[Prediction of trends for fine-scale spread of Oncomelania hupensis in Shanghai Municipality based on supervised machine learning models].

OBJECTIVE: To predict the trends for fine-scale spread of Oncomelania hupensis based on supervised machine learning models in Shanghai Municipality, so as to provide insights into precision O. hupensis snail control. METHODS: Based on 2016 O. hupensis snail survey data in Shanghai Municipality and climatic, geographical, vegetation and socioeconomic data relating to O. hupensis snail distribution, seven supervised machine learning models were created to predict the risk of snail spread in Shanghai, including decision tree, random forest, generalized boosted model, support vector machine, naive Bayes, k-nearest neighbor and C5.0. The performance of seven models for predicting snail spread was evaluated with the area under the receiver operating characteristic curve (AUC), F1-score and accuracy, and optimal models were selected to identify the environmental variables affecting snail spread and predict the areas at risk of snail spread in Shanghai Municipality. RESULTS: Seven supervised machine learning models were successfully created to predict the risk of snail spread in Shanghai Municipality, and random forest (AUC = 0.901, F1-score = 0.840, ACC = 0.797) and generalized boosted model (AUC= 0.889, F1-score = 0.869, ACC = 0.835) showed higher predictive performance than other models. Random forest analysis showed that the three most important climatic variables contributing to snail spread in Shanghai included aridity (11.87%), ≥ 0 °C annual accumulated temperature (10.19%), moisture index (10.18%) and average annual precipitation (9.86%), the two most important vegetation variables included the vegetation index of the first quarter (8.30%) and vegetation index of the second quarter (7.69%). Snails were more likely to spread at aridity of < 0.87, ≥ 0 °C annual accumulated temperature of 5 550 to 5 675 °C, moisture index of > 39% and average annual precipitation of > 1 180 mm, and with the vegetation index of the first quarter of > 0.4 and the vegetation index of the first quarter of > 0.6. According to the water resource developments and township administrative maps, the areas at risk of snail spread were mainly predicted in 10 townships/subdistricts, covering the Xipian, Dongpian and Tainan sections of southern Shanghai. CONCLUSIONS: Supervised machine learning models are effective to predict the risk of fine-scale O. hupensis snail spread and identify the environmental determinants relating to snail spread. The areas at risk of O. hupensis snail spread are mainly located in southwestern Songjiang District, northwestern Jinshan District and southeastern Qingpu District of Shanghai Municipality.

[Validation of a contact-free sleep apnea monitor in adults with obstructive sleep apnea].

Objective: To evaluate the diagnostic value of a contact-free sleep apnea monitor in Chinese adults with obstructive sleep apnea (OSA). Methods: One hundred and ninety-eight participants with snoring were recruited between July 2018 and May 2019 in Sleep Center of Peking University People's Hospital, using nocturnal polysomnography (PSG) and contact-free sleep apnea monitor simultaneously. We evaluated the difference between respiratory event index (REI) generated by contact-free sleep apnea monitor and PSG-Apnea-Hypopnea Index (AHI). We calculated the sensitivity and specificity of OSA diagnosis using the contact-free sleep apnea monitor by hypothesis testing for means, Pearson correlation coefficient and Bland-Altman plots. Then, we used the receiver operating characteristic (ROC) curve to find out the best cut-off of OSA diagnosis. Results: PSG-AHI and the REI of contact-free sleep apnea monitor showed no statistically significant difference [15.9 (4.7, 40.2) vs. 16.2 (6.1, 40.0), P=0.381], and they were significantly correlated (r=0.914, P<0.05), with mean difference of -0.06 (95%CI:-18.44, 18.31). The ROC curve showed that if REI ≥5 events/h was used as diagnostic criteria, the sensitivity and specificity of diagnosing OSA were 91.2% and 58.0%, respectively. The sensitivity and specificity of the contact-free sleep apnea monitor REI≥13.3 in diagnosing moderate and severe OSA were 90.1% and 71.1%, respectively. Conclusion: The REI obtained from the contact-free sleep apnea monitor showed a good agreement with the PSG-AHI, and therefore, the contact-free sleep apnea monitor can be used for the screening of patients with moderate and severe OSA.

