Search

Copyright of Contemporary Accounting Research is the property of Canadian Academic Accounting Association and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Simple Summary: This study developed a prediction model to forecast a 2-year locoregional recurrence in patients with locally advanced esophageal cancer who underwent definitive chemoradiotherapy (dCRT). The model combined clinical and radiomics features extracted from pre-treatment computed tomography (CT) images. A total of 264 patients from three centers were included in the study, with clinical features like tumor stage and tumor volume and radiomic features used to construct the model. The Support Vector Machine (SVM) method integrated these features to predict recurrence. In the training group, the model showed excellent performance (C-index: 0.9841), while in the validation group, it demonstrated moderate performance (C-index: 0.744). The prediction model can help in personalizing treatment strategies for esophageal cancer patients, guiding therapy decisions to potentially improve outcomes. Purpose: We constructed a prediction model to predict a 2-year locoregional recurrence based on the clinical features and radiomic features extracted from the machine learning method using computed tomography (CT) before definite chemoradiotherapy (dCRT) in locally advanced esophageal cancer. Patients and methods: A total of 264 patients (156 in Beijing, 87 in Tianjin, and 21 in Jiangsu) were included in this study. All those locally advanced esophageal cancer patients received definite radiotherapy and were randomly divided into five subgroups with a similar number and divided into training groups and validation groups by five cross-validations. The esophageal tumor and extratumoral esophagus were segmented to extract radiomic features from the gross tumor volume (GTV) drawn by radiation therapists before radiotherapy, and six clinical features associated with prognosis were added. T stage, N stage, M stage, total TNM stage, GTV, and GTVnd volume were included to construct a prediction model to predict the 2-year locoregional recurrence of patients after definitive radiotherapy. Results: A total of 264 patients were enrolled from August 2012 to April 2018, with a median age of 62 years and 81% were males. The 2-year locoregional recurrence rate was 52.6%, and the 2-year overall survival rate was 45.6%. About 66% of patients received concurrent chemotherapy. In total, we extracted 786 radiomic features from CT images and the Principal Component Analysis (PCA) method was used to screen out the maximum 30 features. Finally, the Support Vector Machine (SVM) method was used to construct the integrated prediction model combining radiomics and clinical features. In the five training groups for predicting locoregional recurrence, the mean value of C-index was 0.9841 (95%CI, 0.9809–0.9873), and in the five validation groups, the mean value was 0.744 (95%CI, 0.7437–0.7443). Conclusions: The integrated radiomics model could predict the 2-year locoregional recurrence after dCRT. The model showed promising results and could help guide treatment decisions by identifying high-risk patients and enabling strategies to prevent early recurrence. [ABSTRACT FROM AUTHOR]

We aimed to predict dyslipidemia risk in elderly Chinese adults using machine learning and dietary analysis for public health. This cross-sectional study includes 13,668 Chinese adults aged 65 or older from the 2018 Chinese Longitudinal Healthy Longevity Survey. Dyslipidemia prediction was carried out using a variety of machine learning algorithms, including Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Random Forest (RF), Gaussian Naive Bayes (GNB), Gradient Boosting Machine (GBM), Adaptive Boosting Classifier (AdaBoost), Light Gradient Boosting Machine (LGBM), and K-Nearest Neighbour (KNN), as well as conventional logistic regression (LR). The prevalence of dyslipidemia among eligible participants was 5.4 %. LGBM performed best in predicting dyslipidemia, followed by LR, XGBoost, SVM, GBM, AdaBoost, RF, GNB, and KNN (all AUC > 0.70). Frequency of nut product consumption, childhood water source, and housing types were key predictors for dyslipidemia. Machine learning algorithms that integrated dietary behaviours accurately predicted dyslipidemia in elderly Chinese adults. Our research identified novel predictors such as the frequency of nut product consumption, the main source of drinking water during childhood, and housing types, which could potentially prevent and control dyslipidemia in elderly adults. [ABSTRACT FROM AUTHOR]

From a global perspective, China is one of the countries with higher incidence and mortality rates for cancer. Our objective is to create an online cancer risk prediction tool for middle-aged and elderly Chinese adults by leveraging machine learning algorithms and self-reported data. Drawing from a cohort of 19,798 participants aged 45 and above from the China Health and Retirement Longitudinal Study (2011 - 2018), we employed nine machine learning algorithms (LR: Logistic Regression, Adaboost: Adaptive Boosting, SVM: Support Vector Machine, RF: Random Forest, GNB: Gaussian Naive Bayes, GBM: Gradient Boosting Machine, LGBM: Light Gradient Boosting Machine, XGBoost: eXtreme Gradient Boosting, KNN: K - Nearest Neighbors), which are mainly used for classification and regression tasks, to construct predictive models for various cancers. Utilizing non-invasive self-reported predictors encompassing demographic, educational, marital, lifestyle, health history, and other factors, we focused on predicting "Cancer or Malignant Tumour" outcomes. The types of cancers that can be predicted mainly include lung cancer, breast cancer, cervical cancer, colorectal cancer, gastric cancer, esophageal cancer, and other rare cancers. The developed tool, MyCancerRisk, demonstrated significant performance, with the Random Forest algorithm achieving an AUC of 0.75 and ACC of 0.99 using self-reported variables. Key predictors identified include age, self-rated health, sleep patterns, household heating sources, childhood health status, living conditions, and smoking habits. MyCancerRisk aims to serve as a preventative screening tool, encouraging individuals to undergo testing and adopt healthier behaviours to mitigate the public health impact of cancer. Our study also sheds light on unconventional predictors, such as housing conditions, offering valuable insights for refining cancer prediction models. [Display omitted] [ABSTRACT FROM AUTHOR]

Objectives: To examine (1) how visual green space quantity and quality affect depression among older adults; (2) whether and how the links may be mediated by perceived stress, physical activity, neighbourhood social cohesion, and air pollution (PM2.5); and (3) whether there are differences in the mediation across visual green space quantity and quality. Method: We used older adults samples (aged over 65) from the WHO Study on Global Ageing and Adult Health in Shanghai, China. Depression was quantified by two self-reported questions related to the diagnosis of depression and medications or other treatments for depression. Visual green space quantity and quality were calculated using street view images and machine learning methods (street view green space = SVG). Mediators included perceived stress, social cohesion, physical activity, and PM2.5. Multilevel logistic and linear regression models were applied to understand the mediating roles of the above mediators in the link between visual green space quantity and quality and depression in older adults. Results: SVG quantity and quality were negatively related to depression. Significant partial mediators for SVG quality were social cohesion and perceived stress. For SVG quantity, there was no evidence that any of the above mediators mediated the association. Conclusion: Our results indicated that visual green space quantity and quality may be related to depression in older adults through different mechanisms. [ABSTRACT FROM AUTHOR]

Objective: The COVID-19 pandemic has placed unprecedented strain on healthcare systems, mainly due to the highly variable and challenging to predict patient length of stay (LOS). This study aims to identify the primary factors impacting LOS for patients before and during the COVID-19 pandemic. Methods: This study collected electronic medical record data from Zhongnan Hospital of Wuhan University. We employed six machine learning algorithms to predict the probability of LOS. Results: After implementing variable selection, we identified 35 variables affecting the LOS for COVID-19 patients to establish the model. The top three predictive factors were out-of-pocket amount, medical insurance, and admission deplanement. The experiments conducted showed that XGBoost (XGB) achieved the best performance. The MAE, RMSE, and MAPE errors before and during the COVID-19 pandemic are lower than 3% on average for household registration in Wuhan and non-household registration in Wuhan. Conclusions: Research finds machine learning is reasonable in predicting LOS before and during the COVID-19 pandemic. This study offers valuable guidance to hospital administrators for planning resource allocation strategies that can effectively meet the demand. Consequently, these insights contribute to improved quality of care and wiser utilization of scarce resources. [ABSTRACT FROM AUTHOR]

Anchored in framing theory and the public arenas model, this study investigates the representation and temporal evolution of genetic modification (GM) risk frames on Chinese social media. Through analysis of public discussions on GM risks from 2010 to 2020, and utilising an integration of unsupervised machine learning and computational grounded theory methodologies, this study develops a categorisation schema of 13 GM risk frames. These frames span the full lifecycle of risk social construction, from identification and definition through assessment, social negotiation, attribution, impact evaluation, to management and mitigation. The findings reveal that GM risk discourses are multifaceted, with systematic differences in frame adoption among social actors including government agencies, experts, media outlets, and the general public. The study demonstrates that GM risk frame evolution aligns closely with public attention cycles, exhibiting three distinct patterns: fluctuating decline, punctuated equilibrium, and fluctuating increase. Additionally, it is found that key events or crises catalyse both quantitative changes in frame prominence and qualitative transformations in how GM risks are framed. [ABSTRACT FROM AUTHOR]

