Search

Aims/Introduction: Machine learning algorithms based on the artificial neural network (ANN), support vector machine, naive Bayesian or logistic regression model are commonly used to identify diabetes. This study investigated which approach performed the best and whether muscle strength provided any incremental benefit in identifying undiagnosed diabetes in Chinese adults. Methods: This cross‐sectional study enrolled 4,482 eligible participants from eight provinces in China, who were randomly divided into the training dataset (n = 3,586) and the testing dataset (n = 896). Muscle strength was assessed by handgrip strength and the number of chair stands in the 30‐s chair stand test. An oral glucose tolerance test was used to ascertain undiagnosed diabetes. The areas under the curve (AUCs) were calculated accordingly and compared with each other. Results: Of the included participants, 233 had newly diagnosed diabetes. All the four machine learning algorithms, which were developed based on nonlaboratory parameters, showed acceptable discriminative ability in identifying undiagnosed diabetes (all AUCs >0.70), with the ANN approach performing the best (AUC 0.806). Adding handgrip strength or the 30‐s chair stand test to this approach did not increase the AUC further (P = 0.39 and 0.26, respectively). Furthermore, compared with the New Chinese Diabetes Risk Score, the ANN approach showed a larger AUC in identifying undiagnosed diabetes (Pcomparison < 0.01), regardless of the addition of handgrip strength or the 30‐s chair stand test. Conclusions: The ANN approach performed the best in identifying undiagnosed diabetes in Chinese adults; however, the addition of muscle strength might not improve its efficacy. [ABSTRACT FROM AUTHOR]

Background: Accurately predicting the risk of atherosclerotic cardiovascular disease (ASCVD) is crucial for implementing individualized prevention strategies and improving patient outcomes. Our objective is to develop machine learning (ML)-based models for predicting ASCVD risk in a prospective Chinese population and compare their performance with conventional regression models. Methods: A hybrid dataset consisting of 551 features was used, including 98 demographic, behavioral, and psychological features, 444 Electrocardiograph (ECG) features, and 9 Echocardiography (Echo) features. Seven machine learning (ML)-based models were trained, validated, and tested after selecting the 30 most informative features. We compared the discrimination, calibration, net benefit, and net reclassification improvement (NRI) of the ML models with those of conventional ASCVD risk calculators, such as the Pooled Cohort Equations (PCE) and Prediction for ASCVD Risk in China (China-PAR). Results: The study included 9,609 participants (mean age 53.4 ± 10.4 years, 53.7% female), and during a median follow-up of 4.7 years, 431 (4.5%) participants developed ASCVD. In the testing set, the final ML-based ANN model outperformed PCE, China-PAR, recalibrated PCE, and recalibrated China-PAR in predicting ASCVD. This was demonstrated by the model's higher area under the curve (AUC) of 0.800, compared to 0.777, 0.780, 0.779, and 0.779 for the other models, respectively. Additionally, the model had a lower Hosmer–Lemeshow χ2 of 9.1, compared to 37.3, 67.6, 126.6, and 18.6 for the other models. The net benefit at a threshold of 5% was also higher for the ML-based ANN model at 0.017, compared to 0.016, 0.013, 0.017, and 0.016 for the other models, respectively. Furthermore, the NRI was 0.089 for the ML-based ANN model, while it was 0.355, 0.098, and 0.088 for PCE, China-PAR, and recalibrated PCE, respectively. Conclusions: Compared to conventional regression ASCVD risk calculators, such as PCE and China-PAR, the ANN prediction model may help optimize identification of individuals at heightened cardiovascular risk by flexibly incorporating a wider range of potential predictors. The findings may help guide clinical decision-making and ultimately contribute to ASCVD prevention and management. [ABSTRACT FROM AUTHOR]

In the field of health, China's contribution is generally addressed either through its cooperation programmes or by the opening of private clinics by Chinese 'doctors'. In Yaoundé and Douala, some private practices have been opened and various works have highlighted their role in the dissemination of traditional Chinese medicine (TCM) in Cameroon. Yet the craze for these structures did not last long. Today, while signs of their existence are still visible, many of these firms are closed. China's influence in the health field is, however, far from negligible, but it is taking place in unexpected areas. The circulation of goods and knowledge from China leaves more room for local reappropriation. Indeed, some Cameroonian traditional healers include knowledge from China in their daily practice through the use of 'machines' coming from China to 'purify the body', to 'eliminate fat', to regulate the tension, to 'stimulate acupuncture points' or 'make diagnosis' (using the quantum analyser or a 'diagnostic machine'). From direct observations conducted between 2014 and 2021, this article presents the issues at stake for the practice of traditional healers by the modernization of the field through specific therapeutic devices and the quantum analyser coming from China into the health Cameroonian landscape. The paper demonstrates that the performance of the diagnostic machine has less to do with the concrete efficiency of the diagnosis of pathologies than with the dynamics of visibility vis-à-vis patients. The quantum analyser is, therefore, an interesting element revealing the constant process of renewal of medical pluralism in Cameroon, in which China is playing a central role today. [ABSTRACT FROM AUTHOR]

