Prediction of immunotherapy response in idiopathic membranous nephropathy using deep learning-pathological and clinical factors.

Background: Owing to individual heterogeneity, patients with idiopathic membranous nephropathy (IMN) exhibit varying sensitivities to immunotherapy. This study aimed to establish and validate a model incorporating pathological and clinical features using deep learning training to evaluate the response of patients with IMN to immunosuppressive therapy. Methods: The 291 patients were randomly categorized into training (n = 219) and validation (n = 72) cohorts. Patch-level convolutional neural network training in a weakly supervised manner was utilized to analyze whole-slide histopathological features. We developed a machine-learning model to assess the predictive value of pathological signatures compared to clinical factors. The performance levels of the models were evaluated using the area under the receiver operating characteristic curve (AUC) on the training and validation tests, and the prediction accuracies of the models for immunotherapy response were compared. Results: Multivariate analysis indicated that diabetes and smoking were independent risk factors affecting the response to immunotherapy in IMN patients. The model integrating pathologic features had a favorable predictive value for determining the response to immunotherapy in IMN patients, with AUCs of 0.85 and 0.77 when employed in the training and test cohorts, respectively. However, when incorporating clinical features into the model, the predictive efficacy diminishes, as evidenced by lower AUC values of 0.75 and 0.62 on the training and testing cohorts, respectively. Conclusions: The model incorporating pathological signatures demonstrated a superior predictive ability for determining the response to immunosuppressive therapy in IMN patients compared to the integration of clinical factors.

[Pollution Characteristics and Health Risk Assessment of Atmospheric VOCs in Chengdu].

Volatile organic compounds (VOCs) were measured in atmospheric samples collected from urban and roadside atmospheric environments in Chengdu in September 2012. The composition, chemical reactivity, and concentration level and its variation characteristics of VOCs were studied, and the health risk of aromatic compounds was assessed. Results showed that the mean mass concentrations of total VOCs (TVOCs) were (108.57±52.43) µg·m-3 and (132.61±49.31) µg·m-3 for the urban and roadside atmospheric environments, respectively. The highest mass concentrations were observed for alkanes, followed by aromatics, alkenes, and alkynes. Aromatics and alkenes contributed more to ozone formation potential (OFP) of the urban and roadside atmospheric environments, and m/p-xylene, toluene, ethene, o-xylene, and propene were the key reactive species. The values of hazard quotient and hazard index were less than 1 for benzene, toluene, ethylbenzene, and o-xylene (BTEX), showing that they had no appreciable risk of non-cancer health effects on the exposed population. However, the value of cancer risk was above the safety threshold for benzene, showing that it was a potential cancer risk to the exposed population.

Characteristics, sources and health risk assessment of toxic heavy metals in PM2.5 at a megacity of southwest China.

Twenty trace elements in fine particulate matters (i.e., PM2.5) at urban Chengdu, a southwest megacity of China, were determined to study the characteristics, sources and human health risk of particulate toxic heavy metals. This work mainly focused on eight toxic heavy metal elements (As, Cd, Cr, Cu, Mn, Ni, Pb and Zn). The average concentration of PM2.5 was 165.1 ± 84.7 µg m(-3) during the study period, significantly exceeding the National Ambient Air Quality Standard (35 µg m(-3) in annual average). The particulate heavy metal pollution was very serious in which Cd and As concentrations in PM2.5 significantly surpassed the WHO standard. The enrichment factor values of heavy metals were typically higher than 10, suggesting that they were mainly influenced by anthropogenic sources. More specifically, the Cr, Mn and Ni were slightly enriched, Cu was highly enriched, while As, Cd, Pb and Zn were severely enriched. The results of correlation analysis showed that Cd may come from metallurgy and mechanical manufacturing emissions, and the other metals were predominately influenced by traffic emissions and coal combustion. The results of health risk assessment indicated that As, Mn and Cd would pose a significant non-carcinogenic health risk to both children and adults, while Cr would cause carcinogenic risk. Other toxic heavy metals were within a safe level.