Prediction of NFT Sale Price Fluctuations on OpenSea Using Machine Learning Approaches

The rapid expansion of the non-fungible token(NFT)market has attracted many investors.However,studies on the NFT price fluctuations have been relatively limited.To date,the machine learning approach has not been used to demonstrate a specific error in NFT sale price fluctuation prediction.The aim of this study was to develop a prediction model for NFT price fluctuations using the NFT trading information obtained from OpenSea,the world’s largest NFT marketplace.We used Python programs to collect data and summarized them as:NFT information,collection information,and related account information.AdaBoost and Random Forest(RF)algorithms were employed to predict the sale price and price fluctuation of NFTs using regression and classification models,respectively.We found that the NFT related account information,especially the number of favorites and activity status of creators,confer a good predictive power to both the models.AdaBoost in the regression model had more accurate predictions,the root mean square error(RMSE)in predicting NFT sale price was 0.047.In predicting NFT sale price fluctuations,RF performed better,which the area under the curve(AUC)reached 0.956.We suggest that investors should pay more attention to the information of NFT creators.We anticipate that these prediction models will reduce the number of investment failures for the investors.

Association between adjuvant chemotherapy and survival in stage I gastric cancer patients after curative resection

Background:The efficacy of adjuvant chemotherapy(AC)on survival outcomes of patients with stage I gastric cancer(GC)after curative resection remains controversial.We aimed to determine whether these patients would benefit from AC.Methods:This retrospective study included patients with pathologically confirmed stage I GC who underwent curative resection between November 2010 and December 2020.Patients were divided into AC and non-AC groups,then a 1:1 propensity score matching(PSM)analysis was performed to minimize the selection bias.Potential risk factors including age,pN stage,pT stage,lymphovascular invasion,perineural invasion,tumor size,histological type,and carcinoembryonic antigen level were used as matching covariates.The recurrence-free survival(RFS)and disease-specific survival(DSS)were compared between groups using the Kaplan–Meier method.Results:A total of 902 consecutive patients were enrolled and 174(19.3%)patients were treated with AC.PSM created 123 pairs of patients.Before PSM,patients receiving AC had lower 10-year RFS rates(90%vs 94.6%,P=0.035)than those who did not receive AC;the two groups had similar 10-year DSS rates(93.8%vs 95.0%,P=0.240).After PSM,there were no statistical differences in the 10-year RFS(90.9%vs 93.0%,P=0.507)or DSS rates(93.5%vs 93.6%,P=0.811)between the two groups.Similar results were found in the stage IA and IB subgroups.Moreover,these findings were not affected by AC cycles.Conclusions:The addition of AC could not provide survival benefits for patients with stage I GC after surgery and follow-up is thus recommended.However,large-scale randomized clinical trials are required.

Distribution and potential ecological risk of heavy metals in the typical eco-units of Haihe River Basin

The distribution and characteristics of seven heavy metals in sediments located in the typical ecological units （eco-units） （e.g., rivers, lakes, and estuaries） of Haihe River Basin were analyzed. The Hakanson potential ecological risk index was used for ecological risk assessment. The results indicated that the concentration scales of As, Hg, Cr, Cd, Pb, Cu, and Zn in the eco-units were 2.08 to 24.80 mg·g-1, 0.01 to 1135.50 mg·g-1, 28.70 to 152.73mg·g-1, 0.03 to 195765.83mg·g-1, 8.65 to 157.82mg·g-1, 6.47 to 178.61mg·g-1, and 21.09 to 1076.25 mg·g-1, respectively. The maximum concentra- tions of Hg, Cd, and Zn showed higher levels than other water bodies around the world. Hg and Cd have high concentrations in Zhangweinanhe River （1135.50 and 195765.83mg·g-1, respectively） and Haihe Estuary （790.50 and 548.47 mg·g-1, respectively）. According to the ecological factor, Cd and Hg showed very strong ecological risks. The seven heavy metals, namely, Cd, Hg, As, Cr, Pb, Cu, and Zn, exhibited ecological risk levels in descending order. Based on the potential ecological risk index, Luanhe River and Baiyangdian Lake had moderate ecological risks, whereas every site in Zhangweinanhe River and Haihe Estuary had substantial risk levels. The risk order of the typical eco-units are as follows： Zhangweinan River （2278345.68） 〉 Estuary （161914.74） 〉 Luanhe River （191.54）〉Baiyangdian Lake （120.95）. These results provided a scientific basis for water environment improve- ment and risk management of the Haihe River Basin.

