An evaluation of cervical maturity for Chinese women with labor induction by machine learning and ultrasound images.

BACKGROUND: To evaluate the improvement of evaluation accuracy of cervical maturity for Chinese women with labor induction by adding objective ultrasound data and machine learning models to the existing traditional Bishop method. METHODS: The machine learning model was trained and tested using 101 sets of data from pregnant women who were examined and had their delivery in Peking University Third Hospital in between December 2019 and January 2021. The inputs of the model included cervical length, Bishop score, angle, age, induced labor time, measurement time (MT), measurement time to induced labor time (MTILT), method of induced labor, and primiparity/multiparity. The output of the model is the predicted time from induced labor to labor. Our experiments analyzed the effectiveness of three machine learning models: XGBoost, CatBoost and RF(Random forest). we consider the root-mean-squared error (RMSE) and the mean absolute error (MAE) as the criterion to evaluate the accuracy of the model. Difference was compared using t-test on RMSE between the machine learning model and the traditional Bishop score. RESULTS: The mean absolute error of the prediction result of Bishop scoring method was 19.45 h, and the RMSE was 24.56 h. The prediction error of machine learning model was lower than the Bishop score method. Among the three machine learning models, the MAE of the model with the best prediction effect was 13.49 h and the RMSE was 16.98 h. After selection of feature the prediction accuracy of the XGBoost and RF was slightly improved. After feature selection and artificially removing the Bishop score, the prediction accuracy of the three models decreased slightly. The best model was XGBoost (p = 0.0017). The p-value of the other two models was < 0.01. CONCLUSION: In the evaluation of cervical maturity, the results of machine learning method are more objective and significantly accurate compared with the traditional Bishop scoring method. The machine learning method is a better predictor of cervical maturity than the traditional Bishop method.

Osseous Rosai-Dorfman disease of tibia in children: A case report.

BACKGROUND: Rosai-Dorfman disease (RDD), or sinus histiocytosis with massive lymphadenopathy, is a benign histiocytic disorder. Extranodal involvement is common, occurring in > 40% of patients, but bone involvement occurs in < 10% of cases. In addition, primary bone RDD is extremely rare. The majority of patients are adolescents and young adults, and the mean age at onset is 20-years-old. CASE SUMMARY: We report an 8-year-old Chinese girl who presented to our hospital with an insidious onset of swelling and pain in the middle shaft of her right tibia for 4 mo. We performed total surgical resection of the right tibia lesion and allograft transplantation. A good prognosis was confirmed at the 6 mo follow-up. Pain and swelling symptoms were totally relieved, range of motion of her right knee and ankle returned to normal, and there was no clinical evidence of lesion recurrence at last follow up. Our case is the second reported case of osseous RDD without lymphadenopathy in the shaft of the tibia of a child. CONCLUSION: Extranodal RDD is a rare disease and can be misdiagnosed easily. Lesion resection and allograft transplantation are an option to treat extranodal RDD in children with good short term result. Pediatric orthopedist should be aware of this rare disease, especially extranodal involvement.

Fuzzy Multi-SVR Learning Model for Reliability-Based Design Optimization of Turbine Blades.

The effectiveness of a model is the key factor of influencing the reliability-based design optimization (RBDO) of multi-failure turbine blades in the power system. A machine learning-based RBDO approach, called fuzzy multi-SVR learning method, was proposed by absorbing the strengths of fuzzy theory, support vector machine of regression (SVR), and multi-response surface method. The model of fuzzy multi-SVR learning method was established by adopting artificial bee colony algorithm to optimize the parameters of SVR models and considering the fuzziness of constraints based on fuzzy theory, in respect of the basic thought of multi-response surface method. The RBDO model and procedure with fuzzy multi-SVR learning method were then resolved and designed by multi-objective genetic algorithm. Lastly, the fuzzy RBDO of a turbine blade with multi-failure modes was performed regarding the design parameters of rotor speed, temperature, and aerodynamic pressure, and the design objectives of blade stress, strain, and deformation, and the fuzzy constraints of reliability degree and boundary conditions, as well. It is revealed (1) the stress and deformation of turbine blade are reduced by 92.38 MPa and 0.09838 mm, respectively. (2) The comprehensive reliability degree of the blade was improved by 3.45% from 95.4% to 98.85%. (3) It is verified that the fuzzy multi-SVR learning method is workable for the fuzzy RBDO of complex structures just like a multi-failure blade with high modeling precision, as well as high optimization, efficiency, and accuracy. The efforts of this study open a new research way, i.e., machine learning-based RBDO, for the RBDO of multi-failure structures, which expands the application of machine learning methods, and enriches the mechanical reliability design method and theory as well.