[Epidemiological profiles of echinococcosis cases reported in the National Notifiable Disease Report System in non-endemic areas of China from 2004 to 2016].

OBJECTIVE: To investigate the epidemiological profiles of echinococcosis cases reported in non-endemic areas of China in the National Notifiable Disease Report System from 2004 to 2016, so as to provide insights into the development of effective surveillance and response measures. METHODS: The data pertaining to the echinococcosis cases reported in the National Notifiable Disease Report System in 22 non-endemic provinces of China from 2004 to 2016 were collected, and the epidemiological profiles of the reported echinococcosis cases were descriptively analyzed. RESULTS: A total of 462 echinococcosis cases were reported in the 22 non-endemic provinces of China from 2004 to 2016, and the number of reported cases increased with time (χ2 = 4.516, P = 0.034). During the 13-year period from 2004 to 2016, the highest number of echinococcosis cases was reported in central and eastern China (56.49%), followed by in northern and northeastern China (30.30%), and the highest number of echinococcosis cases was reported in Henan Province (99 cases). Among the 462 echinococcosis cases reported, there were 234 men and 228 women, and the mean age was (41.42 ± 16.03) years (range, 4 to 86 years), with the highest number of echinococcosis cases reported at ages of 20 to 50 years (63.20%). The highest proportion of occupations was farmers and herdsmen (36.15%), and the greatest source was from echinococcosis-endemic provinces (50.43%); in addition, 97.40% of the echinococcosis cases were reported by hospitals. CONCLUSIONS: Echinococcosis cases were reported in all 22 non-endemic provinces of China in the National Notifiable Disease Report System from 2004 to 2016, and the number of reported cases appeared an overall tendency for sporadicity and local increase with time. Screening of echinococcosis is recommended among famers and herdsmen at ages of 20 to 50 years from endemic regions by medical institutions in non-endemic regions for timely identification and treatment of echinococcosis cases.

[Spatiotemporal distribution of Oncomelania hupensis snail habitats in Anhui Province].

OBJECTIVE: To investigate the spatiotemporal distribution of Oncomelania hupensis snails and infected snails in the endemic areas of schistosomiasis in Anhui Province. METHODS: Based on the snail survey data in Anhui Province in 2016, the distribution of snails and infected snails were analyzed, and the spatial distribution of snails and spatial cluster patterns of infected snails were investigated in snail habitats in Anhui Province from 1950 to 2016. RESULTS: A total of 22 757 snail habitats and 5 004 infected snail habitats were identified in Anhui Province from 1950 to 2016, which appeared single-peak and double-peak patterns, with an inflection point seen in 1970. There were 141 000 hm2 historically accumulative snail habitats, 88.08% of which were firstly identified from 1950 to 1979, and totally 114 500 hm2 snail habitats were eradicated, 77.17% of which were eradicated from 1970 to 1999. There were 4 830 snail habitats identified until 2016, in which 1 051 were once detected with infected snails. In addition, 78.12% of current snail habitats had been present for over 40 years, and infected snails had been eliminated in 65.75% of the infected snail habitats within 10 years. There was a spatial autocorrelation of the living snail density in current snail habitats in Anhui Province (Moran's I = 0.196, Z = 139.63, P < 0.001), and local hotspot analysis showed spatial clusters of living snails density in snail habitats, with high-value clusters in south of the Yangtze River and low-value clusters in north of the Yangtze River. The 21 high-value clusters of living snail density with statistical significance were distributed along the Yangtze River basin and its branches. Spatiotemporal scan analysis revealed spatiotemporal clusters of infected snails in 4 current snail habitats. CONCLUSIONS: The current snail habitats have been present for a long period of time, and snails are difficult to be eliminated by chemical treatment alone, which requires the combination of environment improvements. There are spatial clusters of living snail density in current snail habitats in Anhui Province. The epidemic factors and risk of human and animal infections still remain in some clusters of historical infected snail habitats revealed by spatiotemporal scan analysis, which should be consid- ered as the key target areas for snail control in Anhui Province.