Modeling of COVID-19 new cases and deaths in top 10 affected countries

Introduction: This study aimed to develop a model utilizing the data from the top 10 countries (as of August 22, 2020) with the maximum number of infected cases. These countries are the United States of America, Brazil, India, Russia, South Africa, Peru, Mexico, Colombia, Chile, and Spain. The model is developed using the newly infected cases, new deaths, cumulative infected cases, and cumulative deaths due to COVID-19 starting from the day on which the first infected cases of COVID-19 in each of these countries is diagnosed to the date August 19, 2020. Materials and Methods: This study includes data such as the newly infected cases, new deaths, cumulative infected cases, and cumulative deaths due to COVID-19 starting from the day on which the first infected case of COVID-19 in each of these countries is diagnosed to the date August 19, 2020, in the top 10 most affected countries. The data were obtained from World Health Organization (WHO) website. To fit the data into a regression model, IBM SPSS Statistics 21.0 was used. The linear, logarithmic, quadratic, and cubic curves were fitted to the newly infected COVID-19 cases and daily deaths due to COVID-19. In choosing the best-fitted model, the coefficient of determination (R-square) was used. Results: Cubic regression model is the best fit model for new infected COVID-19 cases as well as COVID-19 deaths. It has the highest R-square value as compared to the linear, logarithmic and quadratic. Conclusion: To control the spread of infection, there is a need for aggressive control strategies from the administrative departments of all countries.

Heart Alert: A heart disease prediction system using machine learning approach and optimization techniques

Background@#Cardiovascular diseases belong to the top three leading causes of mortality in the Philippines with 17.8 % of the total deaths. Lifestyle-related habits such as alcohol consumption, smoking, poor diet and nutrition, high sedentary behavior, overweight, and obesity have been increasingly implicated in the high rates of heart disease among Filipinos leading to a significant burden to the country's healthcare system. The objective of this study was to predict the presence of heart disease using various machine learning algorithms (support vector machine, naïve Bayes, random forest, logistic regression, decision tree, and adaptive boosting) evaluated on an anonymized publicly available cardiovascular disease dataset. @*Methodology@#Various machine learning algorithms were applied on an anonymized publicly available cardiovascular dataset from a machine learning data repository (IEEE Dataport). A web-based application system named Heart Alert was developed based on the best machine learning model that would predict the risk of developing heart disease. An assessment of the effects of different optimization techniques as to the imputation methods (mean, median, mode, and multiple imputation by chained equations) and as to the feature selection method (recursive feature elimination) on the classification performance of the machine learning algorithms was made. All simulation experiments were implemented via Python 3.8 and its machine learning libraries (Scikit-learn, Keras, Tensorflow, Pandas, Matplotlib, Seaborn, NumPy). @*Results@#The support vector machine without imputation and feature selection obtained the highest performance metrics (90.2% accuracy, 87.7% sensitivity, 93.6% specificity, 94.9% precision, 91.2% F1-score and an area under the receiver operating characteristic curve of 0.902 ) and was used to implement the heart disease prediction system (Heart Alert). Following very closely were random forest with mean or median imputation and logistic regression with mode imputation, all having no feature selection which also performed well. @*Conclusion@#The performance of the best four machine learning models suggests that for this dataset, imputation technique for missing values may or may not be done. Likewise, recursive feature elimination for feature selection may not apply as all variables seem to be important in heart disease prediction. An early accurate diagnosis leading to prompt intervention efforts is very crucial as it improves the patient's quality of life and diminishes the risk of developing cardiac events.