Simple Summary: This study aimed to develop new machine learning models to support thyroid cancer diagnosis by assessing tumor malignancy. The research utilized a publicly available dataset containing patient data from Shengjing Hospital of China Medical University. The primary innovation of this study lies in applying the naked mole-rat algorithm, a bio-inspired metaheuristic method, for classifier parameter optimization and feature selection. This approach led to the development of an enhanced version of the LightGBM algorithm, achieving a classification accuracy of 81.82% and an F1-score of 86.62%. Additionally, explainability analysis of the model was conducted using SHAP values. Modern technologies, particularly artificial intelligence methods such as machine learning, hold immense potential for supporting doctors with cancer diagnostics. This study explores the enhancement of popular machine learning methods using a bio-inspired algorithm—the naked mole-rat algorithm (NMRA)—to assess the malignancy of thyroid tumors. The study utilized a novel dataset released in 2022, containing data collected at Shengjing Hospital of China Medical University. The dataset comprises 1232 records described by 19 features. In this research, 10 well-known classifiers, including XGBoost, LightGBM, and random forest, were employed to evaluate the malignancy of thyroid tumors. A key innovation of this study is the application of the naked mole-rat algorithm for parameter optimization and feature selection within the individual classifiers. Among the models tested, the LightGBM classifier demonstrated the highest performance, achieving a classification accuracy of 81.82% and an F1-score of 86.62%, following two-level parameter optimization and feature selection using the naked mole-rat algorithm. Additionally, explainability analysis of the LightGBM model was conducted using SHAP values, providing insights into the decision-making process of the model. [ABSTRACT FROM AUTHOR]

The rapid development of rural regions, the mountainous landscape, and frequent subtropical-typhoon-related rainfall have collectively contributed to a high incidence of cut slope-induced landslides in the coastal areas of eastern China. Despite the escalating risk, there has been a noticeable absence of comprehensive hazard assessments and targeted management measures for private housing and road construction in these rural environments. This paper introduces a novel approach for mitigating such risks by employing a susceptibility evaluation framework grounded in machine learning and uncertainty methods, combined with a double-index rainfall intensity-duration (I-D) threshold model. The proposed Intelligent Slope Prevention System operates through a sequential four-step process: (i) Site-specific landslide susceptibility is assessed through cut slope feature investigations and the use of three machine learning algorithms, namely, Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Network (ANN); (ii) the double-index model calculates rainfall thresholds, accounting for both prolonged continuous rainfall and short-term heavy rainfall events; (iii) the integration of rainfall thresholds with susceptibility assessments allows for the categorization of hazard levels; and (iv) tailored management strategies are deployed for data collection and early warning issuance. The study demonstrates that the SVM achieved the highest prediction accuracy across soil, rock-soil mixed, and rock slopes. The double-index model further enhanced the system's performance by predicting all 20 rainfall-induced landslides, with 15 of them falling under high or very high warning levels. An empirical evaluation during a heavy rainfall event on 29th June 2021 confirmed the system's effectiveness in identifying high-hazard areas and issuing timely warnings, thus significantly mitigating potential damage. Implemented in the coastal mountain basins of eastern China, the Intelligent Slope Prevention System leverages the gathered knowledge to manage and regulate slope hazards effectively, thereby enhancing the safety of both residential and infrastructural assets. [ABSTRACT FROM AUTHOR]

Magnitude prediction is a key focus in earthquake science research, and using machine learning models to analyze seismic data, identify pre-seismic anomalies, and improve prediction accuracy is of great scientific and practical significance. Taking the southern part of China's North–South Seismic Belt (20° N~30° N, 96° E~106° E), where strong earthquakes frequently occur, as an example, we used the sliding time window method to calculate 11 seismicity indicators from the earthquake catalog data as the characteristic parameters of the training model, and compared six machine learning models, including the random forest (RF) and long short-term memory (LSTM) models, to select the best-performing LSTM model for predicting the maximum magnitude of an earthquake in the study area in the coming year. The experimental results show that the LSTM model performs exceptionally well in predicting earthquakes of magnitude 5 < ML ≤ 6 within the time window of the test set, with a prediction success rate of 85%. Additionally, the study explores how different time windows, spatial locations, and parameter choices affect model performance. It found that longer time windows and key seismicity parameters, such as the b-value and the square root of total seismic energy, are crucial for improving prediction accuracy. Finally, we propose a magnitude interval-based assessment method to better predict the actual impacts that different magnitudes may cause. This method demonstrates the LSTM model's potential in predicting moderate to strong earthquakes and offers new approaches for earthquake early warning and disaster mitigation. [ABSTRACT FROM AUTHOR]

Background: Methods for accurately predicting the prognosis of patients with recurrent hepatolithiasis (RH) after biliary surgery are lacking. This study aimed to develop a model that dynamically predicts the risk of hepatolithiasis recurrence using a machine-learning (ML) approach based on multiple clinical high-order correlation data. Materials and methods: Data from patients with RH who underwent surgery at five centres between January 2015 and December 2020 were collected and divided into training and testing sets. Nine predictive models, which we named the Correlation Analysis and Recurrence Evaluation System (CARES), were developed and compared using machine learning (ML) methods to predict the patients' dynamic recurrence risk within 5 post-operative years. We adopted a k-fold cross validation with k = 10 and tested model performance on a separate testing set. The area under the receiver operating characteristic curve was used to evaluate the performance of the models, and the significance and direction of each predictive variable were interpreted and justified based on Shapley Additive Explanations. Results: Models based on ML methods outperformed those based on traditional regression analysis in predicting the recurrent risk of patients with RH, with Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) showing the best performance, both yielding an AUC (Area Under the receiver operating characteristic Curve) of∼0.9 or higher at predictions. These models were proved to have even better performance on testing sets than in a 10-fold cross validation, indicating that the model was not overfitted. The SHAP method revealed that immediate stone clearance, final stone clearance, number of previous surgeries, and preoperative CA19-9 index were the most important predictors of recurrence after reoperation in RH patients. An online version of the CARES model was implemented. Conclusion: The CARES model was firstly developed based on ML methods and further encapsulated into an online version for predicting the recurrence of patients with RH after hepatectomy, which can guide clinical decision-making and personalised postoperative surveillance. [ABSTRACT FROM AUTHOR]

Aims: Non-suicidal self-injury (NSSI) is a serious issue that is increasingly prevalent among children and adolescents, especially in rural areas. Developing a suitable predictive model for NSSI is crucial for early identification and intervention. Methods: This study included 2090 Chinese rural children and adolescents. Participants' sociodemographic information, symptoms of anxiety as well as depression, personality traits, family environment and NSSI behaviors were collected through a questionnaire survey. Gender, age, grade, and all survey results except sociodemographic information were used as relevant factors for prediction. Support vector machines, decision tree and random forest models were trained and validated by the train set and valid set, respectively. The metrics of each model were tested and compared to select the most suitable one. Furthermore, the mean decrease Gini index was calculated to measure the importance of relevant factors. Results: The prevalence of NSSI was 38.3%. Out of the 6 models assessed, the random forest model demonstrated the highest suitability in predicting the prevalence of NSSI. It achieved sensitivity, specificity, AUC, accuracy, precision, and F1 scores of 0.65, 0.72, 0.76, 0.70, 0.57, and 0.61, respectively. Anxiety and depression were the top two contributing factors in the prediction model. Neuroticism and conflict were the factors that contributed the most to personality traits and family environment, respectively, in terms of prediction. In addition, demographic factors contributed little to the prediction in this study. Conclusion: This study focused on Chinese children and adolescents in rural areas and demonstrated the potential of using machine learning approaches in predicting NSSI. Our research complements the application of machine learning methods to psychiatric and psychological problems. [ABSTRACT FROM AUTHOR]