Breast cancer is a cancer disease that seriously threatens women's health and occupies the first place in female cancer mortality. At present, the incidence rate of breast cancer in China is the first in the world and is on the rise. In view of the serious harm of breast cancer to life and health, researchers and institutions are making unremitting efforts to find a perfect diagnosis and treatment plan. With the improvement of computer performance and machine learning levels, intelligent algorithms have been able to replace human behavior and judgment in some fields. The traditional breast cancer diagnosis process requires medical experts to observe patient data repeatedly. In this case, the algorithm technology is used to quickly feedback a high probability reference result to doctors, which is particularly important to increase the diagnosis efficiency and reduce the burden of doctors. In order to improve the accuracy of existing breast cancer recognition methods, this paper proposes and implements a scheme based on a whale optimization algorithm to iteratively adjust the key parameters of the support vector machine to improve the accuracy of breast cancer recognition. In order to verify the performance of the WOA-SVM algorithm, this paper uses the Wisconsin breast cancer data in the UCI database for performance verification experiments. Experiments show that the WOA-SVM model has higher recognition accuracy than the traditional breast cancer recognition model. [ABSTRACT FROM AUTHOR]

Data envelopment analysis (DEA) has been widely applied to evaluate the performance of banks, enterprises, governments, research institutions, hospitals, and other fields as a non-parametric estimation method for evaluating the relative effectiveness of research objects. However, the composition of its effective frontier surface is based on the input-output data of existing decision units, which makes it challenging to apply the method to predict the future performance level of other decision units. In this paper, the Slack Based Measure (SBM) model in DEA method is used to measure the relative efficiency values of decision units, and then, eleven machine learning models are used to train the absolute efficient frontier to be applied to the performance prediction of new decisions units. To further improve the prediction effect of the models, this paper proposes a training set under the DEA classification method, starting from the training-set sample selection and input feature indicators. In this paper, regression prediction of test set performance based on the training set under different classification combinations is performed, and the prediction effects of proportional relative indicators and absolute number indicators as machine-learning input features are explored. The robustness of the effective frontier surface under the integrated model is verified. An integrated models of DEA and machine learning with better prediction effects is proposed, taking China's regional carbon-dioxide emission (carbon emission) performance prediction as an example. The novelty of this work is mainly as follows: firstly, the integrated model can achieve performance prediction by constructing an effective frontier surface, and the empirical results show that this is a feasible methodological technique. Secondly, two schemes to improve the prediction effectiveness of integrated models are discussed in terms of training set partitioning and feature selection, and the effectiveness of the schemes is demonstrated by using carbon-emission performance prediction as an example. This study has some application value and is a complement to the existing literature. [ABSTRACT FROM AUTHOR]

• The stepwise linear regression is more suitable for estimating typical steppe AGB in northern China at the Sentinel scale. • Both traditional vegetation indices and soil-adjusted vegetation indices have similar effects on the estimation of typical steppe AGB in northern China. • Sentinel C-band SAR is not applicable for the estimation of typical steppe AGB in northern China. Monitoring aboveground biomass (AGB) is crucial for assessing, managing, and utilizing grassland ecosystems. While the technical form of combining remote sensing and machine learning algorithms is widely used to estimate AGB at a regional scale, few studies have assessed and compared the performance of popular algorithms on the typical steppe in northern China. In this study, the northern Xilinhot, a representative area of typical steppe in China, was selected as the study area to compare the performance of six widely used machine learning algorithms for AGB estimation, namely stepwise linear regression (SLR), partial least square regression (PLS), principal component regression (PCR), random forest (RF), support vector machines (SVM), and k-nearest neighbors (KNN). Additionally, the study explored the modeling capability of multisource variables from Sentinel imagery and auxiliary data. The results showed that (1) considering the aspects of prediction accuracy, noise resistance, ease of operation, and transferability, the SLR algorithm is more suitable for estimating typical steppe AGB in northern China at the Sentinel scale. (2) Vegetation Indices (VI) play a significant role in the development of selected models, with significant contributions from both traditional and soil-adjusted indices. (3) Sentinel C-band synthetic aperture radar (SAR) is unsuitable for modeling typical steppe AGB. (4) Among the selected environmental factors, only clay content and soil pH are significantly linearly correlated with AGB, while elevation, precipitation, temperature, soil pH, and sand content are advantageous for RF prediction. This study can provide important technical references for the research on AGB in typical steppe in northern China. [ABSTRACT FROM AUTHOR]

