Analysis and prediction of hand, foot and mouth disease incidence in China using Random Forest and XGBoost

Prediction of gestational diabetes mellitus at the first trimester: machine-learning algorithms

PURPOSE

Short- and long-term complications of gestational diabetes mellitus (GDM) involving pregnancies and offspring warrant the development of an effective individualized risk prediction model to reduce and prevent GDM together with its associated co-morbidities. The aim is to use machine learning (ML) algorithms to study data gathered throughout the first trimester in order to predict GDM.

METHODS

Two independent cohorts with forty-five features gathered through first trimester were included. We constructed prediction models based on three different algorithms and traditional logistic regression, and deployed additional two ensemble algorithms to identify the importance of individual features.

RESULTS

4799 and 2795 pregnancies were included in the Xinhua Hospital Chongming branch (XHCM) and the Shanghai Pudong New Area People's Hospital (SPNPH) cohorts, respectively. Extreme gradient boosting (XGBoost) predicted GDM with moderate performance (the area under the receiver operating curve (AUC) = 0.75) at pregnancy initiation and good-to-excellent performance (AUC = 0.99) at the end of the first trimester in the XHCM cohort. The trained XGBoost showed moderate performance in the SPNPH cohort (AUC = 0.83). The top predictive features for GDM diagnosis were pre-pregnancy BMI and maternal abdominal circumference at pregnancy initiation, and FPG and HbA1c at the end of the first trimester.

CONCLUSION

Our work demonstrated that ML models based on the data gathered throughout the first trimester achieved moderate performance in the external validation cohort.

Predictive health monitoring: Leveraging artificial intelligence for early detection of infectious diseases in nursing home residents through discontinuous vital signs analysis

This research addresses the problem of detecting acute respiratory, urinary tract, and other infectious diseases in elderly nursing home residents using machine learning algorithms. The study analyzes data extracted from multiple vital signs and other contextual information for diagnostic purposes. The daily data collection process encounters sampling constraints due to weekends, holidays, shift changes, staff turnover, and equipment breakdowns, resulting in numerous nulls, repeated readings, outliers, and meaningless values. The short time series generated also pose a challenge to analysis, preventing the extraction of seasonal information or consistent trends. Blind data collection results in most of the data coming from periods when residents are healthy, resulting in excessively imbalanced data. This study proposes a data cleaning process and then builds a mechanism that reproduces the basal activity of the residents to improve the classification of the disease. The results show that the proposed basal module-assisted machine learning techniques allow anticipating diagnostics 2, 3 or 4 days before doctors decide to start treatment with antibiotics, achieving a performance measured by the area-under-the-curve metric of 0.857. The contributions of this work are: (1) a new data cleaning process; (2) the analysis of contextual information to improve data quality; (3) the generation of a baseline measure for relative comparison; and (4) the use of either binary (disease/no disease) or multiclass classification, differentiating among types of infections and showing the advantages of multiclass versus binary classification. From a medical point of view, the anticipated detection of infectious diseases in institutionalized individuals is brand new.

Advanced detection of coronary artery disease via deep learning analysis of plasma cytokine data

The 2017 World Health Organization Fact Sheet highlights that coronary artery disease is the leading cause of death globally, responsible for approximately 30% of all deaths. In this context, machine learning (ML) technology is crucial in identifying coronary artery disease, thereby saving lives. ML algorithms can potentially analyze complex patterns and correlations within medical data, enabling early detection and accurate diagnosis of CAD. By leveraging ML technology, healthcare professionals can make informed decisions and implement timely interventions, ultimately leading to improved outcomes and potentially reducing the mortality rate associated with coronary artery disease. Machine learning algorithms create non-invasive, quick, accurate, and economical diagnoses. As a result, machine learning algorithms can be employed to supplement existing approaches or as a forerunner to them. This study shows how to use the CNN classifier and RNN based on the LSTM classifier in deep learning to attain targeted "risk" CAD categorization utilizing an evolving set of 450 cytokine biomarkers that could be used as suggestive solid predictive variables for treatment. The two used classifiers are based on these "45" different cytokine prediction characteristics. The best Area Under the Receiver Operating Characteristic curve (AUROC) score achieved is (0.98) for a confidence interval (CI) of 95; the classifier RNN-LSTM used "450" cytokine biomarkers had a great (AUROC) score of 0.99 with a confidence interval of 0.95 the percentage 95, the CNN model containing cytokines received the second best AUROC score (0.92). The RNN-LSTM classifier considerably beats the CNN classifier regarding AUROC scores, as evidenced by a p-value smaller than 7.48 obtained via an independent t-test. As large-scale initiatives to achieve early, rapid, reliable, inexpensive, and accessible individual identification of CAD risk gain traction, robust machine learning algorithms can now augment older methods such as angiography. Incorporating 65 new sensitive cytokine biomarkers can increase early detection even more. Investigating the novel involvement of cytokines in CAD could lead to better risk detection, disease mechanism discovery, and new therapy options.