Aims: Early identification and intervention of the frailty of the elderly will help lighten the burden of social medical care and improve the quality of life of the elderly. Therefore, we used machine learning (ML) algorithm to develop models to predict frailty risk in the elderly. Design: A prospective cohort study. Methods: We collected data on 6997 elderly people from Chinese Longitudinal Healthy Longevity Study wave 6–7 surveys (2011–2012, 2014). After the baseline survey in 1998 (wave 1), the project conducted follow‐up surveys (wave 2–8) in 2000–2018. The osteoporotic fractures index was used to assess frailty. Four ML algorithms (random forest [RF], support vector machine, XGBoost and logistic regression [LR]) were used to develop models to identify the risk factors of frailty and predict the risk of frailty. Different ML models were used for the prediction of frailty risk in the elderly and frailty risk was trained on a cohort of 4385 elderly people with frailty (split into a training cohort [75%] and internal validation cohort [25%]). The best‐performing model for each study outcome was tested in an external validation cohort of 6997 elderly people with frailty pooled from the surveys (wave 6–7). Model performance was assessed by receiver operating curve and F2‐score. Results: Among the four ML models, the F2‐score values were similar (0.91 vs. 0.91 vs. 0.88 vs. 0.90), and the area under the curve (AUC) values of RF model was the highest (0.75), followed by LR model (0.74). In the final two models, the AUC values of RF and LR model were similar (0.77 vs. 0.76) and their accuracy was identical (87.4% vs. 87.4%). Conclusion: Our study developed a preliminary prediction model based on two different ML approaches to help predict frailty risk in the elderly. Impact: The presented models from this study can be used to inform healthcare providers to predict the frailty probability among older adults and maybe help guide the development of effective frailty risk management interventions. Implications for the Profession and/or Patient Care: Detecting frailty at an early stage and implementing timely targeted interventions may help to improve the allocation of health care resources and to reduce frailty‐related burden. Identifying risk factors for frailty could be beneficial to provide tailored and personalized care intervention for older adults to more accurately prevent or improve their frail conditions so as to improve their quality of life. Reporting Method: The study has adhered to STROBE guidelines. Patient or Public Contribution: No patient or public contribution. [ABSTRACT FROM AUTHOR]

To establish a predictive model for clinical pregnancy outcomes following the transfer of a single fresh blastocyst in vitro fertilization (IVF). 615 patients (492 in training set and 123 in test set) who underwent the first single and fresh blastocyst transfer in the first IVF or intracytoplasmic sperm injection cycle performed in fertility centre of Shenzhen Zhongshan Obstetrics & Gynecology Hospital from July 2015 to June 2021 were enrolled in this study. Conventional method such as logistic regression (LR), individual machine learning methods including naive bayesian (NB), K-nearest neighbours (K-NN), support vector machine (SVM), decision tree (DT), and ensemble learning methods including random forest (RF), XGBoost, LightGBM, Voting were used to establish the clinical pregnancy outcome prediction model, and the efficacy among different models was compared. Three major types of prediction models, including conventional method: LR (AUC = 0.707), individual machine learning classifiers: NB (AUC = 0.741), K-NN (AUC = 0.719), SVM (AUC = 0.761), DT (AUC = 0.728), ensemble models: RF (AUC = 0.790), XGBoost (AUC = 0.799), LightGBM (AUC = 0.794), Voting (AUC = 0.845) were established. It was found that the performance of the voting model was best. This study revealed that a voting classifier can provide a more accurate estimate of IVF outcome, which can assist clinicians to make individual patient counselling. [ABSTRACT FROM AUTHOR]

Automatically detecting Ulva prolifera (U. prolifera) in rainy and cloudy weather using remote sensing imagery has been a long-standing problem. Here, we address this challenge by combining high-resolution Synthetic Aperture Radar (SAR) imagery with the machine learning, and detect the U. prolifera of the South Yellow Sea of China (SYS) in 2021. The findings indicate that the Random Forest model can accurately and robustly detect U. prolifera, even in the presence of complex ocean backgrounds and speckle noise. Visual inspection confirmed that the method successfully identified the majority of pixels containing U. prolifera without misidentifying noise pixels or seawater pixels as U. prolifera. Additionally, the method demonstrated consistent performance across different images, with an average Area Under Curve (AUC) of 0.930 (±0.028). The analysis yielded an overall accuracy of over 96%, with an average Kappa coefficient of 0.941 (±0.038). Compared to the traditional thresholding method, Random Forest model has a lower estimation error of 14.81%. Practical application indicates that this method can be used in the detection of unprecedented U. prolifera in 2021 to derive continuous spatiotemporal changes. This study provides a potential new method to detect U. prolifera and enhances our understanding of macroalgal outbreaks in the marine environment. [ABSTRACT FROM AUTHOR]

High-spatiotemporal-resolution and accurate soil moisture (SM) data are crucial for investigating climate, hydrology, and agriculture. Existing SM products do not yet meet the demands for high spatiotemporal resolution. The objective is to develop and evaluate a retrieval framework to derive SM estimates with high spatial (100 m) and temporal (<3 days) resolution that can be used on a national scale in China. Therefore, this study integrates multi-source data, including optical remote sensing (RS) data from Sentinel-2 and Landsat-7/8/9, synthetic aperture radar (SAR) data from Sentinel-1, and auxiliary data. Four machine learning and deep learning algorithms are applied, including Random Forest Regression (RFR), Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM) networks, and Ensemble Learning (EL). The integrated framework (IF) considers three feature scenarios (SC1: optical RS + auxiliary data, SC2: SAR + auxiliary data, SC3: optical RS + SAR + auxiliary data), encompassing a total of 33 features. The results are as follows: (1) The correlation coefficients (r) between auxiliary data (such as sand fraction, r = −0.48; silt fraction, r = 0.47; and evapotranspiration, r = −0.42), SAR features (such as the backscatter coefficients for VV-pol ( σ v v 0 ), r = 0.47), and optical RS features (such as Shortwave Infrared Band 2 (SWIR2) reflectance data from Sentinel-2 and Landsat-7/8/9, r = −0.39) with observed SM are significant. This indicates that multi-source data can provide complementary information for SM monitoring. (2) Compared to XGBoost and LSTM, RFR and EL demonstrate superior overall performance and are the preferred models for SM prediction. Their R2 for the training and test sets exceed 0.969 and 0.743, respectively, and their ubRMSE are below 0.022 and 0.063 m3/m3, respectively. (3) The SM prediction accuracy is highest for the scenario of optical + SAR + auxiliary data, followed by SAR + auxiliary data, and finally optical + auxiliary data. (4) With an increasing Normalized Difference Vegetation Index (NDVI) and SM values, the trained models exhibit a general decrease in prediction performance and accuracy. (5) In 2021 and 2022, without considering cloud cover, the IF theoretically achieved an SM revisit time of 1–3 days across 95.01% and 96.53% of China's area, respectively. However, SC1 was able to achieve a revisit time of 1–3 days over 60.73% of China's area in 2021 and 69.36% in 2022, while the area covered by SC2 and SC3 at this revisit time accounted for less than 1% of China's total area. This study validates the effectiveness of combining multi-source RS data with auxiliary data in large-scale SM monitoring and provides new methods for improving SM retrieval accuracy and spatiotemporal coverage. [ABSTRACT FROM AUTHOR]

Background: The construction of a robust healthcare information system is fundamental to enhancing countries' capabilities in the surveillance and control of hepatitis B virus (HBV). Making use of China's rapidly expanding primary healthcare system, this innovative approach using big data and machine learning (ML) could help towards the World Health Organization's (WHO) HBV infection elimination goals of reaching 90% diagnosis and treatment rates by 2030. We aimed to develop and validate HBV detection models using routine clinical data to improve the detection of HBV and support the development of effective interventions to mitigate the impact of this disease in China. Methods: Relevant data records extracted from the Family Medicine Clinic of the University of Hong Kong-Shenzhen Hospital's Hospital Information System were structuralized using state-of-the-art Natural Language Processing techniques. Several ML models have been used to develop HBV risk assessment models. The performance of the ML model was then interpreted using the Shapley value (SHAP) and validated using cohort data randomly divided at a ratio of 2:1 using a five-fold cross-validation framework. Results: The patterns of physical complaints of patients with and without HBV infection were identified by processing 158,988 clinic attendance records. After removing cases without any clinical parameters from the derivation sample (n=105,992), 27,392 cases were analysed using six modelling methods. A simplified model for HBV using patients' physical complaints and parameters was developed with good discrimination (AUC = 0.78) and calibration (goodness of fit test p-value >0.05). Conclusions: Suspected case detection models of HBV, showing potential for clinical deployment, have been developed to improve HBV surveillance in primary care setting in China. (Word count: 264) [ABSTRACT FROM AUTHOR]

Background: High-need, high-cost (HNHC) patients are a major focus of international healthcare reform. However, research on HNHC children in China remains limited. This study aims to classify HNHC pediatric patients, analyze the differences among groups, and explore the factors influencing HNHC status. Methods: Data were obtained from a retrospective observational cohort of hospitalized children in Shanghai, China from 2017 to 2023. K-means clustering, one of the unsupervised learning algorithms, was employed to classify patients according to their HNHC status. Descriptive statistical analysis and the Kruskal-Wallis H test were used to describe and test the differences among different groups, with the logit regression models to analyze the predictors. Results: 688,131 hospitalized children were classified into three groups: 1,871 persistent HNHC, 32,539 episodic HNHC, and 653,721 non-HNHC. Significant differences were observed among these groups. Persistent HNHC patients have significantly higher costs and longer HNHC durations compared to episodic and non-HNHC patients, who were more likely to be aged 30 days to 1 year or 13–18 years, female with only one type of health insurance, and leukemia was the most prevalent and costly disease. They exhibited distinct healthcare utilization patterns, including emergency admissions, higher surgery rates, longer hospital stays, more frequent hospitalizations, and a preference for tertiary and specialized hospitals in city centers. Multiple influencing factors of persistent HNHC versus episodic HNHC and non-HNHC were identified. Conclusion: This study provides valuable insights into the classification, characteristics, and influencing factors of persistent, episodic, and non-HNHC hospitalized children in China. Persistent HNHC patients warrant targeted interventions to improve health outcomes and reduce healthcare costs. Enhanced medical coverage for key diseases, high-quality healthcare services tailored to their needs, and early interventions are crucial. [ABSTRACT FROM AUTHOR]

