Solving the class imbalance problem using ensemble algorithm: application of screening for aortic dissection.

BACKGROUND: Imbalance between positive and negative outcomes, a so-called class imbalance, is a problem generally found in medical data. Despite various studies, class imbalance has always been a difficult issue. The main objective of this study was to find an effective integrated approach to address the problems posed by class imbalance and to validate the method in an early screening model for a rare cardiovascular disease aortic dissection (AD). METHODS: Different data-level methods, cost-sensitive learning, and the bagging method were combined to solve the problem of low sensitivity caused by the imbalance of two classes of data. First, feature selection was applied to select the most relevant features using statistical analysis, including significance test and logistic regression. Then, we assigned two different misclassification cost values for two classes, constructed weak classifiers based on the support vector machine (SVM) model, and integrated the weak classifiers with undersampling and bagging methods to build the final strong classifier. Due to the rarity of AD, the data imbalance was particularly prominent. Therefore, we applied our method to the construction of an early screening model for AD disease. Clinical data of 523,213 patients from the Institute of Hypertension, Xiangya Hospital, Central South University were used to verify the validity of this method. In these data, the sample ratio of AD patients to non-AD patients was 1:65, and each sample contained 71 features. RESULTS: The proposed ensemble model achieved the highest sensitivity of 82.8%, with training time and specificity reaching 56.4 s and 71.9% respectively. Additionally, it obtained a small variance of sensitivity of 19.58 × 10-3 in the seven-fold cross validation experiment. The results outperformed the common ensemble algorithms of AdaBoost, EasyEnsemble, and Random Forest (RF) as well as the single machine learning (ML) methods of logistic regression, decision tree, k nearest neighbors (KNN), back propagation neural network (BP) and SVM. Among the five single ML algorithms, the SVM model after cost-sensitive learning method performed best with a sensitivity of 79.5% and a specificity of 73.4%. CONCLUSIONS: In this study, we demonstrate that the integration of feature selection, undersampling, cost-sensitive learning and bagging methods can overcome the challenge of class imbalance in a medical dataset and develop a practical screening model for AD, which could lead to a decision support for screening for AD at an early stage.

Construction of Z-scheme g-C3N4 / MnO2 /GO ternary photocatalyst with enhanced photodegradation ability of tetracycline hydrochloride under visible light radiation.

A facile wet-chemical method was adopted to synthesize g-C3N4/MnO2/GO heterojunction photocatalyst for visible-light photodegradation of tetracycline hydrochloride (TC). The addition of MnO2 and GO increased the absorption of visible light and the specific surface area of the photocatalyst. The results of photoluminescence, electrochemical impedance spectroscopy, and photocurrent response indicated that CMG-10 had the lowest electron-hole recombination probability, which was beneficial for the photocatalytic reaction. The ternary photocatalyst exhibited enhanced photoelectric performance and superior photocatalytic activity with 91.4% removal of TC (10 mg/L) under a mere 60 min visible light illumination, which showed enhanced photocatalytic degradation when compared with binary (CM, 77.95%; CG, 78.83%) and single (C3N4, 55.5%; MnO2, 36.41%) photocatalysts. A pH of 6 was optimal for the CMG-10 photocatalytic degradation of TC, and the optimal photocatalyst dosage was 0.5 g/L. Common coexisting ions influenced the removal of TC by influencing the production of active species. The catalyst is stable and reusable with only a 10% reduction in removal efficiency after four cycles. According to the active species analysis, the Z-scheme mechanism was a charge transfer behavior in the composite photocatalyst, which could prevent the recombination of photogenerated carriers. This study presents a photocatalytic approach to the effective removal of TC from water bodies, which provides practical implications to advance the use of photocatalytic technology in the restoration of aqueous environmental pollution.

Aortic Dissection Auxiliary Diagnosis Model and Applied Research Based on Ensemble Learning.

Aortic dissection (AD), a dangerous disease threatening to human beings, has a hidden onset and rapid progression and has few effective methods in its early diagnosis. At present, although CT angiography acts as the gold standard on AD diagnosis, it is so expensive and time-consuming that it can hardly offer practical help to patients. Meanwhile, the artificial intelligence technology may provide a cheap but effective approach to building an auxiliary diagnosis model for improving the early AD diagnosis rate by taking advantage of the data of the general conditions of AD patients, such as the data about the basic inspection information. Therefore, this study proposes to hybrid five types of machine learning operators into an integrated diagnosis model, as an auxiliary diagnostic approach, to cooperate with the AD-clinical analysis. To improve the diagnose accuracy, the participating rate of each operator in the proposed model may adjust adaptively according to the result of the data learning. After a set of experimental evaluations, the proposed model, acting as the preliminary AD-discriminant, has reached an accuracy of over 80%, which provides a promising instance for medical colleagues.

