Machine learning predicts the serum PFOA and PFOS levels in pregnant women: Enhancement of fatty acid status on model performance.

Human exposure to per- and polyfluoroalkyl substances (PFASs) has received considerable attention, particularly in pregnant women because of their dramatic changes in physiological status and dietary patterns. Predicting internal PFAS exposure in pregnant women, based on external and relevant parameters, has not been investigated. Here, machine learning (ML) models were developed to predict the serum concentrations of PFOA and PFOS in a large population of 588 pregnant participants. Dietary exposure characteristics, demographic parameters, and in particular, serum fatty acid (FA) data were used for the model development. The fitting results showed that the inclusion of FAs as covariates significantly improved the performance of the ML models, with the random forest (RF) model having the best predictive performance for PFOA (R2 = 0.33, MAE = 1.51 ng/mL, and RMSE = 1.89 ng/mL) and PFOS (R2 = 0.12, MAE = 2.65 ng/mL, and RMSE = 3.37 ng/mL). The feature importance analysis revealed that serum FAs greatly affected PFOA concentration in the pregnant women, with saturated FAs being associated with decreased PFOA levels and unsaturated FAs with increased levels. Comparison with one-compartment pharmacokinetic model further demonstrated the advantage of the ML models in predicting PFAS exposure in pregnant women. Our models correlate for the first time blood chemical concentrations with human FA status using ML, introducing a novel perspective on predicting PFAS levels in pregnant women. This study provides valuable insights concerning internal exposure of PFASs generated from external exposure, and contributes to risk assessment and management in pregnant populations.

Investigation on risk factors of haemorrhagic fever with renal syndrome (HFRS) in Xuancheng City in Anhui Province, Mainland China.

Haemorrhagic fever with renal syndrome (HFRS), a rodent-borne disease, is a major public health concern in both developed and developing countries. China is the most severe endemic country in the world, constituting 90% of the cases. Although the incidence of HFRS has substantively decreased in most areas of China, HFRS has rebounded remarkably in some epidemic areas. Xuancheng is one of these areas. In this study, we collected the case data reported recently in Xuancheng and designed a 1:3 case-control study. The Chi-square test, univariate and multivariate logistic regression analysis were performed. In all cases, farmers made up the highest proportion of occupations. And there were 20 variables with statistical significance including indoor hygienic conditions; the surrounding environment; whether bitten by rats at work and other criteria. In addition, exposure to rodents and rats bites is a high-risk factor for HFRS. Rodent density was calculated at 20.9% (159/760), the virus carrier rate was 9.4% (15/159) and the index of rats with a virus was about 2.0%. Exposure to rodents and insect bites is also high-risk factors for HFRS among local residents in Xuancheng. More importantly, during the flood years, the increased density of rodents led to an increased risk of human exposure to rodents. As our statistical analysis proves, targeted strategies should be developed and implemented to reduce the incidence of local diseases in the future.

Genetic characterization of the first detected human case of avian influenza A (H5N6) in Anhui Province, East China.

We compared complete genome sequences of two strains of an avian influenza A (H5N6) virus isolated from a patient in Anhui Province with those of other strains from GenBank and Global initiative on sharing all influenza data (GISAID). The HA gene of the isolated virus shared homology with that of A/chicken/Zhejiang/727155/2014 (H5N6) at the level of similarity of 98%. The six internal genes of the Anhui strains were close to those of H9N2 viruses from Zhejiang, Shandong, and Guangdong provinces, with a similarity of 99%. In addition, the similarity between the internal antigens (NP and MP) of the isolated H5N6 virus and H7N9 and H10N8 viruses was 99%. Based on the data of phylogenetic analysis, the H5N6 influenza virus isolated in Anhui Province belonged to clade 2.3.4.4. The virus was shown to have molecular characteristics of highly pathogenic avian influenza viruses, including eight glycosylation sites and an amino acid sequence of the HA protein cleavage site, PLRERRRKKR/GLF, containing multiple basic amino acids. Additionally, the stalk domain of the NA protein was found to have a deletion in NA stalk region (11 amino acids in N6, positions 58-68). Our study demonstrated that the H5N6 virus from Anhui Province represented a triple-reassortant virus and could be highly pathogenic to humans. The prevalence of this virus should be closely monitored.