We developed an interpretable model, BOUND (Bayesian netwOrk for large-scale lUng caNcer Digital prescreening), using a comprehensive EHR dataset from the China to improve lung cancer detection rates. BOUND employs Bayesian network uncertainty inference, allowing it to predict lung cancer risk even with missing data and identify high-risk factors. Developed using data from 905,194 individuals, BOUND achieved an AUC of 0.866 in internal validation, with time- and geography-based external validations yielding AUCs of 0.848 and 0.841, respectively. In datasets with 10%–70% missing data, AUC ranged from 0.827 – 0.746. The model demonstrates strong calibration, clinical utility, and robust performance in both balanced and imbalanced datasets. A risk scorecard was also created, improving detection rates up to 6.8 times, available free online (https://drzhang1.aiself.net/). BOUND enables non-radiative, cost-effective lung cancer prescreening, excels with missing data, and addresses treatment inequities in resource-limited primary healthcare settings. [ABSTRACT FROM AUTHOR]

Background: Patients with migraine often experience not only headache pain but also cognitive dysfunction, particularly in attention, which is frequently overlooked in both diagnosis and treatment. The influence of these attentional deficits on the pain-related clinical characteristics of migraine remains poorly understood, and clarifying this relationship could improve care strategies. Methods: This study included 52 patients with migraine and 34 healthy controls. We employed the Attentional Network Test for Interactions and Vigilance–Executive and Arousal Components paradigm, combined with electroencephalography, to assess attentional deficits in patients with migraine, with an emphasis on phasic alerting, orienting, executive control, executive vigilance, and arousal vigilance. An extreme gradient boosting binary classifier was trained on features showing group differences to distinguish patients with migraine from healthy controls. Moreover, an extreme gradient boosting regression model was developed to predict clinical characteristics of patients with migraine using their attentional deficit features. Results: For general performance, patients with migraine presented a larger inverse efficiency score, a higher prestimulus beta-band power spectral density and a lower gamma-band event-related synchronization at Cz electrode, and stronger high alpha-band activity at the primary visual cortex, compared to healthy controls. Although no behavior differences in three basic attentional networks were found, patients showed magnified N1 amplitude and prolonged latency of P2 for phasic alerting-trials as well as an increased orienting evoked-P1 amplitude. For vigilance function, improvements in the hit rate of executive vigilance-trials were exhibited in controls but not in patients. Besides, patients with migraine exhibited longer reaction time as well as larger variability in arousal vigilance-trials than controls. The binary classifier developed by such attentional deficit features achieved an F1 score of 0.762 and an accuracy of 0.779 in distinguishing patients with migraine from healthy controls. Crucially, the predicted value available from the regression model involving attentional deficit features significantly correlated with the real value for the frequency of headache. Conclusions: Patients with migraine demonstrated significant attentional deficits, which can be used to differentiate migraine patients from healthy populations and to predict clinical characteristics. These findings highlight the need to address cognitive dysfunction, particularly attentional deficits, in the clinical management of migraine. [ABSTRACT FROM AUTHOR]

Based on upper echelon theory, we employ machine learning to explore how CEO characteristics influence corporate violations using a large-scale dataset of listed firms in China for the period 2010–2020. Comparing ten machine learning methods, we find that eXtreme Gradient Boosting (XGBoost) outperforms the other models in predicting corporate violations. An interpretable model combining XGBoost and SHapley Additive exPlanations (SHAP) indicates that CEO characteristics play a central role in predicting corporate violations. Tenure has the strongest predictive power and is negatively associated with corporate violations, followed by marketing experience, education, duality (i.e., simultaneously holding the position of chairperson), and research and development experience. In contrast, shareholdings, age, and pay are positively related to corporate violations. We also analyze violation severity and violation type, confirming the role of tenure in predicting more severe and intentional violations. Overall, our findings contribute to preventing corporate violations, improving corporate governance, and maintaining order in the financial market. [ABSTRACT FROM AUTHOR]

Background and Aims: To study the unknown influencing factors of delayed medical treatment behavior in oral cancer patients in western China and to develop a prediction model on the risk of delayed medical treatment in oral cancer patients. Method: We investigated oral cancer patients attending a tertiary Grade A dental hospital in western China from June 2022 to July 2023. The logistic regression and four machine learning models (nearest neighbors, the RBF SVM, random forest, and QDA) were used to identify risk factors and establish a risk prediction model. We used the established model to predict the data before and after the COVID-19 pandemic and test whether the prediction effect can still remain stable and accurate under the interference of COVID-19. Result: Out of the 495 patients included in the study, 122 patients (58.65%) delayed seeking medical treatment before the lifting of the restrictions of the pandemic, while 153 patients (53.13%) did so after the lifting of restrictions. The logistic regression model revealed that living with adult children was a protective factor for patients in delaying seeking medical attention, regardless of the implementation of pandemic control measures. After comparing each model, it was found that the statistical indicators of the random forest algorithm such as the AUC score (0.8380) and specificity (0.8077) ranked first, with the best prediction performance and stable performance. Conclusions: This study systematically elucidates the critical factors influencing patient delay behavior in oral cancer diagnosis and treatment, employing a comprehensive risk prediction model that accurately identifies individuals at an elevated risk of delay. It represents a pioneering large-scale investigation conducted in western China, focusing explicitly on the multifaceted factors affecting the delayed medical treatment behavior of oral cancer patients. The findings underscore the imperative of implementing early intervention strategies tailored to mitigate these delays. Furthermore, this study emphasizes the pivotal role of robust social support systems and positive family dynamics in facilitating timely access to healthcare services for oral cancer patients, thereby potentially improving outcomes and survival rates. [ABSTRACT FROM AUTHOR]

Land use and cover change (LUCC) is a key factor influencing global environmental and socioeconomic systems. Many long-term geospatial LUCC datasets have been developed at various scales during the recent decades owing to the availability of long-term satellite data, statistical data and computational techniques. However, most existing LUCC products cannot accurately reflect the spatiotemporal change patterns of LUCC at the regional scale in China. Based on these geospatial LUCC products, normalized difference vegetation index (NDVI), socioeconomic data and statistical data, we developed multiple procedures to represent both the spatial and temporal changes of the major LUC types by applying machine-learning, regular decision-tree and hierarchical assignment methods using northeastern China (NEC) as a case study. In this approach, each individual LUC type was developed in sequence under different schemes and methods. The accuracy evaluation using sampling plots indicated that our approach can accurately reflect the actual spatiotemporal patterns of LUC shares in NEC, with an overall accuracy of 82%, Kappa coefficient of 0.77 and regression coefficient of 0.82. Further comparisons with existing LUCC datasets and statistical data also indicated the accuracy of our approach and datasets. Our approach unfolded the mixed-pixel issue of LUC types and integrated the strengths of existing LUCC products through multiple fusion processes. The analysis based on our developed dataset indicated that forest, cropland and built-up land area increased by 17.11 × 104 km2, 15.19 × 104 km2 and 2.85 × 104 km2, respectively, during 1980–2020, while grassland, wetland, shrubland and bare land decreased by 26.06 × 104 km2, 4.24 × 104 km2, 3.97 × 104 km2 and 0.92 × 104 km2, respectively, in NEC. Our developed approach accurately reconstructed the shares and spatiotemporal patterns of all LUC types during 1980–2020 in NEC. This approach can be further applied to the entirety of China, and worldwide, and our products can provide accurate data supports for studying LUCC consequences and making effective land use policies. [ABSTRACT FROM AUTHOR]

While it is widely recognized that a country's bureaucratic structure significantly influences economic growth, its subnational variations remain relatively unexplored. To address this gap, this paper introduces a unique model to quantify the collective career incentives of subnational leadership in China. By adopting machine-learning techniques that incorporate 250 individual features, this study derives a predicted probability of promotion as a proxy to measure an official's career prospects. The individual career prospects are subsequently transformed into collective career incentives through an inverse-U-shaped relationship between the two. The empirical findings indicate that from 1997 to 2015, Chinese provincial governments achieved higher economic growth rates when a larger proportion of officials held mid-range rankings in terms of career prospects. This study also finds that the better economic performance stemmed from the collective career incentives of provincial leadership, rather than those of the supreme leaders of the province. [ABSTRACT FROM AUTHOR]