A review of metal organic framework (MOFs)-based materials for antibiotics removal via adsorption and photocatalysis.

Antibiotic abuse has led to serious water pollution and severe harm to human health; therefore, there is an urgent need for antibiotic removal from water sources. Adsorption and photodegradation are two ideal water treatment methods because they are cheap, simple to operate, and reusable. Metal organic frameworks (MOFs) are excellent adsorbents and photocatalysts because of their high porosity, adaptability, and good crystal form. The aim of this study is to suggest ways to overcome the limitations of adsorption and photocatalysis treatment methods by reviewing previous applications of MOFs to antibiotic adsorption and photocatalysis. The different factors influencing these processes are also discussed, as well as the various adsorption and photocatalysis mechanisms. This study provides a valuable resource for researchers intending to use MOFs to remove antibiotics from water bodies.

Reduced graphene oxide modified Z-scheme AgI/Bi2MoO6 heterojunctions with boosted photocatalytic activity for water treatment originated from the efficient charge pairs partition and migration.

In order to enhance degradation of harmful organic pollutants like Rhodamine B (RhB) dye under visible-light irradiation (λ >420 nm), a silver iodide/reduced graphene oxide/bismuth molybdate (AgI/rGO/Bi2MoO6) Z-scheme heterojunction photocatalyst was synthesized by a solvothermal process combined with an in-situ precipitation technique. The AgI (15 wt.%)/rGO/Bi2MoO6 (AGBMO-15) photocatalyst with a dosage of 0.5 g/L exhibited the highest photocatalytic activity with 98.0% RhB removal under an initial concentration of 10 mg/L within 30 min. This removal rate was approximately 65.8%, 57.7%, and 72.7% higher than that for a rGO/Bi2MoO6 (GBMO) binary composite, pure AgI powder, and pristine Bi2MoO6 nanoplates, respectively. The novel photocatalyst achieved approximately three times higher photocatalytic degradation within a shorter period of visible-light irradiation than pure Bi2MoO6. Through photoluminescence analysis and trapping experiments, this outstanding performance was attributed to the efficient separation of photogenerated electron-hole pairs owing to an internal electric field at the contact interface of AgI and Bi2MoO6, which generated more superoxide radical anions (•O2-) as primary reactive species to promote RhB degradation. Meanwhile, the rGO participated in the capture of visible-light and played a role of solid electronic medium at the AgI/Bi2MoO6 interface, which realized an effective Z-scheme electron transfer path, avoided the self oxidation of photocatalyst and prolonged the carrier life. Furthermore, the AGBMO-15 photocatalyst exhibited excellent photocatalytic degradation stability, maintaining an RhB removal rate of 96.2% after four cycles of reuse. Due to its simplicity, reusability, and controllability, the proposed photocatalyst has excellent application potential for the environmental remediation of wastewater.

An early aortic dissection screening model and applied research based on ensemble learning.

BACKGROUND: As a particularly dangerous and rare cardiovascular disease, aortic dissection (AD) is characterized by complex and diverse symptoms and signs. In the early stage, the rate of misdiagnosis and missed diagnosis is relatively high. This study aimed to use machine learning technology to establish a fast and accurate screening model that requires only patients' routine examination data as input to obtain predictive results. METHODS: A retrospective analysis of the examination data and diagnosis results of 53,213 patients with cardiovascular disease was conducted. Among these samples, 802 samples had AD. Forty-two features were extracted from the patients' routine examination data to establish a prediction model. There were five ensemble learning models applied to explore the possibility of using machine learning methods to build screening models for AD, including AdaBoost, XGBoost, SmoteBagging, EasyEnsemble and XGBF. Among these, XGBF is an ensemble learning model that we propose to deal with the imbalance of the positive and negative samples. The seven-fold cross validation method was used to analyze and verify the performance of each model. Due to the imbalance of the samples, the evaluation indicators were sensitivity and specificity. RESULTS: Comparative experiments showed that the sensitivity of XGBF was 80.5%, which was better than the 16.1% of AdaBoost, 15.7% of XGBoost, 78.0% of SmoteBagging and 77.8% of EasyEnsemble. Additionally, XGBF had relatively high specificity, and the training time consumption was short. Based on these three indicators, XGBF performed best, and met the application requirements, which means through careful design, we can use machine learning technology to achieve early AD screening. CONCLUSIONS: Through reasonable design, the ensemble learning method can be used to build an effective screening model. The XGBF has high practical application value for screening for AD.

Immobilizing laccase on kaolinite and its application in treatment of malachite green effluent with the coexistence of Cd (П).

