with the highest-risk areas primarily in Poyang Lake and Dongting Lake regions, requiring to focus on vigilance against the rebound of the epidemic. Development of high-sensitivity detection methods and integrating the transmission links such as human and livestock infection, wild animal infection, and O. hupensis into the surveillance-response system will ensure the elimination of schistosomiasis in China by 2030.
Реферат
Objective: To determine the spatiotemporal distribution of Schistosoma (S.) japonicum infections in humans, livestock, and Oncomelania (O.) hupensis across the endemic foci of China. Methods: Based on multi-stage continuous downscaling of sentinel monitoring, county-based schistosomiasis surveillance data were captured from the national schistosomiasis surveillance sites of China from 2005 to 2019. The data included S. japonicum infections in humans, livestock, and O. hupensis. The spatiotemporal trends for schistosomiasis were detected using a Joinpoint regression model, with a standard deviational ellipse (SDE) tool, which determined the central tendency and dispersion in the spatial distribution of schistosomiasis. Further, more spatiotemporal clusters of S. japonicum infections in humans, livestock, and O. hupensis were evaluated by the Poisson model. Results: The prevalence of S. japonicum human infections decreased from 2.06% to zero based on data of the national schistosomiasis surveillance sites of China from 2005 to 2019, with a reduction from 9.42% to zero for the prevalence of S. japonicum infections in livestock, and from 0.26% to zero for the prevalence of S. japonicum infections in O. hupensis. Analysis using an SDE tool showed that schistosomiasis-affected regions were reduced yearly from 2005 to 2014 in the endemic provinces of Hunan, Hubei, Jiangxi, and Anhui, as well as in the Poyang and Dongting Lake regions. Poisson model revealed 11 clusters of S. japonicum human infections, six clusters of S. japonicum infections in livestock, and nine clusters of S. japonicum infections in O. hupensis. The clusters of human infection were highly consistent with clusters of S. japonicum infections in livestock and O. hupensis. They were in the 5 provinces of Hunan, Hubei, Jiangxi, Anhui, and Jiangsu, as well as along the middle and lower reaches of the Yangtze River. Humans, livestock, and O. hupensis infections with S. japonicum were mainly concentrated in the north of the Hunan Province, south of the Hubei Province, north of the Jiangxi Province, and southwestern portion of Anhui Province. In the 2 mountainous provinces of Sichuan and Yunnan, human, livestock, and O. hupensis infections with S. japonicum were mainly concentrated in the northwestern portion of the Yunnan Province, the Daliangshan area in the south of Sichuan Province, and the hilly regions in the middle of Sichuan Province. Conclusions: A remarkable decline in the disease prevalence of S. japonicum infection was observed in endemic schistosomiasis in China between 2005 and 2019. However, there remains a long-term risk of transmission in local areas, with the highest-risk areas primarily in Poyang Lake and Dongting Lake regions, requiring to focus on vigilance against the rebound of the epidemic. Development of high-sensitivity detection methods and integrating the transmission links such as human and livestock infection, wild animal infection, and O. hupensis into the surveillance-response system will ensure the elimination of schistosomiasis in China by 2030.