Biologic risk and source diagnose of 16 PAHs from Haihe River Basin, China

Surface sediments of rivers can exhibit spatial and temporal variations in contaminant concentrations that may significantly affect risk evaluations. As to pollution control and remediation of watershed, large-scale and further background data on PAHs in China were required urgently. Spatial distribution and compositional character- istics of 16 polycyclic aromatic hydrocarbons （PAHs） in surface sediments from Haihe River Basin were investi- gated. A method based on effects range （ER） was used to assess ecosystem risk of ZPAHs （the total of 16 PAH） sensitively and accurately. The results indicated that ∑PAHs content levels ranged from 257 to 16901 μg·kg-1 dry weight. The lower tings predominated in the samples, and 2-, 3-, 4-, 5- and 6-ring PAHs accounted for 12%, 21%, 30%, 30%, and 7% respectively in total PAHs. The ratio of F1 / （F1 ＋ Py） uniformly distributed in the interval 0.20- 0.80, indicating that it may be affected by petroleum origin, oil combustion, biomass and coal combustion jointly. ∑PAHs in Cetian （S6）, Dongwushi （S19）, Handan （S20）, Aixinzhuang （S21） and Tianjin （S37） exceeded effects range low （ERL）, in which biologic effects were in a medium level with an adverse effect on biologic organisms. Thus, it is necessary to strengthen the PAHs monitoring and research of the Haihe River Basin.

The associations of lens power with age, axial length and type 2 diabetes mellitus in Chinese adults aged 50 years and above

Background:To investigate the associations of lens power with age,axial length(AL),and type 2 diabetes mellitus(DM)inChineseadultsaged5oandabove.Methods:Random clustering sampling was used to identify adults aged 50 years and above in urban regions of Shanghai.The participants underwent a comprehensive ophthalmic examination including subjective refraction,autorefraction,and IOL-Master.The crystalline lens power was calculated using Bennett's formula.Results:A total of 4177 adults were included.A linear decrease in lens power was observed both with age and with AL,followed by a stop of lens power loss after the age of 70 or when AL≥25 mm,respectively.Participants with type 2 DM presented higher lens power(0.43 diopter(D),P<0.001)and thicker lens thickness(0.06 mm,P<0.001).In multivariate regression models,there was a positive correlation between lens power and type 2 DM when age<75 years(P<0.001)or AL<25 mm(P<0.001)after adjusting for other factors,while no significant association was found in participants aged≥75 years(P=0.122)or with AL≥25 mm(P=0.172).Conclusions:The lens power in adults aged 50 and above exhibited two stages with age and with AL.Type 2 DM caused an increase in lens power,which was not seen in participants aged≥75 years or with AL≥25 mm.

The associations of lens power with age,axial length and type 2 diabetes mellitus in Chinese adults aged 50 and above

Background:To investigate the associations of lens power with age,axial length(AL),and Type 2 diabetes mellitus(DM)in Chinese adults aged 50 and above.Methods:Random clustering sampling was used to identify adults aged 50 years and above in urban regions of Shanghai.The participants underwent a comprehensive ophthalmic examination including subjective refraction,autorefraction,and IOL-Master.The crystalline lens power was calculated using Bennett’s formula.Results:A total of 4177 adults were included.A linear decrease in lens power was observed both with age and with AL,followed by a stop of lens power loss after the age of 70 or when AL≥25 mm,respectively.Participants with Type 2 DM presented higher lens power(0.43 diopter(D),p<0.001)and thicker lens thickness(0.06 mm,p<0.001).In multivariate regression models,there was a positive correlation between lens power and Type 2 DM when age<75 years(p<0.001)or AL<25 mm(p<0.001)after adjusting for other factors,while no significant association was found in participants aged≥75 years(p=0.122)or with AL≥25 mm(p=0.172).Conclusions:The lens power in adults aged 50 and above exhibited two stages with age and with AL.Type 2 DM caused an increase in lens power,which was not seen in participants aged≥75 years or with AL≥25 mm.