[Arsenic Content and Speciation in the Surficial Sediments of Liangshui River in Beijing].

Arsenic (As) content and speciation in the surface sediments of the typical urban river ( Liangshui River) with unconventional water sources in Beijing were investigated by different methods, including BCR three-step sequential extraction procedure, enrichment factor (EF), risk assessment code (RAC) and sediment quality guidelines (SQGs). The results showed that total As contents in the surface sediments ranged from 2.18 mg x kg(-1) to 22.5 mg x kg(-1), with an average of 6.01 mg x kg(-1), and most of them were lower than the soil background value. In terms of speciation, As mainly existed in B4 ( with an average content of 3. 93 mg x kg(-1)), and the contents of the four forms followed the sequence: B4 > B2 > B3 > B1. In addition, the percentage of biological available As was 39. 61%. The EF values due to As showed there was not significant enrichment in most studied sediments. The analysis results of RAC showed that the surface sediments from 60% of the sampling sites posed moderate risk, and 40% of the sampling points showed low risk. The results of SQGs showed that As content in the surface sediments from 55% of the sampling points was below the threshold effect level (TEL), and that in 40% of the sampling points was between TEL and probable effects level (PEL).

[Research of the Stormwater Runoff and Pollution Characteristics in Rural Area of Yuhang District, Hangzhou].

In order to investigate the pollution characteristics of stormwater runoff in the southern developed rural region, the runoff samples were collected from four different underlying surfaces during three storm events in Caoqiao and Pujia Tou, which are two typical villages and are located in Yuhang District of Hangzhou. The content of nutrition (nitrogen and phosphorus) and heavy metals (Mn, Cu, Zn, Ni, Cr, Cd, As, Pb) in the simples were analyzed, and the difference of EMC ( event mean concentration) and pollution load of the contaminants in the runoff on different underlying surfaces were compared. The results showed that the EMC of TSS, COD, NH4(+)-N, TP and TN were 16.19, 21.01, 0.74, 1.39 and 2.39 mg x L(-1) in the Caoqiao, respectively; as to Pujia Tou, they were 3.10, 15.69, 0.90, 0.78 and 3.58 mg x L(-1), respectively. The content of heavy metals was all lower than the national surface water quality of two type water in the runoff. Compared with the quality standards for surface water, the EMC of TP was 9 times and 3. 5 times higher and TN was 1. 8 times and 1. 2 times higher in two areas. Besides, the pollution loads of TSS and COD were the highest in farmland.

[Characterization and optimization of the NaOH-EDTA extracts for solution 31P-NMR analysis of organic phosphorus in river sediments].

Optimization and mechanism of NaOH-EDTA extraction solutions were studied in phosphorus (P) pollution river sediments, which were Fe, Al-rich sediment, by solution 31P nuclear magnetic resonance spectroscopy (31P-NMR). Different proportions of NaOH and EDTA showed different extraction efficiency on total P (TP) and organic P (Po) in the sediment. The concentration of Po in NaOH + EDTA extract was higher than that in NaOH extract. The mechanism was that the TP and Po were released under the conditions of EDTA chelating with Fe and Al. The concentration of TP and Po were the highest in 1.00 mol x L(-1) NaOH +75 mmol x L(-1) EDTA extract and 0.25 mol x L(-1) NaOH + 50 mmol x L(-1) EDTA extract, which were 3.88 mg x g(-1) and 0.24 mg x g(-1), respectively. The extractions of Fe, Mn, Ca, Mg, Al were increasing as the EDTA increased under the same NaOH concentration. Extraction efficiency of Fe, Mn, Ca showed negative correlation with the pH of the extracting solution (P < 0.01). Exponential relationship was found between the extraction of Al and the pH of the extraction solution (P < 0.01) because of the AlO2- and EDTA-Al complex. The quality of spectra of NaOH-EDTA extract was better than that of NaOH extract. Six P species were detected in different extractions, including phosphonates, orthophosphate, pyrophosphate, orthophosphate monoesters, phospholipids and deoxyribonucleic acids. Therefore, 0. 25 mol x L(-1) NaOH + 50 mmol x L(-1) EDTA was the optimization extraction solution for Po analysis in Fe and Al-rich river sediment by 31P-NMR.

[Heavy metals distribution and risk assessment of sediments in the riverine wetland of Sanmenxia Reservoir].