A Novel Early Warning Model for Hand, Foot and Mouth Disease Prediction Based on a Graph Convolutional Network / 生物医学与环境科学（英文）

Objectives@#Hand, foot and mouth disease (HFMD) is a widespread infectious disease that causes a significant disease burden on society. To achieve early intervention and to prevent outbreaks of disease, we propose a novel warning model that can accurately predict the incidence of HFMD.@*Methods@#We propose a spatial-temporal graph convolutional network (STGCN) that combines spatial factors for surrounding cities with historical incidence over a certain time period to predict the future occurrence of HFMD in Guangdong and Shandong between 2011 and 2019. The 2011-2018 data served as the training and verification set, while data from 2019 served as the prediction set. Six important parameters were selected and verified in this model and the deviation was displayed by the root mean square error and the mean absolute error.@*Results@#As the first application using a STGCN for disease forecasting, we succeeded in accurately predicting the incidence of HFMD over a 12-week period at the prefecture level, especially for cities of significant concern.@*Conclusions@#This model provides a novel approach for infectious disease prediction and may help health administrative departments implement effective control measures up to 3 months in advance, which may significantly reduce the morbidity associated with HFMD in the future.

The changed abundance of intestinal Prevotella_copri and its predictive value in patients with Parkinson′s disease / 医学研究生学报

ObjectiveGut microbiota plays an important role in Parkinson′s disease, but the mechanisms behind this remain unknown. This study aims to investigate the characteristics of intestinal microbiota in patients with Parkinson′s disease, and to study the changes of intestinal Prevotella_copri and their role in this disease.Methods The study was carried out in 46 patients with Parkinson′s disease and their spouses. The spouse has been living with the patient for a long time, not suffering from any disease. Fecal samples from all subjects were collected using sterile containers. The bacterial DNA was extracted on ice following the Kit protocol. We used the BGISEQ-500 high-throughput sequencing platform to conduct metagenomic shotgun sequencing, to explore the changes of patients′ intestinal microbiota through bioinformatics, and to analyze the function and role of differential microorganisms in disease.ResultsCompared to healthy spouse, the gut microbiota of patients with Parkinson′s disease was significantly changed, which was characterized by decreased Prevotellaceae and Prevotella_copri, but by significantly elevated Bacteroides_stercoris and Escherichia_coli. Prevotella_copri was decreased with age increasing. The correlation analysis showed a significantly negative correlation between the abundance of Prevotella_copri and age, H-Ystage, UPDR total score, and UPDRS Ⅲ score. Results of the random forest model indicated five items including Prevotella_copri had good predictive value for the disease. The functional analysis stated pathways associated with super-pathway of thiamin diphosphate biosynthesis, 4-aminobutanoate degradation. The glucose-1-phosphate degradation and methyl phosphonate degradation significantly increased in patients, while pathways associated with aromatic amino acid biosynthesis, chorismate biosynthesis, thiamin formation, and pyrimidine deoxyribonucleosides salvage significantly decreased. Pathways of Prevotella_copri were mainly concentrated in UMP biosynthesis, S-adenosyl-L-methionine cycle, and guanosine ribonucleotides de novo biosynthesis.ConclusionStructural composition and metabolic functions of gut microbiota were significantly changed in patients with Parkinson′s disease. Prevotella_copri plays an important role in the occurrence and progression of the disease and can be used as a potential biomarker for Parkinson′s disease.

Application of infectious disease index to prediction of infectious diseases / 预防医学

Objective@#To establish a prediction model for infectious disease index（IDI）by autoregressive integrated moving average（ARIMA）,and to provide forcast of infectious diseases to the public. @*Methods@#The data of the percentage of influenza-like illness（ILI）,the incidence rates of hand-foot-mouth disease（HFMD）and other infectious diarrhea（OID）from the 1st week of 2014 to the 14th week of 2018,and Breteau index（BI）from the 1st week of 2016 to the 14th week of 2018 were collected. ARIMA models were built to predict the risk indicators of ILI,HFMD,OID and BI. The weights of the four indicators were evaluated seasonally by the entropy weight method. Then the IDI was calculated and the data of ILI,HFMD, OID and BI from 15th to 19th week in 2018 was used for verification. @*Results@#The forecast was in summer,so IDI=ROUND（0.33×risk index of ILI percentage +0.47×risk index of HFMD incidence +0.10×risk index of OID incidence+0.10×risk index of BI）. The predicted IDI would be 2（less safe）in the whole city and Xiangzhou District,and 1（safe）in Doumen District and Jinwan District. The consistency rates of IDI prediction was 97.50%,95.00%,97.50%,85.00% and 77.50% from 15th to 19th week in 2018,respectively.@*Conclusion@#It was feasible to use IDI for short-term risk prediction of infectious diseases.