FRP-XGBoost: Identification of ferroptosis-related proteins based on multi-view features

Ferroptosis represents a novel form of programmed cell death. Pan-cancer bioinformatics analysis indicates that identifying and modulating ferroptosis offer innovative approaches for preventing and treating diverse tumor pathologies. However, the precise detection of ferroptosis-related proteins via conventional wet-laboratory techniques remains a formidable challenge, largely due to the constraints of existing methodologies. These traditional approaches are not only labor-intensive but also financially burdensome. Consequently, there is an imperative need for the development of more sophisticated and efficient computational tools to facilitate the detection of these proteins. In this paper, we presented a XGBoost and multi-view features-based machine learning prediction method for predicting ferroptosis-related proteins, which was referred to as FRP-XGBoost. In this study, we explored four types of protein feature extraction methods and evaluated their effectiveness in predicting ferroptosis-related proteins using six of the most commonly used traditional classifiers. To enhance the representational power of the hybrid features, we employed a two-step feature selection technique to identify the optimal subset of features. Subsequently, we constructed a prediction model using the XGBoost algorithm. The FRP-XGBoost achieved an accuracy of 96.74 % in 10-fold cross-validation and a further accuracy of 91.52 % in an independent test. The implementation source code of FRP-XGBoost is available at https://github.com/linli5417/FRP-XGBoost.

Machine learning for layer-by-layer nanofiltration membrane performance prediction and polymer candidate exploration

In this study, machine learning-based models were established for layer-by-layer (LBL) nanofiltration (NF) membrane performance prediction and polymer candidate exploration. Four different models, i.e., linear, random forest (RF), boosted tree (BT), and eXtreme Gradient Boosting (XGBoost), were formed, and membrane performance prediction was determined in terms of membrane permeability and selectivity. The XGBoost exhibited optimal prediction accuracy for membrane permeability (coefficient of determination (R2): 0.99) and membrane selectivity (R2: 0.80). The Shapley Additive exPlanation (SHAP) method was utilized to evaluate the effects of different LBL NF membrane fabrication conditions on membrane performances. The SHAP method was also used to identify the relationships between polymer structure and membrane performance. Polymers were represented by Morgan fingerprint, which is an effective description approach for developing modeling. Based on the SHAP value results, two reference Morgan fingerprints were constructed containing atomic groups with positive contributions to membrane permeability and selectivity. According to the reference Morgan fingerprint, 204 potential polymers were explored from the largest polymer database (PoLyInfo). By calculating the similarities between each potential polymer and both reference Morgan fingerprints, 23 polymer candidates were selected and could be further used for LBL NF membrane fabrication with the potential for providing good membrane performance. Overall, this work provided new ways both for LBL NF membrane performance prediction and high-performance polymer candidate exploration. The source code for the models and algorithms used in this study is publicly available to facilitate replication and further research. https://github.com/wangliwfsd/LLNMPP/.

Cluster energy prediction based on multiple strategy fusion whale optimization algorithm and light gradient boosting machine

BACKGROUND

Clusters, a novel hierarchical material structure that emerges from atoms or molecules, possess unique reactivity and catalytic properties, crucial in catalysis, biomedicine, and optoelectronics. Predicting cluster energy provides insights into electronic structure, magnetism, and stability. However, the structure of clusters and their potential energy surface is exceptionally intricate. Searching for the global optimal structure (the lowest energy) among these isomers poses a significant challenge. Currently, modelling cluster energy predictions with traditional machine learning methods has several issues, including reliance on manual expertise, slow computation, heavy computational resource demands, and less efficient parameter tuning.