The survey for contents and fractions of heavy metal in sediments of riverine wetland in Sanmenxia Reservoir were carried out. Sediment pollution index was applied to assess the potential ecological risk and mass fraction of heavy metal in surface sediment was conducted for release risk assessment. The results showed that the total concentrations of Cr, Ni, Cu, Zn, Cd and Pb ranged in 25.8-68.5, 12.1-36.7, 3.25-48.74, 33.5-472.4, 0.16-0.69 and 9.04-90.74 mg x kg(-1), respectively. The heavy metal contents in the sediments increased obviously from the upper reaches of reservoir to Sanmenxia dam. The concentrations of Ni, Cu, Zn, Cd, Pb in sediments were higher in lower reach located after Weihe River than those of the upstream. The Weihe River was the biggest branch of Yellow River, and heavy metals accumulated obviously in the sediments of typical polluted branch (Hongnongjian River) , which might be attributed to the long-term discharge of industrial wastewater. The sediment pollution index (SPI) of Sanmenxia Reservoir ranged from 1.83 to 7.39, with an average value for 3.11. Sediment pollution aggravated in the downstream after Weihe River flowed in, and SPI reached 6.33 in Hongnongjian River mouth for medium risk. The exchangeable and carbonates fraction of Cd, Cu and Pb mass fractions in surface sediments accounted for 63.8%-85.7%, 6.58%-22.62% and 10.6%-28.9%, respectively. The pollutants discharge in branches caused heavy metal accumulation, ecological risk aggravation in lower reach of Sanmenxia basin. And the release risk followed the sequence Cd > Pb > Cu > Ni in surface sediment. The conclusions of this article supplied reference and basis for sediment pollution treatment and in situ remediation.

[Temporal and spatial variation of nitrogen and phosphorus and eutrophication assessment in downstream river network areas of North Canal River Watershed].

Based on the water quality survey for one year in the downstream river network areas of North Canal River Watershed, variation features of inorganic nitrogen (N) and phosphorus (P) were analyzed, and water eutrophication degree of river network areas was also assessed. The results showed that the average concentration of TN was 12.50 mg x L(-1) (NH4(+)-N, 67.41%); TP was 1.45 mg x L(-1) (SRP, 80.81%). The temporal and spatial variations of N and P in the river network areas were obvious. Various forms of TN and NO3(-)-N concentrations almost had a similar change by month; NH4(+)-N was a little different; TP and SRP also had a similar change. The concentrations of N and P all decreased gradually from water coming region to water leaving region, TN, NH4(+)-N and NO3(-)-N decreased from 19.30, 13.22 and 2.19 mg x L(-1) to 7.98, 4.45 and 1.50 mg x L(-1) on average, respectively; TP and SRP were from 1.95 and 1.59 mg x L(-1) to 1.11 and 0.91 mg x L(-1). Water eutrophication degrees of river network areas were all the highest level at both temporal and spatial scale.

[Construct of Yangtze-Huai River rural areas ecological drainage system and its retention effect on pollutants].

Ecological drainage system (EDS) including ditches, ponds and wetland was constructed at the Paifangchen village on the north of Chaohu Lake, Anhui, and its retention effect on pollution was investigated. With the comprehensive function of sewage discharge, collecting and process, the system could intercept runoff pollutants effectively. The results acquired from 3 rainfall events showed that the retention rates of EDS to TSS, COD, TP and TN were 78.2%, 57.8%, 55.5% and 64.2% respectively, and the concentrations at outflow of the system to TSS, COD, TP and NH4(+) -N were 23.5, 66.3, 0.49 and 3.03 mg x L(-1) separately, met the first standard of "Integrated Wastewater Discharge Standards". Ponds were the important unit of EDS and the daily water quality concentrations of TSS, COD, TP and TN were 28.0, 31.2, 0.47 and 4.65 mg x L(-1) respectively, met the V standard of "Environment Quality Standards for Surface Water" basically.

[Studies on the properties and co-immobilization of manganese peroxidase].

White-rot fungus manganese peroxidase (MnP) oxidizes a wide range of substrates, rendering it an interesting enzyme for potential applications. The stability of MnP can be improved by immobilization. With sodium alginate, gelatin, or chitosan as a carrier, and glutaraldehyde as the crosslinking agent, MnP was co-immobilized using the embed-crosslinked method and the adsorb-crosslinked method. The immobilization conditions and the partial properties of the three immobilized enzymes were investigated. When compared with the free enzyme, the optimum pH values and the temperatures of the three immobilized MnPs carried by alginate, gelatin, and chitosan were respectively shifted from 7.0 to 5.0, 5.0, 3.0 and from 35 degrees C to 75 degrees C , 55 degrees , 75 degrees C . The thermostabilities of the three immobilized MnPs were considerably better than that of the native enzyme. The chitosan-decreased by less than 5% even after repeated use for 6 - 9 times. The ability of decolorizing azo dyes in static and shaky situation by gelatin-immobilized MnP approached to the free enzyme, and there was no loss of enzyme activity during 2 repeated batch reactions.