Search

Background: Schistosomiasis japonica represents a significant public health concern in South Asia. There is an urgent need to optimize existing schistosomiasis diagnostic techniques. This study aims to develop models for the different stages of liver fibrosis caused by Schistosoma infection utilizing ultrasound radiomics and machine learning techniques. Methods: From 2018 to 2022, we retrospectively collected data on 1,531 patients and 5,671 B-mode ultrasound images from the Second People's Hospital of Duchang City, Jiangxi Province, China. The datasets were screened based on inclusion and exclusion criteria suitable for radiomics models. Liver fibrosis due to Schistosoma infection (LFSI) was categorized into four stages: grade 0, grade 1, grade 2, and grade 3. The data were divided into six binary classification problems, such as group 1 (grade 0 vs. grade 1) and group 2 (grade 0 vs. grade 2). Key radiomic features were extracted using Pyradiomics, the Mann-Whitney U test, and the Least Absolute Shrinkage and Selection Operator (LASSO). Machine learning models were constructed using Support Vector Machine (SVM), and the contribution of different features in the model was described by applying Shapley Additive Explanations (SHAP). Results: This study ultimately included 1,388 patients and their corresponding images. A total of 851 radiomics features were extracted for each binary classification problems. Following feature selection, 18 to 76 features were retained from each groups. The area under the receiver operating characteristic curve (AUC) for the validation cohorts was 0.834 (95% CI: 0.779–0.885) for the LFSI grade 0 vs. LFSI grade 1, 0.771 (95% CI: 0.713–0.835) for LFSI grade 1 vs. LFSI grade 2, and 0.830 (95% CI: 0.762–0.885) for LFSI grade 2 vs. LFSI grade 3. Conclusion: Machine learning models based on ultrasound radiomics are feasible for classifying different stages of liver fibrosis caused by Schistosoma infection. Author summary: Schistosomiasis is a devastating disease caused by parasitic worms, leading to stunting, reduced learning ability in children, and impaired work capacity in adults. Currently, there is no ideal staging system to assess schistosomiasis-related liver conditions. Advances in machine learning can help us understand and evaluate liver ultrasound images in entirely new dimensions. Regions with high infection rates are predominantly underdeveloped and characterized by a scarcity of medical resources, where B-mode ultrasound equipment serves as one of the primary diagnostic tools. This study aims to develop an intelligent recognition model based on ultrasound radiomics and machine learning to provide a basis for the ultrasound diagnosis of schistosomiasis. [ABSTRACT FROM AUTHOR]

Objective: To understand the epidemiological distribution characteristics of mountain-type zoonotic visceral leishmaniasis (MT-ZVL) in Yangquan City, Shanxi Province, China, from 2006 to 2021, to explore the influencing factors leading to the re-emergence of the epidemic, and to provide a basis for the formulation of targeted control strategies. Methods: Case information spanning from 2006 to 2021 in Yangquan City was collected for a retrospective case-control study conducted from June to September 2022. A 1:3 matched ratio was employed. A questionnaire was utilized to gather data on basic information, demographic characteristics, awareness of MT-ZVL knowledge, residence, and dog breeding and living habits. The study employed a multifactorial conditional stepwise logistic regression model to analyze the influencing factors. Results: A total of 508 subjects was analyzed. Risk factors for MT-ZVL included the use of soil/stone/concrete as building materials (OR = 3.932), presence of nearby empty/stone stack houses (OR = 2.515), dog breeding (OR = 4.215), presence of stray dogs (OR = 2.767), and neighbor's dog breeding (OR = 1.953). Protective factors comprised knowledge of MT-ZVL (OR = 0.113) and using mosquito repellents (OR = 0.388). The findings indicate significant associations between environmental and behavioral factors and MT-ZVL incidence in Yangquan City, Shanxi Province, China, from 2006 to 2021. These results underscore the importance of public awareness campaigns and targeted interventions aimed at reducing exposure to risk factors and promoting protective measures to mitigate the re-emergence of MT-ZVL outbreaks. Conclusion: House building materials, presence of neighboring empty houses, breeding domestic dogs and distribution of stray dogs surrounding the home are risk factors for MT-ZVL. Awareness of MT-ZVL and implementation of preventive measures during outdoor activities in summer and autumn are protective and may reduce the risk of MT-ZVL. Author summary: In recent years, a rapid reemergence of mountain-type zoonotic visceral leishmaniasis (MT-ZVL) has been seen in the extension region of the Loess Plateau that had previously achieved elimination in China. In this study, we investigate the epidemiological characteristics of MT-ZVL and identify the factors associated with the rapid rise in MT-ZVL epidemics using a case-control design. A questionnaire was used to collect basic information, demographic characteristics, awareness of MT-ZVL knowledge, residence, and dog breeding and living habits. A multifactorial conditional stepwise logistic regression model was used to analyze the influencing factors. The study revealed that there has been a rising trend in the MT-ZVL endemic areas. House building materials, presence of neighboring empty houses, breeding domestic dogs and distribution of stray dogs surrounding the home are risk factors for MT-ZVL. Awareness of MT-ZVL and implementation of preventive measures during outdoor activities in summer and autumn are protective and may reduce the risk of MT-ZVL. We believe that our study makes a significant contribution to the literature to develop strategy for control the ongoing local transmission of MT-ZVL in hill districts. By analyzing the epidemiological characteristics and influencing factors of MT-ZVL, this research provides a basis for further optimizing the targeted control strategies. [ABSTRACT FROM AUTHOR]