Search

Climate change intensifies, so does the need to reduce carbon emissions to achieve the goal of being "carbon neutral" for China. This paper focuses on carbon emission prediction and constructs a comprehensive model integrating least absolute shrinkage and selection operator (LASSO), principal component analysis (PCA), support vector regression (SVR), and differential evolution-gray wolf optimization (DE-GWO). Firstly, LASSO is used for feature selection, and important information is extracted from various influencing factors to find out what have a great impact on carbon emission. Principal component analysis is used to extract the features of the remaining variables to avoid missing information caused by feature selection. Secondly, DE-GWO algorithm is used to optimize the parameters of SVR to improve the prediction accuracy. The scenario analysis and prediction algorithm are combined to predict China's carbon emissions. The results show that (1) coal and oil consumption, plate glass, pig iron, and crude steel production are important factors affecting carbon emissions; (2) the use of PCA to comprehensively consider the impact of remaining factors on carbon emissions has a positive influence on carbon emissions prediction; and (3) DE-GWO optimized SVR has higher prediction accuracy than other algorithms. [ABSTRACT FROM AUTHOR]

Background: Coronary heart disease (CHD) is a common cardiovascular disease with high morbidity and mortality in China. The CHD risk prediction model has a great value in early prevention and diagnosis. Methods: In this study, CHD risk prediction models among rural residents in Xinxiang County were constructed using Random Forest (RF), Support Vector Machine (SVM), and the least absolute shrinkage and selection operator (LASSO) regression algorithms with identified 16 influencing factors. Results: Results demonstrated that the CHD model using the RF classifier performed best both on the training set and test set, with the highest area under the curve (AUC = 1 and 0.9711), accuracy (one and 0.9389), sensitivity (one and 0.8725), specificity (one and 0.9771), precision (one and 0.9563), F1-score (one and 0.9125), and Matthews correlation coefficient (MCC = one and 0.8678), followed by the SVM (AUC = 0.9860 and 0.9589) and the LASSO classifier (AUC = 0.9733 and 0.9587). Besides, the RF model also had an increase in the net reclassification index (NRI) and integrated discrimination improvement (IDI) values, and achieved a greater net benefit in the decision curve analysis (DCA) compared with the SVM and LASSO models. Conclusion: The CHD risk prediction model constructed by the RF algorithm in this study is conducive to the early diagnosis of CHD in rural residents of Xinxiang County, Henan Province. [ABSTRACT FROM AUTHOR]

Background: Timely diagnosis of ischemic stroke (IS) in the acute phase is extremely vital to achieve proper treatment and good prognosis. In this study, we developed a novel prediction model based on the easily obtained information at initial inspection to assist in the early identification of IS. Methods: A total of 627 patients with IS and other intracranial hemorrhagic diseases from March 2017 to June 2018 were retrospectively enrolled in the derivation cohort. Based on their demographic information and initial laboratory examination results, the prediction model was constructed. The least absolute shrinkage and selection operator algorithm was used to select the important variables to form a laboratory panel. Combined with the demographic variables, multivariate logistic regression was performed for modeling, and the model was encapsulated within a visual and operable smartphone application. The performance of the model was evaluated on an independent validation cohort, formed by 304 prospectively enrolled patients from June 2018 to May 2019, by means of the area under the curve (AUC) and calibration. Results: The prediction model showed good discrimination (AUC = 0.916, cut-off = 0.577), calibration, and clinical availability. The performance was reconfirmed in the more complex emergency department. It was encapsulated as the Stroke Diagnosis Aid app for smartphones. The user can obtain the identification result by entering the values of the variables in the graphical user interface of the application. Conclusion: The prediction model based on laboratory and demographic variables could serve as a favorable supplementary tool to facilitate complex, time-critical acute stroke identification. [ABSTRACT FROM AUTHOR]

