Objective: To analyze the exposure level and the geographical distribution trend of toxicological indicators of rural drinking water in Shandong Province. Methods: The drawing method was used to randomly select no less than 60% villages and towns from 137 counties (cities, districts) of 17 cities in Shandong Province in 2015, and then 1-3 rural centralized water supply units were selected according to the circumstance of rural centralized water supply units in each village and town. In total, 735 villages and towns, 1 473 rural centralized water supply units were selected, and 1 473 water samples were collected. The water treatment process, water supply population and other circumstances of the rural centralized water supply units were investigated, the water quality was monitored, the content of toxicological indicators of drinking water in different areas was compared, and the trend surface isogram of excessive toxicological indicators was drawn. Results: The qualified rate of toxicological indicators in 1 473 water samples was 83.64% (n=1 232). The main toxicological indicators that affected the qualified rate of toxicological indicators of drinking water in rural areas in Shandong Province were nitrate and fluoride. The excessive rate of fluoride was 5.70% (n=84) and the exposed population was 1 736 709 (4.22%). The excessive rate of nitrate (as nitrogen) was 12.29% (n=181) and the exposed population was 1 393 612 (3.39%). The P₅0 content of fluoride in the eastern, middle and western regions was 0.24, 0.29 and 0.59 mg/L, respective;which was higher in the western region than in the east and the middle regions (P<0.05). There was no significant difference between the eastern and the middle regions (P>0.05). The P₅₀ content of nitrate (as nitrogen) in the eastern, middle and western regions was 8.00, 7.48, and 2.00 mg/L, which was higher in the eastern and middle regions than in the west region (P<0.05), there was no significant difference between the eastern and the middle regions (P>0.05). The trend surface isogram of nitrate and fluoride content showed that the content of nitrate (as nitrogen) in rural drinking water in the eastern region was significantly higher than that in the western region, especially there was a high peak area in the northeastern region, and this high content distribution extended diagonally to the central region, while the other regions were in a relatively low range. The content of fluoride in rural drinking water in the western region was significantly higher than that in the eastern region, and there were high peaks in the southwest and northwest regions, and the other regions were in a relatively low range. Conclusion The high exposed toxicological indicators in rural drinking water in Shandong Province were nitrate (as nitrogen) and fluoride, and their distribution showed obvious geographical distribution trend.

Objective:To establish a set of artificial intelligence (AI) verification rules for blood routine analysis.Methods:Blood routine analysis data of 18 474 hospitalized patients from the First Hospital of Jilin University during August 1st to 31st, 2019, were collected as training group for establishment of the AI verification rules,and the corresponding patient age, microscopic examination results, and clinical diagnosis information were collected. 92 laboratory parameters, including blood analysis report parameters, research parameters and alarm information, were used as candidate conditions for AI audit rules; manual verification combining microscopy was considered as standard, marked whether it was passed or blocked. Using decision tree algorithm, AI audit rules are initially established through high-intensity, multi-round and five-fold cross-validation and AI verification rules were optimized by setting important mandatory cases. The performance of AI verification rules was evaluated by comparing the false negative rate, precision rate, recall rate, F1 score, and pass rate with that of the current autoverification rules using Chi-square test. Another cohort of blood routine analysis data of 12 475 hospitalized patients in the First Hospital of Jilin University during November 1sr to 31st, 2023, were collected as validation group for validation of AI verification rules, which underwent simulated verification via the preliminary AI rules, thus performance of AI rules were analyzed by the above indicators. Results:AI verification rules consist of 15 rules and 17 parameters and do distinguish numeric and morphological abnormalities. Compared with auto-verification rules, the true positive rate, the false positive rate, the true negative rate, the false negative rate, the pass rate, the accuracy, the precision rate, the recall rate and F1 score of AI rules in training group were 22.7%, 1.6%, 74.5%, 1.3%, 75.7%, 97.2%, 93.5%, 94.7%, 94.1, respectively.All of them were better than auto-verification rules, and the difference was statistically significant ( P<0.001), and with no important case missed. In validation group, the true positive rate, the false positive rate, the true negative rate, the false negative rate, the pass rate, the accuracy, the precision rate, the recall rate and F1 score were 19.2%, 8.2%, 70.1%, 2.5%, 72.6%, 89.2%, 70.0%, 88.3%, 78.1, respectively, Compared with the auto-verification rules, The false negative rate was lower, the false positive rate and the recall rate were slightly higher, and the difference was statistically significant ( P<0.001). Conclusion:A set of the AI verification rules are established and verified by using decision tree algorithm of machine learning, which can identify, intercept and prompt abnormal results stably, and is moresimple, highly efficient and more accurate in the report of blood analysis test results compared with auto-vefication.