Objective: To establish the dynamic treatment strategy of Chinese medicine (CM) for metastatic colorectal cancer (mCRC) by machine learning algorithm, in order to provide a reference for the selection of CM treatment strategies for mCRC. Methods: From the outpatient cases of mCRC in the Department of Oncology at Xiyuan Hospital, China Academy of Chinese Medical Sciences, 197 cases that met the inclusion criteria were screened. According to different CM intervention strategies, the patients were divided into 3 groups: CM treatment alone, equal emphasis on Chinese and Western medicine treatment (CM combined with local treatment of tumors, oral chemotherapy, or targeted drugs), and CM assisted Western medicine treatment (CM combined with intravenous regimen of Western medicine). The survival time of patients undergoing CM intervention was taken as the final evaluation index. Factors affecting the choice of CM intervention scheme were screened as decision variables. The dynamic CM intervention and treatment strategy for mCRC was explored based on the cost-sensitive classification learning algorithm for survival (CSCLSurv). Patients' survival was estimated using the Kaplan-Meier method, and the survival time of patients who received the model-recommended treatment plan were compared with those who received actual treatment plan. Results: Using the survival time of patients undergoing CM intervention as the evaluation index, a dynamic CM intervention therapy strategy for mCRC was established based on CSCLSurv. Different CM intervention strategies for mCRC can be selected according to dynamic decision variables, such as gender, age, Eastern Cooperative Oncology Group score, tumor site, metastatic site, genotyping, and the stage of Western medicine treatment at the patient's first visit. The median survival time of patients who received the model-recommended treatment plan was 35 months, while those who receive the actual treatment plan was 26.0 months (P=0.06). Conclusions: The dynamic treatment strategy of CM, based on CSCLSurv for mCRC, plays a certain role in providing clinical hints in CM. It can be further improved in future prospective studies with larger sample sizes. [ABSTRACT FROM AUTHOR]

Background: Circadian rhythm disruption is typical in Parkinson's disease (PD) early stage, and it plays an important role in the prognosis of the treatment effect in the advanced stage of PD. There is growing evidence that circadian rhythm genes can influence development of PD. Therefore, this study explored specific regulatory mechanism of circadian genes (C-genes) in PD through bioinformatic approaches. Methods: Differentially expressed genes (DEGs) between PD and control samples were identified from GSE22491 using differential expression analysis. The key model showing the highest correlation with PD was derived through WGCNA analysis. Then, DEGs, 1,288 C-genes and genes in key module were overlapped for yielding differentially expressed C-genes (DECGs), and they were analyzed for LASSO and SVM-RFE for yielding critical genes. Meanwhile, from GSE22491 and GSE100054, receiver operating characteristic (ROC) was implemented on critical genes to identify biomarkers, and Gene Set Enrichment Analysis (GSEA) was applied for the purpose of exploring pathways involved in biomarkers. Eventually, immune infiltrative analysis was applied for understanding effect of biomarkers on immune microenvironment, and therapeutic drugs which could affect biomarkers expressions were also predicted. Finally, we verified the expression of the genes by q-PCR. Results: Totally 634 DEGs were yielded between PD and control samples, and MEgreen module had the highest correlation with PD, thus it was defined as key model. Four critical genes (AK3, RTN3, CYP4F2, and LEPR) were identified after performing LASSO and SVM-RFE on 18 DECGs. Through ROC analysis, AK3, RTN3, and LEPR were identified as biomarkers due to their excellent ability to distinguish PD from control samples. Besides, biomarkers were associated with Parkinson's disease and other functional pathways. Conclusion: Through bioinformatic analysis, the circadian rhythm related biomarkers were identified (AK3, RTN3 and LEPR) in PD, contributing to studies related to PD treatment. [ABSTRACT FROM AUTHOR]

Accurate and fine‐scaled prediction of ozone concentrations across space and time, as well as the assessment of associated human risks, is crucial for protecting public health and promoting environmental conservation. This paper introduces NetGBM, an innovative machine‐learning model designed to comprehensively model ozone levels across China's diverse topography and analyze the spatiotemporal distribution of ozone and exposure. Our model focuses on daily, weekly, and monthly predictions, achieving commendable R2 ${\mathrm{R}}^{2}$ coefficients of 0.83, 0.77, and 0.79, respectively. By constructing a gridded map of ozone and incorporating both land use and meteorological features into each grid, we achieved ozone prediction at a high spatiotemporal resolution, outperforming previous research in terms of performance and scale, particularly in regions with limited monitoring stations. The results can be further improved when applied to regional research using meteorological and ozone data from regional stations. Additionally, our research revealed that temperature is the most significant factor affecting ozone concentrations across China. In health risk assessment, we retrieved a high‐resolution spatial distribution of ozone‐attributed mortality for 5‐COD and daily ozone inhalation distributions during our study period. We concluded that ozone‐attributed mortality is predominantly caused by stroke and IHD, accounting for more than 70% of the total deaths in 2021, with the highest mortality rates in developed urban areas such as the NCP and the YRD. Our experiment demonstrated the potential of NetGBM in robustly modeling ozone across China with high spatiotemporal resolution and its applicability in measuring associated health risks. Plain Language Summary: This study introduces NetGBM, an innovative machine‐learning model designed to forecast ozone levels and assess ozone‐attributed public health risks. This model is crucial for post‐pandemic air quality management, providing high‐resolution predictions that are essential for targeted health interventions and informed environmental policies. By integrating feature engineering with predictive analytics, NetGBM enhances its performance, particularly in regions with limited monitoring. This makes it a robust tool for developing sustainable environmental strategies. Key Points: We introduce NetGBM, a machine‐learning model for high spatiotemporal resolution ozone prediction across ChinaWe perform ozone inhalation and GEMM analysis, which identifies regions facing elevated health risks due to high ozone exposureThe NetGBM model has superior performance compared to prior research and performs robustly in regions with limited monitoring resources [ABSTRACT FROM AUTHOR]

Objective: To evaluate the effectiveness of multimodal features based on gait analysis and eye tracking for elderly people screening with subjective cognitive decline in the community. Methods: In the study, 412 cognitively normal older adults aged over 65 years were included. Among them, 230 individuals were diagnosed with nonsubjective cognitive decline and 182 with subjective cognitive decline. All participants underwent assessments using three screening tools: the traditional SCD9 scale, gait analysis, and eye tracking. The gait analysis involved three tasks: the single task, the counting backwards dual task, and the naming animals dual task. Eye tracking included six paradigms: smooth pursuit, median fixation, lateral fixation, overlap saccade, gap saccade, and anti-saccade tasks. Using the XGBoost machine learning algorithm, several models were developed based on gait analysis and eye tracking to classify subjective cognitive decline. Results: A total of 161 gait and eye-tracking features were measured. 22 parameters, including 9 gait and 13 eye-tracking features, showed significant differences between the two groups (p < 0.05). The top three eye-tracking paradigms were anti-saccade, gap saccade, and median fixation, with AUCs of 0.911, 0.904, and 0.891, respectively. The gait analysis features had an AUC of 0.862, indicating better discriminatory efficacy compared to the SCD9 scale, which had an AUC of 0.762. The model based on single and dual task gait, antisaccade, gap saccade, and median fixation achieved the best efficacy in SCD screening (AUC = 0.969). Conclusion: The gait analysis, eye-tracking multimodal assessment tool is an objective and accurate screening method that showed better detection of subjective cognitive decline. This finding provides another option for early identification of subjective cognitive decline in the community. [ABSTRACT FROM AUTHOR]

Informed by the biopsychosocial framework, our study uses the Chinese Longitudinal Healthy Longevity Survey (CLHLS) dataset to examine cognitive function trajectories among the oldest-old (80+). Employing K-means clustering, we identified two latent groups: High Stability (HS) and Low Stability (LS). The HS group maintained satisfactory cognitive function, while the LS group exhibited consistently low function. Lasso regression revealed predictive factors, including socioeconomic status, biological conditions, mental health, lifestyle, psychological, and behavioral factors. This data-driven approach sheds light on cognitive aging patterns and informs policies for healthy aging. Our study pioneers non-parametric machine learning methods in this context. [ABSTRACT FROM AUTHOR]