Skin cancer is a common malignant tumor in China and throughout the world, and the rate of recurrence is considerably high, thus endangering the quality of life and health of patients, and increasing the economic burden and pressure to the families of those afflicted. Due to the limitations of traditional drug treatments, it is difficult to achieve the desired therapeutic effect of complete removal. However, targeted gene therapy may be a novel means of treating skin cancer, as the targeted nature of treatment may improve therapeutic outcomes. However, targeted gene therapy requires physicians to select the appropriate gene, which means suitable genetic biomarkers must be identified from complex genetic data. In the present study, the least absolute shrinkage and selection operator regression analysis method was used with 10-fold cross verification to reduce the dimensions of gene data in patients with skin cancer, and subsequently, 20 gene biomarkers were screened. A prognostic model was constructed using these 20 gene biomarkers, and the validity of the model was assessed using a training set and a verification set, which showed that the model performed well. Finally, gene function analysis of these 20 gene biomarkers was determined. Relevant studies were found to show that the genetic biomarkers identified in this paper may possess value for the follow-up clinical treatment of skin cancer. [ABSTRACT FROM AUTHOR]

The accurate estimation of reference evapotranspiration (ETo) is a fundamental requirement for precision irrigation and regional water resource planning. In this regard, the application of the standard model, FAO-56 Penman–Monteith, is limited because of insufficient meteorological data. This study aims to improve the accuracy of ETo calculations in regions with scarce meteorological data. A hybrid model integrating two data preprocessing methods (variational mode decomposition (VMD) and Box–Cox transformation (BC)) into a support vector machine (SVM) model (VMD–BC–SVM) is proposed. The model estimates the daily ETo based on the meteorological data (1980–2019) of 10 stations in the Wei River Basin of China. The VMD method was employed to extract multiple intrinsic mode functions (IMFs) and eliminate non-stationarity. This is achieved by decomposing meteorological factors, which are further transformed by BC to alleviate skewness characteristics. The least absolute shrinkage and selection operator regression (LASSO) identifies the key driving modes from the transformed IMFs, which are used as the input of the SVM model. The VMD–BC–SVM estimation model framework based on decomposition–transformation–identification–estimation is proposed. The performance of each of the hybrid VMD–BC–SVM models was further compared with those of the standalone extreme learning machine (ELM) model and two empirical models (Hargreaves–Samani and Priestley–Taylor models). The results revealed that the hybrid models outperformed the single models. The VMD–BC–SVM model achieved higher accuracy compared with the other models. Specifically, the coefficient of correlation (R) and Nash–Sutcliffe efficiency coefficient (NSE) were both greater than 0.96. Furthermore, the mean absolute percentage error (MAPE) and root mean square error (RMSE) were less than 8.41% and 0.38 mm/d, respectively. In terms of the amount of information provided, the VMD–BC–SVM model is superior to empirical models in identifying high-dimensional and nonlinear information. Moreover, the estimation performance is more stable, and the level of uncertainty is lower. This study provides a novel approach for predicting ETo in regions with limited meteorological data. • A novel VMD-BC-SVM approach was proposed to estimate ETo. • VMD and Box-Cox were used to remove the non-stationarity and skewness of inputs. • LASSO regression was used to identify the key driving modes as optimal input. • VMD-BC-SVM model outperforms comparison models for estimation ETo. [ABSTRACT FROM AUTHOR]