Nowadays, it is commonplace for geological surveys to integrate multi-source geophysical data and drilling data in order to construct three-dimensional (3D) lithological models. In this context, manual translation of complex geophysical data into parameters used for 3D lithological modeling is challenging. Machine learning has recently shown great potential in 3D lithological modeling. However, the performance of machine learning algorithm is influenced by the imbalance in number of categories of lithological samples. In addition, the uncertainty associated with 3D lithological modeling by machine learning has rarely been quantified. This study presents a novel integrated machine learning framework to address the imbalance issue and to quantify uncertainty in 3D lithological modeling. As its novelty, our integrated machine learning framework can subdivide total uncertainty into aleatoric and epistemic uncertainties in the 3D lithological modeling procedure by stochastic gradient Langevin boosting. Another innovation of this study is the use of Bayesian hyperparameter optimization for automatic tuning of hyperparameters of the integrated machine learning framework. The 3D lithological and uncertainty modeling case study in the Jiaojia–Sanshandao gold district of China demonstrated the superiority of our proposed integrated machine learning framework. The proposed framework has great potential in integrating multi-source geophysical and drilling data for 3D lithological and uncertainty modeling in engineering geology. • Construct 3D lithological and uncertainty modeling using machine learning from geophysical and drilling data. • Total uncertainty was subdivided into aleatoric and epistemic uncertainties in the 3D lithological modeling. • SMOTE-ENN was utilized to address the lithological imbalance issue in training for 3D lithological modeling. • The Bayesian hyperparameter optimization was applied to tune the hyperparameters of machine learning model automatically. [ABSTRACT FROM AUTHOR]

This paper compares the performance of five popular machine learning methods, namely, particle swarm optimization–extreme learning machine (PSO–ELM), particle swarm optimization–kernel extreme learning machine (PSO–KELM), particle swarm optimization–support vector machine (PSO–SVM), particle swarm optimization–least squares support vector machine (PSO–LSSVM), and long short-term memory neural network (LSTM), in the prediction of reservoir landslide displacement. The Baishuihe, Shuping, and Baijiabao landslides in the Three Gorges reservoir area of China were used for case studies. Cumulative displacement was decomposed into trend displacement and periodic displacement by the Hodrick–Prescott filter. The double exponential smoothing method and the five machine learning methods were used to predict the trend and periodic displacement, respectively. The five machine learning methods are compared in three aspects: highest single prediction accuracy, mean prediction accuracy, and prediction stability. The results show that no method performed the best for all three aspects in the three landslide cases. LSTM and PSO–ELM achieved better single prediction accuracy, but worse mean prediction accuracy and stability. PSO–KELM, PSO–LSSVM, and PSO–SVM always yielded consistent predictions with slight variations. On the whole, PSO–KELM and PSO–LSSVM are recommended for their superior mean prediction accuracy and prediction stability. • The performances of machine learning methods depend on the selected evaluation index and reservoir landslide case. • Using single prediction accuracy for evaluating the superiority of machine learning methods may be unreliable. • PSO-KELM and PSO-LSSVM are recommended for their superior mean prediction accuracy and prediction stability. [ABSTRACT FROM AUTHOR]

In spite of the state-of-the-art performances of machine learning in the PM 2.5 estimation, the high-value PM 2.5 underestimation and non-random aerosol optical depth (AOD) missing are still huge obstacles. By incorporating wavelet decomposition (WD) into the extreme gradient boosting (XGBoost), a hybrid XGBoost-WD model was established to obtain the full-coverage PM 2.5 estimation at 3-km spatial resolution in the Yangtze River Delta Urban Agglomeration (YRDUA). In this study, 3-km-resolution meteorological fields simulated by WRF along with AOD derived from Moderate Resolution Imaging Spectroradiometer (MODIS) were served as explanatory variables. Model MW and Model NW were developed using XGBoost-WD for the areas with and without AOD respectively to obtain a full-coverage PM 2.5 mapping in the YRDUA. The XGBoost-WD model showed good performances in estimating PM 2.5 with R2 of 0.80 in the Model MW and 0.87 in the Model NW. Moreover, the K-value of Model MW increased from 0.77 to 0.79 and that of Model NM increased from 0.81 to 0.86 compared with the model without the step of WD, indicating an improvement on the problem of PM 2.5 underestimation. Due to a better ability of capturing abrupt changes in the PM 2.5 concentrations, the spatial evolution of PM 2.5 during a typical pollution event could be mapped more accurately. Finally, the analysis of variable importance showed that the three most important variables in the estimation of the low-frequency coefficients of PM 2.5 (PM 2.5 _A4) were temperature at 2 m (T2), day of year (DOY) and longitude (LON), while that in the high-frequency coefficients of PM 2.5 (PM 2.5 _D) were CO, AOD and NO 2. This study not only provided an effective solution to the PM 2.5 underestimation and AOD missing problems in the PM 2.5 estimation, but also proposed a new method to further refine the sophisticated correlations between PM 2.5 and some spatiotemporal variables. • Fine-resolution and full-coverage PM 2.5 concentrations are estimated in the YRDUA. • WRF is applied to simulate 3-km-resolution meteorological fields in the estimation. • The problem of PM 2.5 underestimation is improved with the hybrid XGBoost-WD model. • The importance of explanatory variables to the model is quantitatively measured. [ABSTRACT FROM AUTHOR]