Fractional vegetation cover (FVC) is a crucial indicator for measuring the growth of surface vegetation. The changes and predictions of FVC significantly impact biodiversity conservation, ecosystem health and stability, and climate change response and prediction. Southwest China (SWC) is characterized by complex topography, diverse climate types, and rich vegetation types. This study first analyzed the spatiotemporal variation of FVC at various timescales in SWC from 2000 to 2020 using FVC values derived from pixel dichotomy model. Next, we constructed four machine learning models—light gradient boosting machine (LightGBM), support vector regression (SVR), k-nearest neighbor (KNN), and ridge regression (RR)—along with a weighted average heterogeneous ensemble model (WAHEM) to predict growing-season FVC in SWC from 2000 to 2023. Finally, the performance of the different ML models was comprehensively evaluated using tenfold cross-validation and multiple performance metrics. The results indicated that the overall FVC in SWC predominantly increased from 2000 to 2020. Over the 21 years, the FVC spatial distribution in SWC generally showed a high east and low west pattern, with extremely low FVC in the western plateau of Tibet and higher FVC in parts of eastern Sichuan, Chongqing, Guizhou, and Yunnan. The determination coefficient R2 scores from tenfold cross-validation for the four ML models indicated that LightGBM had the strongest predictive ability whereas RR had the weakest. WAHEM and LightGBM models performed the best overall in the training, validation, and test sets, with RR performing the worst. The predicted spatial change trends were consistent with the MODIS-MOD13A3-FVC and FY3D-MERSI-FVC, although the predicted FVC values were slightly higher but closer to the MODIS-MOD13A3-FVC. The feature importance scores from the LightGBM model indicated that digital elevation model (DEM) had the most significant influence on FVC among the six input features. In contrast, soil surface water retention capacity (SSWRC) was the most influential climate factor. The results of this study provided valuable insights and references for monitoring and predicting the vegetation cover in regions with complex topography, diverse climate types, and rich vegetation. Additionally, they offered guidance for selecting remote sensing products for vegetation cover and optimizing different ML models. [ABSTRACT FROM AUTHOR]

Background: Numerous higher education institutions worldwide have adopted English‐language‐medium computer science courses and integrated online problem‐solving competitions to bridge gaps in theory and practice (Alhamami Education and Information Technologies, 2021; 26: 6549–6562). Objectives: This study aimed to investigate the factors influencing the use of online competitions in machine learning courses and their impact on student learning. We also analyse disparities in learning outcomes and instructional language effects (Chinese vs. English). Methods: Among 123 participants at northern Taiwan university, 74 chose Chinese instruction (CMI), and 49 opted for English instruction (EMI). The course spanned 18 weeks: team formation in week one, data analysis, machine learning, and deep learning from week 2 to 8, draft proposals and oral presentations by week 9, instructor guidance in weeks 9–17, followed by off‐campus competitions. In week 18, students presented projects for evaluation by judges. Results: The results showed improved scores in competition proposal writing and oral presentations, especially for CMI students, who excelled in these areas and in terms of creativity. CMI students emphasized domain knowledge, implementation completeness, and technical depth in proposals. The EMI students focused on implementation completeness and artificial intelligence model accuracy, along with creativity. Conclusion: CMI students achieved superior outcomes in machine learning courses, particularly in terms of competition proposals, oral presentations, and increased creativity. Instructional language choice significantly influenced learning trajectories, leading to distinct knowledge development focuses for CMI and EMI. Lay Description: What is already known about this topic: Historically, artificial intelligence (AI) education focused on theory and skills, but now there are AI competitions that encourage real‐world problem‐solving (AIdea. Competitions. 2023. https://aidea-web.tw/about?lang=zh).Competition‐based learning bridges the gap between academia and industry, fostering creativity and talent discovery (Abou‐Warda and Roberts. International Journal of Educational Management. 2016; 30(5): 698).Computer science education globally uses English as the primary language (Alhamami. Education and Information Technologies, 2021; 26: 6549–6562).Non‐English speaking nations are adopting English as the medium of instruction, impacting teaching effectiveness (Alhamami. Education and Information Technologies, 2021; 26: 6549–6562). What this paper adds: This study combines online problem‐solving competitions with machine learning courses, using both Chinese and English instruction.Individual tutoring tailored to each team's competition topic provided real‐world problem‐solving experience and fostered school‐enterprise interactions.A rubric was created for evaluating domain knowledge, proposal writing, presentation skills, AI model accuracy, and competition outcomes by external experts, instructors, TAs, and peers. Implications for practice and/or policy: Combining competition‐based learning with machine learning courses can boost students' domain knowledge, competition skills, and outcomes.This study confirms that using Chinese instruction in machine learning benefits non‐native English‐speaking students more than English instruction.Our teaching approach for information technology courses can be applied to develop students' relevant skills in this field. [ABSTRACT FROM AUTHOR]

This study offers detailed recommendations on strengthening government support without harming digital finance benefits, especially in negatively affected areas, which is critical for enhancing the inclusiveness of the digital financial landscape and reducing social disparities. This paper uses year 2011–2022 panel data from China's 31 provinces to empirically analyze digital finance's effects, mechanisms, and heterogeneity on agricultural economy resilience with a two-way, fixed-effect model. It further explores each feature's impacts using machine learning methodologies like the random forest, GBRT, SHAP value method, and ALE plot. The findings show that digital finance boosted agri-economy resilience, varying by food-producing status and marketization. Among all the features analyzed, government input, urbanization level, and planting structure emerged as the most critical factors influencing agri-economy resilience. Notably, government input negatively moderated this relationship. The ALE plot revealed non-linear effects of digital finance and planting structure on agri-economy resilience. [ABSTRACT FROM AUTHOR]

Aim: To develop and test different machine learning algorithms for predicting nocturnal hypoglycaemia in patients with type 2 diabetes mellitus. Design: A retrospective study. Methods: We collected data from dynamic blood glucose monitoring of patients with T2DM admitted to the Department of Endocrinology and Metabolism at a hospital in Shanghai, China, from November 2020 to January 2022. Patients undergone the continuous glucose monitoring (CGM) for ≥ 24 h were included in this study. Logistic regression, random forest and light gradient boosting machine algorithms were employed, and the models were validated and compared using AUC, accuracy, specificity, recall rate, precision, F1 score and the Kolmogorov–Smirnov test. Results: A total of 4015 continuous glucose‐monitoring data points from 440 patients were included, and 28 variables were selected to build the risk prediction model. The 440 patients had an average age of 62.7 years. Approximately 48.2% of the patients were female and 51.8% were male. Nocturnal hypoglycaemia appeared in 573 (14.30%) of 4015 continuous glucose monitoring data. The light gradient boosting machine model demonstrated the highest predictive performances: AUC (0.869), specificity (0.802), accuracy (0.801), precision (0.409), recall rate (0.797), F1 score (0.255) and Kolmogorov (0.603). The selected predictive factors included time below the target glucose range, duration of diabetes, insulin use before bed and dynamic blood glucose monitoring parameters from the previous day. Patient or Public Contribution: No Patient or Public Contribution. [ABSTRACT FROM AUTHOR]

Elderly people in regions of China with hot summers and cold winters have significantly higher heat sensitivity than people in other regions and are ambiguous in their subjective perceptions of temperature, humidity, and solar radiation. This makes the elderly more vulnerable to the heat; consequently, when they engage in outdoor activities during the summer wearing light clothing, their diminished thermal perception increases the risk of heat stress injuries. Therefore, to more accurately evaluate the outdoor thermal comfort perception of the elderly in summer, this study used traditional field meteorological measurements, a questionnaire survey, physiological data, and machine learning prediction methods, to establish an outdoor thermal benchmark for retirement communities in hot summer and cold winter regions. Findings from the study reveal that the neutral universal thermal climate index (NUTCI) and the neutral universal thermal climate index range are 25.94°C and 22.23°C to 29.66°C respectively, and that the thermal comfort threshold is 35.39°C. It was also found that for 80% of elderly residents in the two retirement communities studied, the thermal acceptable range is from 19.41°C to 35.07°C. Using these findings as a guide, the thermal categories proposed are neutral 22.23°C to 33.08°C, slightly warm 33.08°C to 39.68°C, warm 39.68°C to 43.52°C, and hot above 43.52°C, with a preferred UTCI of 27.02°C. [ABSTRACT FROM AUTHOR]

Precise and reliable displacement prediction is essential for preventing landslide disasters, but the evolution of landslides is a dynamic process influenced by diverse factors at different stages. Despite advances in the application of machine learning models to landslide displacement prediction, these models struggle to dynamically capture triggers during the prediction process. This limitation not only fails to capture the characteristics of the short-term fast deformation area, thus affecting the overall prediction accuracy, but also fails to establish a connection between the data relationships and the physical mechanism, thereby limiting the understanding of the physical mechanism of the landslide and resulting in low reliability of the prediction results. In this study, we establish a new model for landslide displacement prediction that combines double exponential smoothing (DES), variational mode decomposition (VMD), and evolutionary attention-based long short-term memory (EA–LSTM). The prediction process is as follows: (i) VMD is used to extract trend, periodic, and random displacement from cumulative displacement; (ii) DES is utilized for forecasting trend displacement, and periodic and random displacements are predicted by EA–LSTM; and (iii) these individual predictions are combined to produce the total displacement prediction. The proposed model is validated using monitoring data collected from the Baishuihe and Bazimen landslides in the Three Gorges Reservoir area. The results indicate that, compared with other models, the proposed model demonstrates higher predictive accuracy. In addition, the real-time dynamic weights of historical information revealed by the model on different time stamps are consistent with the actual historical evolution of landslides. These results verify that the proposed model is a promising tool for the high-quality prediction of landslides and can inform landslide treatment-related decision-making. [ABSTRACT FROM AUTHOR]