RESULTS

This paper introduces a predictive model for the energy of a gold cluster comprising twenty atoms (referred to as Au20 cluster). The model integrates the Multiple Strategy Fusion Whale Optimization Algorithm (MSFWOA) with the Light Gradient Boosting Machine (LightGBM), resulting in the MSFWOA-LightGBM model. This model employs the Coulomb matrix representation and eigenvalue solution methods for feature extraction. Additionally, it incorporates the Tent chaotic mapping, cosine convergence factor, and inertia weight updating strategy to optimize the Whale Optimization Algorithm (WOA), leading to the development of MSFWOA. Subsequently, MSFWOA is employed to optimize the parameters of LightGBM for supporting the energy prediction of Au20 cluster.

CONCLUSIONS

The experimental results show that the most stable Au20 cluster structure is a regular tetrahedron with the lowest energy, displaying tight and uniform atom distribution, high geometric symmetry. Compared to other models, the MSFWOA-LightGBM model excels in accuracy and correlation, with MSE, RMSE, and R2 values of 0.897, 0.947, and 0.879, respectively. Additionally, the MSFWOA-LightGBM model possesses outstanding scalability, offering valuable insights for material design, energy storage, sensing technology, and biomedical imaging, with the potential to drive research and development in these areas.

Evaluation of models for multi-step forecasting of hand, foot and mouth disease using multi-input multi-output: A case study of Chengdu, China

BACKGROUND

Hand, foot and mouth disease (HFMD) is a public health concern that threatens the health of children. Accurately forecasting of HFMD cases multiple days ahead and early detection of peaks in the number of cases followed by timely response are essential for HFMD prevention and control. However, many studies mainly predict future one-day incidence, which reduces the flexibility of prevention and control.

METHODS

We collected the daily number of HFMD cases among children aged 0-14 years in Chengdu from 2011 to 2017, as well as meteorological and air pollutant data for the same period. The LSTM, Seq2Seq, Seq2Seq-Luong and Seq2Seq-Shih models were used to perform multi-step prediction of HFMD through multi-input multi-output. We evaluated the models in terms of overall prediction performance, the time delay and intensity of detection peaks.

RESULTS

From 2011 to 2017, HFMD in Chengdu showed seasonal trends that were consistent with temperature, air pressure, rainfall, relative humidity, and PM10. The Seq2Seq-Shih model achieved the best performance, with RMSE, sMAPE and PCC values of 13.943~22.192, 17.880~27.937, and 0.887~0.705 for the 2-day to 15-day predictions, respectively. Meanwhile, the Seq2Seq-Shih model is able to detect peaks in the next 15 days with a smaller time delay.

CONCLUSIONS

The deep learning Seq2Seq-Shih model achieves the best performance in overall and peak prediction, and is applicable to HFMD multi-step prediction based on environmental factors.

Research on hand, foot and mouth disease incidence forecasting using hybrid model in mainland China

BACKGROUND

This study aimed to construct a more accurate model to forecast the incidence of hand, foot, and mouth disease (HFMD) in mainland China from January 2008 to December 2019 and to provide a reference for the surveillance and early warning of HFMD.

METHODS

We collected data on the incidence of HFMD in mainland China between January 2008 and December 2019. The SARIMA, SARIMA-BPNN, and SARIMA-PSO-BPNN hybrid models were used to predict the incidence of HFMD. The prediction performance was compared using the mean absolute error(MAE), mean squared error(MSE), root mean square error (RMSE), mean absolute percentage error (MAPE), and correlation analysis.

RESULTS

The incidence of HFMD in mainland China from January 2008 to December 2019 showed fluctuating downward trends with clear seasonality and periodicity. The optimal SARIMA model was SARIMA(1,0,1)(2,1,2)_[12], with Akaike information criterion (AIC) and Bayesian Schwarz information criterion (BIC) values of this model were 638.72, 661.02, respectively. The optimal SARIMA-BPNN hybrid model was a 3-layer BPNN neural network with nodes of 1, 10, and 1 in the input, hidden, and output layers, and the R-squared, MAE, and RMSE values were 0.78, 3.30, and 4.15, respectively. For the optimal SARIMA-PSO-BPNN hybrid model, the number of particles is 10, the acceleration coefficients c1 and c2 are both 1, the inertia weight is 1, the probability of change is 0.95, and the values of R-squared, MAE, and RMSE are 0.86, 2.89, and 3.57, respectively.