Malachite green effluent with the Coexistence of Cd (П) was efficiently decolorized by kaolinite-laccase (Kaolin-Lac). Laccase from Trametes versicolor was immobilized onto the kaolinite through physical adsorption contact. The optimal conditions were 180 min of immobilization time and 0.8 mg/mL of enzyme solution. Kaolin-Lac could obtain a loading efficiency of 88.22%, a loading capacity of 12.25 mg/g, and the highest activity of 839.01 U/g. Moreover, the process of immobilization increased its pH stability and operational stability. Kaolin-Lac retained above 50% of the original activity and nearly 80% decolorization for MG after 5 cycles. In the presence of 3, 5-Dimethoxy-4-hydroxybenzaldehyde (SA), Kaolin-Lac could degrade over 98% of malachite green. The coexistence of Cd (П) was beneficial to the decolorization of malachite green by Kaolin-Lac. The structural and morphological features of kaolinite, Kaolin-Lac and Kaolin-Lac after degradation were determined by scanning electron microscopy-energy spectrum analysis (SEM-EDS) and Fourier transform infrared spectroscopy (FTIR). Cadmium appeared on the Kaolin-Lac after degradation. After immobilization and degradation, the surface groups on kaolinite were changed. Kaolin-Lac showed its more potential continuous employment than free laccase in practical malachite green dyes effluent mixed with Cd (П).

An investigation on fatality of drivers in vehicle-fixed object accidents on expressways in China: Using multinomial logistic regression model.

This study aims to identify the effects of characteristics of vehicle, roadway, driver, and environment on fatality of drivers in vehicle-fixed object accidents on expressways in Changsha-Zhuzhou-Xiangtan district of Hunan province in China by developing multinomial logistic regression models. For this purpose, 121 vehicle-fixed object accidents from 2011-2017 are included in the modeling process. First, descriptive statistical analysis is made to understand the main characteristics of the vehicle-fixed object crashes. Then, 19 explanatory variables are selected, and correlation analysis of each two variables is conducted to choose the variables to be concluded. Finally, five multinomial logistic regression models including different independent variables are compared, and the model with best fitting and prediction capability is chosen as the final model. The results showed that the turning direction in avoiding fixed objects raised the possibility that drivers would die. About 64% of drivers died in the accident were found being ejected out of the car, of which 50% did not use a seatbelt before the fatal accidents. Drivers are likely to die when they encounter bad weather on the expressway. Drivers with less than 10 years of driving experience are more likely to die in these accidents. Fatigue or distracted driving is also a significant factor in fatality of drivers. Findings from this research provide an insight into reducing fatality of drivers in vehicle-fixed object accidents.

A novel biosorbent prepared by immobilized Bacillus licheniformis for lead removal from wastewater.

Magnetic polyving akohol (PVA) immobilized the endogenous bacterium Bacillus licheniformis with sodium alginate to get a novel biosorbent. The optimum preparation and adsorption conditions were studied. The optimal preparation conditions was the fraction of magnetic PVA was 9%, the fraction of sodium alginate was 0.8%, the fraction of microbial suspensions was 5% and the crosslinking time was 20 h. The best adsorption conditions were listed as follows: pH was 6, the biosorbent dosage was 0.7 g L-1, the initial concentration of lead ions was 200 mg L-1 and the optimal adsorption time was 12 h. The results of SEM and FTIR spectroscopy analysis displayed this novel biosorbents had good structure and the functional groups on the surface was abundant. The VSM analysis confirmed the novel biosorbents had good magnetic magnetization and were easily separated from aqueous medium. Under the optimum conditions, the removal rate of lead ions from waste water could reach 98%, the calculated maximum adsorption capacity could be up to 113.84 mg g-1. The whole adsorption process was well fit by the pseudo-second order kinetic and it was also a Langmuir monolayer adsorption. The desorption experiments showed the biosorbent had good re-usability.

Microplastic pollution in surface sediments of urban water areas in Changsha, China: Abundance, composition, surface textures.

Microplastics pollution in the global marine environment has received much recent research attention. However, microplastics contamination of the freshwater environment has not been fully studied, especially with respect to the surface sediments of urban water areas in China. This study investigated surface sediment samples from twelve selected sites in Changsha, China. The average microplastic concentrations in the surface sediments of the urban water areas ranged from 270.17 ±â€¯48.23 items·kg-1 to 866.59 ±â€¯37.96 items·kg-1, and the highest concentration of microplastics was found in Yuejin Lake sediments. Most of the collected microplastics were transparent, and most were classified as fragments. Most microplastics (58.31%) were smaller than 1 mm across all samples. Raman analysis indicated that polystyrene dominated the sediments samples. This study provided framework for future studies of microplastics pollution in the surface sediment of urban water areas in China.