Objectives: Temporomandibular disorders (TMDs) have a relatively high prevalence among university students. This study aimed to identify independent risk factors for TMD in university students and develop an effective risk prediction model. Methods: This study included 1,122 university students from four universities in Changchun City, Jilin Province, as subjects. Predictive factors were screened by using the least absolute shrinkage and selection operator (LASSO) regression and the machine learning Boruta algorithm in the training cohort. A multifactorial logistic regression analysis was used to construct a TMD risk prediction model. Internal validation of the model was conducted via bootstrap resampling, and an external validation cohort comprised 205 university students undergoing oral examinations at the Stomatological Hospital of Jilin University. Results: The prevalence of TMD among university students was 44.30%. Ten predictive factors were included in the model, comprising gender, facial cold stimulation, unilateral chewing, biting hard or resilient foods, clenching teeth, grinding teeth, excessive mouth opening, malocclusion, stress, and anxiety. The model demonstrated good predictive ability with area under the receiver operating characteristic curve (AUC) values of 0.853, 0.838, and 0.821 in the training cohort, internal validation cohort, and external validation cohort, respectively. The calibration curves demonstrated that the predicted results were consistent with the actual results, and the decision curve analysis (DCA) indicated the model's high clinical utility. Conclusions: An online nomogram of TMD in university students with good predictive performance was constructed, which can effectively predict the risk of TMD in university students. The model provides a useful tool for the early identification and treatment of TMDs in university students, helping clinicians to predict the probability of TMDs in each patient, thus providing more personalized and accurate treatment decisions for patients. [ABSTRACT FROM AUTHOR]

Under the challenges posed by the randomness in ocean systems and the lack of labeled observation datasets, a novel DTW-TRSAX method is presented for detecting anomalies of ocean observing time-series (OOTS), which combines dynamic time warping (DTW) algorithm and trend-based symbolic aggregate approximation (TRSAX) distance. The detecting threshold was constructed according to the tracking distance of sliding window. The trend feature was used to improve SAX to capture the temporal characteristics of different OOTS. The datasets from the National Ocean Test Site of China and the National Marine Data Center were selected for verifying the method. The result shows that 98.5% of confidence level is adequate to provide a reasonable trade-off between the false negative and false positive. Compared with four supervised and unsupervised machine learning algorithms, the DTW-TRSAX method performs more efficient. The approach introduced here is reliable and has the potential to run automatically. [ABSTRACT FROM AUTHOR]

To provide a more comprehensive reconstruction of China's energy consumption, this paper built a machine-learning-based geospatial model that shows great accuracy in recovering historical biomass consumption data using the household survey dataset for China, combined with province-level characteristics and spatiotemporal information. Our study suggested that 6.9 ± 2.6 giga-tons of coal equivalent of biomass were uncounted in China's statistics, representing 15.9 ± 6.0 percent for China and 2.5 ± 0.9 percent for global final energy consumption. This new estimate significantly reshaped our understanding of China's energy composition, sectoral mix, indoor air pollutants, and the factors driving energy consumption. These findings provide a replicable template for developing countries hoping to uncover the biomass demand to better design public policy to achieve Sustainable Development Goals. JEL Classification: Q41, Q53, R12, C81, O13 [ABSTRACT FROM AUTHOR]

Aim: Reversible cognitive frailty (RCF) is an ideal target to prevent asymptomatic cognitive impairment and dependency. This study aimed to develop and validate prediction models for incident RCF. Methods: A total of 1230 older adults aged ≥60 years from China Health and Retirement Longitudinal Study 2011–2013 survey were included as the training set. The modified Poisson regression and three machine learning algorithms including eXtreme Gradient Boosting, support vector machine and random forest were used to develop prediction models. All models were evaluated internally with fivefold cross‐validation, and evaluated externally using a temporal validation method through the China Health and Retirement Longitudinal Study 2013–2015 survey. Results: The incidence of RCF was 27.4% in the training set and 27.5% in the external validation set. A total of 13 important predictors were selected to develop the model, including age, education, contact with their children, medical insurance, vision impairment, heart diseases, medication types, self‐rated health, pain locations, loneliness, self‐medication, night‐time sleep and having running water. All models showed acceptable or approximately acceptable discrimination (AUC 0.683–0.809) for the training set, but fair discrimination (AUC 0.568–0.666) for the internal and external validation. For calibration, only modified Poisson regression and eXtreme Gradient Boosting were acceptable in the training set. All models had acceptable overall prediction performance and clinical usefulness. Older adults were divided into three groups by the risk scoring tool constructed based on modified Poisson regression: low risk (≤24), median risk (24–29) and high risk (>29). Conclusions: This risk tool could assist healthcare providers to predict incident RCF among older adults in the next 2 years, facilitating early identification of a high‐risk population of RCF. Geriatr Gerontol Int 2024; 24: 874–882. [ABSTRACT FROM AUTHOR]

This paper applies causal machine learning methods to analyze the heterogeneous regional impacts of monetary policy in China. The methods uncover the heterogeneous monetary policy impacts on the provincial figures for real GDP growth, CPI inflation, and loan growth compared to the national averages. The varying effects of expansionary and contractionary monetary policy phases on Chinese provinces are highlighted and explained. Subsequently, applying interpretable machine learning, the empirical results show that the credit channel is the main channel affecting the regional impacts of monetary policy. An imminent conclusion of the uneven provincial responses to the "one-size-fits-all" monetary policy is that different policymakers should coordinate their efforts to search for the optimal fiscal and monetary policy mix. [ABSTRACT FROM AUTHOR]

Mining activities have resulted in a substantial accumulation of cadmium (Cd) in agricultural soils, particularly in southern China. Long-term Cd exposure can cause plant growth inhibition and various diseases. Rapid identification of the extent of soil Cd pollution and its driving factors are essential for soil management and risk assessment. However, traditional geostatistical methods are difficult to simulate the complex nonlinear relationships between soil Cd and potential features. In this study, sequential extraction and hotspot analyses indicated that Cd accumulation increased significantly near mining sites and exhibited high mobility. The concentration of Cd was estimated using three machine learning models based on 3169 topsoil samples, seven quantitative variables (soil pH, Fe, Ca, Mn, TOC, Al/Si and ba value) and three quantitative variables (soil parent rock, terrain and soil type). The random forest model achieved marginally better performance than the other models, with an R2 of 0.78. Importance analysis revealed that soil pH and Ca and Mn contents were the most significant factors affecting Cd accumulation and migration. Conversely, due to the essence of controlling Cd migration being soil property, soil type, terrain, and soil parent materials had little impact on the spatial distribution of soil Cd under the influence of mining activities. Our results provide a better understanding of the geochemical behavior of soil Cd in mining areas, which could be helpful for environmental management departments in controlling the diffusion of Cd pollution and capturing key targets for soil remediation. [ABSTRACT FROM AUTHOR]

Background: Natural medicines present a considerable analytical challenge due to their diverse botanical origins and complex multi‐species composition. This inherent complexity complicates their rapid identification and analysis. Tangerine peel, a product of the Citrus species from the Rutaceae family, is widely used both as a culinary ingredient and in traditional Chinese medicine. It is classified into two primary types in China: Citri Reticulatae Pericarpium (CP) and Citri Reticulatae Pericarpium Viride (QP), differentiated by harvest time. A notable price disparity exists between CP and another variety, Citri reticulatae "Chachi" (GCP), with differences being based on the original variety. Methods: This study introduces an innovative method using portable miniature mass spectrometry for swift on‐site analysis of QP, CP, and GCP, requiring less than a minute per sample. And combined with machine learning to differentiate the three types on site, the method was used to try to distinguish GCP from different storage years. Results: This novel method using portable miniature mass spectrometry for swift on‐site analysis of tangerine peels enabled the characterization of 22 compounds in less than one minute per sample. The method simplifies sample processing and integrates machine learning to distinguish between the CP, QP, and GCP varieties. Moreover, a multiple‐perceptron neural network model is further employed to specifically differentiate between CP and GCP, addressing the significant price gap between them. Conclusions: The entire analytical time of the method is about 1 minute, and samples can be analyzed on site, greatly reducing the cost of testing. Besides, this approach is versatile, operates independently of location and environmental conditions, and offers a valuable tool for assessing the quality of natural medicines. [ABSTRACT FROM AUTHOR]