CONCLUSIONS

Compared with the SARIMA and SARIMA-BPNN hybrid models, the SARIMA-PSO-BPNN model can effectively forecast the change in observed HFMD incidence, which can serve as a reference for the prevention and control of HFMD.

Analysis of the epidemiological trends of enterovirus A in Asia and Europe

BACKGROUND

Enteroviruses have been in massive, cyclical epidemics worldwide. An in-depth understanding of the international epidemiological characteristics of Enterovirus A (EVA) is critical to determining its clinical significance and total disease burden. Although much research has been conducted on EVA epidemiology, there is still a lack of a comprehensive overview of EVA epidemiological characteristics and trends.

OBJECTIVE

EVA nucleic acid sequences from the NCBI virus database were used to summarize the epidemic time (based on the time of specimen collection), spatial and serotype distribution of EVA, and to analyze EVA isolated from cerebrospinal fluid specimens.

METHODS

EVA sequences were searched in NCBI Virus by keyword ("Enterovirus A″ or "EVA") to screen sequences released before December 2021 and sort them to analyze EVA by year, geographic region and serotype prevalence.

RESULTS

The results found 23,041 retrieved nucleic acid sequences with precise collection dates and geographical regions as of December 2021, with Asia accounting for 87%, Europe for 11% and Africa and the Americas for only 2%. Overall, EV-A71, CVA6 and CVA16 are a few of the main prevalent serotypes; and the prevalence characteristics of the different serotypes change over time from place to place.

CONCLUSION

The prevalence of different serotypes of EVA varies considerably over time and space, and we focused on analysing the epidemiological characteristics of EVAs in Asia and Europe and EVAs that invade the nervous system. This study will likely provide important clues for prevention, control and future research in virological surveillance, disease management and vaccine development.

Machine Learning Prediction Model of Tuberculosis Incidence Based on Meteorological Factors and Air Pollutants

BACKGROUND

Tuberculosis (TB) is a public health problem worldwide, and the influence of meteorological and air pollutants on the incidence of tuberculosis have been attracting interest from researchers. It is of great importance to use machine learning to build a prediction model of tuberculosis incidence influenced by meteorological and air pollutants for timely and applicable measures of both prevention and control.

METHODS

The data of daily TB notifications, meteorological factors and air pollutants in Changde City, Hunan Province ranging from 2010 to 2021 were collected. Spearman rank correlation analysis was conducted to analyze the correlation between the daily TB notifications and the meteorological factors or air pollutants. Based on the correlation analysis results, machine learning methods, including support vector regression, random forest regression and a BP neural network model, were utilized to construct the incidence prediction model of tuberculosis. RMSE, MAE and MAPE were performed to evaluate the constructed model for selecting the best prediction model.

RESULTS

(1) From the year 2010 to 2021, the overall incidence of tuberculosis in Changde City showed a downward trend. (2) The daily TB notifications was positively correlated with average temperature (r = 0.231), maximum temperature (r = 0.194), minimum temperature (r = 0.165), sunshine duration (r = 0.329), PM_2.5 (r = 0.097), PM₁₀ (r = 0.215) and O₃ (r = 0.084) (p < 0.05). However, there was a significant negative correlation between the daily TB notifications and mean air pressure (r = -0.119), precipitation (r = -0.063), relative humidity (r = -0.084), CO (r = -0.038) and SO₂ (r = -0.034) (p < 0.05). (3) The random forest regression model had the best fitting effect, while the BP neural network model exhibited the best prediction. (4) The validation set of the BP neural network model, including average daily temperature, sunshine hours and PM₁₀, showed the lowest root mean square error, mean absolute error and mean absolute percentage error, followed by support vector regression.

CONCLUSIONS

The prediction trend of the BP neural network model, including average daily temperature, sunshine hours and PM₁₀, successfully mimics the actual incidence, and the peak incidence highly coincides with the actual aggregation time, with a high accuracy and a minimum error. Taken together, these data suggest that the BP neural network model can predict the incidence trend of tuberculosis in Changde City.