Several screening tools have been developed to facilitate early diagnosis of psoriatic arthritis (PsA); however, their performance varied greatly across different studies. In this study, we validated and compared the performance of four screening tools in detecting undiagnosed PsA Chinese patients with psoriasis, and determined the key questions and their weights. The four screening tools were the Early Arthritis for Psoriatic Patients (EARP) questionnaire, Psoriatic Arthritis Screening and Evaluation (PASE) questionnaire, Psoriasis and Arthritis Screening Questionnaire (PASQ), and Psoriasis Epidemiology Screening Tool (PEST). The receiver-operator curve (ROC) with area under curve (AUC) was used to determine sensitivity, specificity, and accuracy. Least absolute shrinkage and selection operator and logistic regression were utilized to retrieve key questions, and a nomogram was utilized to visualize their weights. Of 482 psoriasis patients from dermatology clinics, 77 were newly diagnosed with PsA. Another 68 patients with newly diagnosed PsA from rheumatology clinics were incorporated in the analysis. ROC analysis indicated that the optimal cut-off values for EARP, PASE, PASQ, and PEST were 3, 40, 7, and 3, with corresponding sensitivities of 91.4%, 88.6%, 86.2%, and 88.5%, and specificities of 88.6%, 75.2%, 80.2%, and 83.6%, respectively. The AUC of EARP (0.925) was higher than those of PASE (0.885), PASQ (0.905), and PEST (0.827). However, none of them were sufficiently sensitive to identify pure axial PsA (sensitivities of EARP, PASQ, and PASE were 25.0%, 36.8%, and 42.1%, respectively). Twelve key questions were retrieved from these four tools to establish a nomogram with a high discrimination (C-index = 0.993) and a good calibration (mean absolute error = 0.014). In conclusion, to screen undiagnosed PsA, EARP has slightly better balanced sensitivity and specificity, and higher accuracy. The retrieval of key questions and nomogram signify the necessity of attributing different scores to differently weighted questions when developing a new screening tool to make it function more efficiently., (© 2022 Japanese Dermatological Association.)

Objectives: Oesophagectomy for malignancy is a highly complex and difficult procedure associated with considerable postoperative complications. In this study, we aimed to identify the ability of an intraoperative factor (IPFs)-based classifier to predict complications after oesophagectomy., Methods: This retrospective review included 251 patients who underwent radical oesophagectomy from October 2015 to December 2017. Using the least absolute shrinkage and selection operator regression model, we extracted IPFs that were associated with postoperative morbidity and then built a classifier. Preoperative variables and the IPF-based classifier were analysed using univariable and multivariable logistic regression analysis. A nomogram to predict the risk of postoperative morbidity was constructed and validated using bootstrap resampling., Results: Following the least absolute shrinkage and selection operator regression analysis, we discovered that those 4 IPF (surgical approach, lowest heart rate, lowest mean arterial blood pressure and estimated blood loss) were associated with postoperative morbidity. After stratification into low-and high-risk groups with the IPF-based classifier, the differences in 30-day morbidity (7.2% vs 70.1%, P < 0.001, respectively) and mortality (0% vs 4.7%, P = 0.029, respectively) were found to be statistically significant. The multivariable analysis demonstrated that the IPF-based classifier was an independent risk factor for predicting postoperative morbidity for patients with oesophageal cancer. The performance of the nomogram was evaluated and proven to be clinically useful., Conclusions: We demonstrated that an IPF-based nomogram could reliably predict the risk of postoperative morbidity. It has the potential to facilitate the individual perioperative management of patients with oesophageal cancer., (© The Author(s) 2019. Published by Oxford University Press on behalf of the European Association for Cardio-Thoracic Surgery. All rights reserved.)

Numerous studies have investigated the impacts of ambient fine particulate matter (PM 2.5 ) on human health. In this study, we examined the association of daily PM 2.5 concentrations with the number of deaths for the cerebrovascular disease on the same day, using the generalized additive model (GAM) controlling for temporal trend and meteorological variables. We used the data between 2012 and 2014 from Shanghai, China, where the adverse health effects of PM 2.5 have been of particular concern. Three different approaches (principal component analysis, shrinkage smoothers, and the least absolute shrinkage and selection operator regularization) were used in GAM to handle multicollinear meteorological variables. Our results indicate that the average daily concentration of PM 2.5 in Shanghai was high, 55 μg/m 3 , with an average daily death for cerebrovascular disease (CVD) of 62. There was 1.7% raised cerebrovascular disease deaths per 10 μg/m 3 increase in PM 2.5 concentration in the unadjusted model. However, PM 2.5 concentration was no longer associated with CVD deaths after controlling for meteorological variables. The results were consistent in the three modelling techniques that we used. As a large number of people are exposed to air pollution, further investigation with longer time period including individual-level information is needed to examine the association.