Fetal macrosomia is associated with maternal and newborn complications due to incorrect fetal weight estimation or inappropriate choice of delivery models. The early screening and evaluation of macrosomia in the third trimester can improve delivery outcomes and reduce complications. However, traditional clinical and ultrasound examinations face difficulties in obtaining accurate fetal measurements during the third trimester of pregnancy. This study aims to develop a comprehensive predictive model for detecting macrosomia using machine learning (ML) algorithms. The accuracy of macrosomia prediction using logistic regression, k-nearest neighbors, support vector machine, random forest (RF), XGBoost, and LightGBM algorithms was explored. Each approach was trained and validated using data from 3244 pregnant women at a hospital in southern China. The information gain method was employed to identify deterministic features associated with the occurrence of macrosomia. The performance of six ML algorithms based on the recall and area under the curve evaluation metrics were compared. To develop an efficient prediction model, two sets of experiments based on ultrasound examination records within 1-7 days and 8-14 days prior to delivery were conducted. The ensemble model, comprising the RF, XGBoost, and LightGBM algorithms, showed encouraging results. For each experimental group, the proposed ensemble model outperformed other ML approaches and the traditional Hadlock formula. The experimental results indicate that, with the most risk-relevant features, the ML algorithms presented in this study can predict macrosomia and assist obstetricians in selecting more appropriate delivery models. [ABSTRACT FROM AUTHOR]

Machine learning methods have improved in recent years and provide increasingly powerful tools for understanding landscape evolution. In this study, we used the random forest method based on Google Earth Engine to evaluate the desertification dynamics in northern China from 1995 to 2020. We selected Landsat series image bands, remote sensing inversion data, climate baseline data, land use data, and soil type data as variables for majority voting in the random forest method. The method's average classification accuracy was 91.6% ± 5.8 [mean ± SD], and the average kappa coefficient was 0.68 ± 0.09, suggesting good classification results. The random forest classifier results were consistent with the results of visual interpretation for the spatial distribution of different levels of desertification. From 1995 to 2000, the area of aeolian desertification increased at an average rate of 9977 km2 yr−1, and from 2000 to 2005, from 2005 to 2010, from 2010 to 2015, and from 2015 to 2020, the aeolian desertification decreased at an average rate of 2535, 3462, 1487, and 4537 km2 yr−1, respectively. [ABSTRACT FROM AUTHOR]

Rapid urbanization is universally acknowledged to degrade ecosystem services, posing significant threats to human well-being. However, the effects of urban shrinkage, a global phenomenon and a counterpart to urbanization, on ecosystem services (ESs) remain unclear. This study focuses on China's Rust Belt during the period from 2000 to 2020, constructing a comprehensive analytical framework based on long-term remote sensing data to reveal the temporal and spatial patterns of ESs and their associations with cities experiencing varying degrees of shrinkage. It employs a random forest (RF) model and a Shapley additive explanation (SHAP) model to measure and visualize the significance and thresholds of socioeconomic factors influencing changes in ESs. Our findings highlight the following: (1) Since 2010, the three provinces of Northeast China (TPNC) have begun to shrink comprehensively, with the degree of shrinkage intensifying over time. Resource-based cities have all experienced contraction. (2) Regional urban shrinkage has been found to enhance the overall provision capacity of ESs, with the most significant improvements in cities undergoing continuous shrinkage. (3) The impact of the same socioeconomic drivers varies across cities with different levels of shrinkage; increasing green-space ratios and investing more in public welfare have been identified as effective measures to enhance ESs. (4) Threshold analysis indicates that the stability of the tertiary sector's proportion is critically important for enhancing ESs in cities undergoing intermittent shrinkage. An increase of 10% to 15% in this sector can allow continuously shrinking cities to balance urban development with ecological improvements. This research highlights the positive aspects of urban shrinkage, demonstrating its ability to enhance the provision capacity of ESs. It offers new insights into the protection and management of regional ecosystems and the urban transformation of the three eastern provinces. [ABSTRACT FROM AUTHOR]

Detecting potential depression and identifying the critical predictors of depression among older adults with chronic diseases are essential for timely intervention and management of depression. Therefore, risk prediction models (RPMs) of depression in elderly people should be further explored. A total of 3959 respondents aged 60 years or over from the wave four survey of the China Health and Retired Longitudinal Study (CHARLS) were included in this study. We used five machine learning (ML) algorithms and three data balancing techniques to construct RPMs of depression and calculated feature importance scores to determine which features are essential to depression. The prevalence of depression was 19.2 % among older Chinese adults with chronic diseases in the wave four survey. The random forest (RF) model was more accurate than the other models after balancing the data using the Synthetic Minority Oversampling Technique (SMOTE) algorithm, with an area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) of 0.957 and 0.920, respectively, a balanced accuracy of 0.891 and a sensitivity of 0.875. Furthermore, we further identified several important predictors between male and female patients via constructed sex-stratified models. Further research on the clinical impact studies of our models and external validation are needed. After several techniques were used to address class imbalance issues, most RPMs achieved satisfactory accuracy in predicting depression among elderly people with chronic diseases. RPMs may thus become valuable screening tools for both older individuals and healthcare practitioners to assess the risk of depression. • This study aimed to develop models to predict depression and explore the risk factors for depression among different research objects using machine learning methods. • The best-performing models in different populations generated approximately the same set of features (life satisfaction, self-reported health status, sleep duration, vision, etc.). • The prevalence of depression was 19.2 % among older adults with chronic diseases in China. Besides, the depression incidence rate in women was twice as high as that in men (68.4 % vs. 31.6 %). [ABSTRACT FROM AUTHOR]

Purpose: To identify the key risk factors for venous thromboembolism (VTE) in urological inpatients based on the Caprini scale using an interpretable machine learning method. Methods: VTE risk data of urological inpatients were obtained based on the Caprini scale in the case hospital. Based on the data, the Boruta method was used to further select the key variables from the 37 variables in the Caprini scale. Furthermore, decision rules corresponding to each risk level were generated using the rough set (RS) method. Finally, random forest (RF), support vector machine (SVM), and backpropagation artificial neural network (BPANN) were used to verify the data accuracy and were compared with the RS method. Results: Following the screening, the key risk factors for VTE in urology were "(C1) Age," "(C2) Minor Surgery planned," "(C3) Obesity (BMI > 25)," "(C8) Varicose veins," "(C9) Sepsis (< 1 month)," (C10) "Serious lung disease incl. pneumonia (< 1month) " (C11) COPD," "(C16) Other risk," "(C18) Major surgery (> 45 min)," "(C19) Laparoscopic surgery (> 45 min)," "(C20) Patient confined to bed (> 72 h)," "(C18) Malignancy (present or previous)," "(C23) Central venous access," "(C31) History of DVT/PE," "(C32) Other congenital or acquired thrombophilia," and "(C34) Stroke (< 1 month." According to the decision rules of different risk levels obtained using the RS method, "(C1) Age," "(C18) Major surgery (> 45 minutes)," and "(C21) Malignancy (present or previous)" were the main factors influencing mid- and high-risk levels, and some suggestions on VTE prevention were indicated based on these three factors. The average accuracies of the RS, RF, SVM, and BPANN models were 79.5%, 87.9%, 92.6%, and 97.2%, respectively. In addition, BPANN had the highest accuracy, recall, F1-score, and precision. Conclusions: The RS model achieved poorer accuracy than the other three common machine learning models. However, the RS model provides strong interpretability and allows for the identification of high-risk factors and decision rules influencing high-risk assessments of VTE in urology. This transparency is very important for clinicians in the risk assessment process. [ABSTRACT FROM AUTHOR]

Understanding charging vehicles, charging stations, and built environment concerning idle connection times significantly guided the management of charging infrastructure. However, the interplay between these factors had remained incompletely understood. This study addressed this gap by investigating public charging stations in Changshu, Suzhou, China, as a case study. The random forest regression and partial dependence plots were employed to explore the nonlinear relationships between idle connection times of vehicles at public fast-charging stations and the built environment, charging stations, and charging vehicles. The exploration encompassed two typical scenarios: workdays and weekends. The findings reveal the distinct influences of various factors in different scenarios. Notably, catering service points of interests in the proximity of charging stations, significantly impact the idle connection time on both workdays and weekends. Furthermore, government groups and residential areas have a notable influence on idle connection times during workdays. Shopping service and Leisure sport have a significant impact on idle connection time during the weekends. Variables such as the charging start time and charged energy also exhibit significant effects. Importantly, these influencing factors demonstrate heterogeneity and exhibit different threshold effects. This research can offer valuable insights to planning authorities and charging facility operators for formulating strategies to enhance charging infrastructure utilization. [ABSTRACT FROM AUTHOR]