Progress in research and application of Radiomics / 肿瘤

Radiomics refers to the extraction and analysis of large amounts of advanced quantitative imaging features with high throughput from medical images obtained with CT, MRI and PET, finding disease biomarkers to increase precision in diagnosis, assessment of prognosis and prediction of therapy response. It is well known that cancer treatment is a great challenge; however, early detection and early treatment can greatly increase the survival rate of patients. The change of tumor cells can be monitored by the examination of gene expression. Moreover, it can also be monitored by imaging markers, which makes Radiomics method widely used in cancer treatment, so Radiomics plays a more and more important role in medical imaging and the related fields. This paper firstly summarizes and analyzes the key problems (including multi-modality image acquisition and reconstruction, image segmentation, feature extraction and qualification, and databases, data sharing, informatics analyses and modeling) to be solved in Radiomics. Different challenges are available in each process. Next, the paper describes the application of Radiomics in detection of non-small cell lung cancer, prostate cancer, breast cancer and other cancers. Finally, taking the rapid development of advanced technologies, the paper puts forward several points of future prediction in terms of the development of Radiomics method.

Genetic risk score: principle, methods and application / 中华流行病学杂志

Genetic risk score (GRS) is used for evaluating the effects of genetic susceptible factors in risk prediction models.Five methods are commonly used for GRS:i.e.simple count genetic risk score (SC-GRS),odds ratio weighted genetic risk score (OR-GRS),direct logistic regression genetic risk score (DL-GRS),polygenic genetic risk score (PG-GRS) and explained variance weighted genetic risk score (EV-GRS).This paper summarizes the models,application conditions,advantages and limitations of the five methods.The complexity of prediction models increased along with the inclusion of more susceptible SNPs,some method have been developed to solve the problems,but the effects of new methods needs further evaluation.

Development and Application of Chronic Disease Risk Prediction Models

Currently, non-communicable chronic diseases are a major cause of morbidity and mortality worldwide, and a large proportion of chronic diseases are preventable through risk factor management. However, the prevention efficacy at the individual level is not yet satisfactory. Chronic disease prediction models have been developed to assist physicians and individuals in clinical decision-making. A chronic disease prediction model assesses multiple risk factors together and estimates an absolute disease risk for the individual. Accurate prediction of an individual's future risk for a certain disease enables the comparison of benefits and risks of treatment, the costs of alternative prevention strategies, and selection of the most efficient strategy for the individual. A large number of chronic disease prediction models, especially targeting cardiovascular diseases and cancers, have been suggested, and some of them have been adopted in the clinical practice guidelines and recommendations of many countries. Although few chronic disease prediction tools have been suggested in the Korean population, their clinical utility is not as high as expected. This article reviews methodologies that are commonly used for developing and evaluating a chronic disease prediction model and discusses the current status of chronic disease prediction in Korea.

Development and Application of Chronic Disease Risk Prediction Models

Currently, non-communicable chronic diseases are a major cause of morbidity and mortality worldwide, and a large proportion of chronic diseases are preventable through risk factor management. However, the prevention efficacy at the individual level is not yet satisfactory. Chronic disease prediction models have been developed to assist physicians and individuals in clinical decision-making. A chronic disease prediction model assesses multiple risk factors together and estimates an absolute disease risk for the individual. Accurate prediction of an individual's future risk for a certain disease enables the comparison of benefits and risks of treatment, the costs of alternative prevention strategies, and selection of the most efficient strategy for the individual. A large number of chronic disease prediction models, especially targeting cardiovascular diseases and cancers, have been suggested, and some of them have been adopted in the clinical practice guidelines and recommendations of many countries. Although few chronic disease prediction tools have been suggested in the Korean population, their clinical utility is not as high as expected. This article reviews methodologies that are commonly used for developing and evaluating a chronic disease prediction model and discusses the current status of chronic disease prediction in Korea.