Nonlinear Effects of the Neighborhood Environments on Residents' Mental Health

In the context of rapid urbanization and the "Healthy China" strategy, neighborhood environments play an important role in improving mental health among urban residents. While an increasing number of studies have explored the linear relationships between neighborhood environments and mental health, much remains to be revealed about the nonlinear health effects of neighborhood environments, the thresholds of various environmental factors, and the optimal environmental exposure levels for residents. To fill these gaps, this paper collected survey data from 1003 adult residents in Guangzhou, China, and measured the built and social environments within the neighborhoods. The random forest model was then employed to examine the nonlinear effects of neighborhood environments on mental health, evaluate the importance of each environmental variable, as well as identify the thresholds and optimal levels of various environmental factors. The results indicated that there are differences in the importance of diverse neighborhood environmental factors affecting mental health, and the more critical environmental factors included greenness, neighborhood communication, and fitness facility density. The nonlinear effects were shown to be universal and varied among neighborhood environmental factors, which could be classified into two categories: (i) higher exposure levels of some environmental factors (e.g., greenness, neighborhood communication, and neighborhood safety) were associated with better mental health; (ii) appropriate exposure levels of some environmental factors (e.g., medical, fitness, and entertainment facilities, and public transport stations) had positive effects on mental health, whereas a much higher or lower exposure level exerted a negative impact. Additionally, this study identified the exact thresholds and optimal exposure levels of neighborhood environmental factors, such as the threshold (22.00%) and optimal exposure level (>22.00%) of greenness and the threshold (3.80 number/km²) and optimal exposure level (3.80 number/km²) of fitness facility density.

A Predictive Model for Abnormal Bone Density in Male Underground Coal Mine Workers

The dark and humid environment of underground coal mines had a detrimental effect on workers’ skeletal health. Optimal risk prediction models can protect the skeletal health of coal miners by identifying those at risk of abnormal bone density as early as possible. A total of 3695 male underground workers who attended occupational health physical examination in a coal mine in Hebei, China, from July to August 2018 were included in this study. The predictor variables were identified through single-factor analysis and literature review. Three prediction models, Logistic Regression, CNN and XG Boost, were developed to evaluate the prediction performance. The training set results showed that the sensitivity of Logistic Regression, XG Boost and CNN models was 74.687, 82.058, 70.620, the specificity was 80.986, 89.448, 91.866, the F1 scores was 0.618, 0.919, 0.740, the Brier scores was 0.153, 0.040, 0.156, and the Calibration-in-the-large was 0.104, 0.020, 0.076, respectively, XG Boost outperformed the other two models. Similar results were obtained for the test set and validation set. A two-by-two comparison of the area under the ROC curve (AUC) of the three models showed that the XG Boost model had the best prediction performance. The XG Boost model had a high application value and outperformed the CNN and Logistic regression models in prediction.

Prediction of adolescent suicidal ideation after the COVID-19 pandemic: A nationwide survey of a representative sample of Korea

OBJECTIVE

This study developed a model to predict groups vulnerable to suicidal ideation after the declaration of the COVID-19 pandemic based on nomogram techniques targeting 54,948 adolescents who participated in a national survey in South Korea.

METHODS

This study developed a model to predict suicidal ideation by using logistic regression analysis. The model aimed to understand the relationship between predictors associated with the suicidal ideation of South Korean adolescents by using the top seven variables with the highest feature importance confirmed in XGBoost (extreme gradient boosting). The regression model was developed using a nomogram so that medical workers could easily interpret the probability of suicidal ideation and identify groups vulnerable to suicidal ideation.

RESULTS

This epidemiological study predicted that eighth graders who experienced depression in the past 12 months, had a lot of subjective stress, frequently felt lonely in the last 12 months, experienced much-worsened household economic status during the COVID-19 pandemic, and had poor academic performance were vulnerable to suicidal ideation. The results of 10-fold cross-validation revealed that the area under the curve (AUC) of the adolescent suicidal ideation prediction nomogram was 0.86, general accuracy was 0.89, precision was 0.87, recall was 0.89, and the F1-score was 0.88.

CONCLUSION

It is required to recognize the seriousness of adolescent suicide and mental health after the onset of the COVID-19 pandemic and prepare a customized support system that considers the characteristics of persons at risk of suicide at the school or community level.