Analysis on the Impacting Factors of Hand, Foot and Mouth Disease Incidence Using Random Forest

Abstract The burden of disease caused by ambient high temperature has become a public health concern, but the association between high temperature and hand, foot and mouth disease (HFMD) remain indistinct. We used Distributed Lag Non-linear Model (DLNM) to estimate the burden of disease attribute to high temperature, adjusting for long-term trend and weather confounders. Total 18167455 cases were reported in 31 Chinese provinces, the incidence of HFMD showed a gradually increasing trend from 2008 to 2017 in China. Minimum Mortality Temperature (MMT) was mainly concentrated at 17°C to 23°C in the age group less than 5 years old, 18°C to 25°C in the age group 6~10 years old and 19°C to 27°C in the age group above 10 years old. The greatest RR in age group 0~5 years old was 2.06 (95%CI: 1.85~2.30) in Heilongjiang, and the lowest RR was 1.02 (95%CI: 1.00~1.05) in Guangdong; the greatest RR in age group 6~10 years old was 2.24 (95%CI: 1.72~2.91) in Guizhou, and the lowest RR was 1.01 (95%CI: 0.97~1.12) in Tianjin; the greatest RR in the age group over 10 years old was 2.53 (95%CI: 1.66~3.87) in Heilongjiang, and the lowest RR 1.02 (95%CI: 0.71~1.46) in Henan. We found the positive association between high temperature and HFMD in China.

Download Full-text

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

PLoS ONE ◽

10.1371/journal.pone.0261629 ◽

2021 ◽

Vol 16 (12) ◽

pp. e0261629

Author(s):

Delin Meng ◽

Jun Xu ◽

Jijun Zhao

Keyword(s):

Machine Learning ◽

Random Forest ◽

Social Factors ◽

Prediction Models ◽

Mainland China ◽

Foot And Mouth Disease ◽

Influential Factors ◽

Mouth Disease ◽

Extreme Gradient Boosting ◽

Foot And Mouth

Hand, foot and mouth disease (HFMD) is an increasingly serious public health problem, and it has caused an outbreak in China every year since 2008. Predicting the incidence of HFMD and analyzing its influential factors are of great significance to its prevention. Now, machine learning has shown advantages in infectious disease models, but there are few studies on HFMD incidence based on machine learning that cover all the provinces in mainland China. In this study, we proposed two different machine learning algorithms, Random Forest and eXtreme Gradient Boosting (XGBoost), to perform our analysis and prediction. We first used Random Forest to examine the association between HFMD incidence and potential influential factors for 31 provinces in mainland China. Next, we established Random Forest and XGBoost prediction models using meteorological and social factors as the predictors. Finally, we applied our prediction models in four different regions of mainland China and evaluated the performance of them. Our results show that: 1) Meteorological factors and social factors jointly affect the incidence of HFMD in mainland China. Average temperature and population density are the two most significant influential factors; 2) Population flux has different delayed effect in affecting HFMD incidence in different regions. From a national perspective, the model using population flux data delayed for one month has better prediction performance; 3) The prediction capability of XGBoost model was better than that of Random Forest model from the overall perspective. XGBoost model is more suitable for predicting the incidence of HFMD in mainland China.

Download Full-text

Biophysical Measurement of Molecular Weight of Foot-and-Mouth Disease RNA Fragments

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100051323 ◽

1974 ◽

Vol 32 ◽

pp. 262-263

Author(s):

Sydney S. Breese ◽

Howard L. Bachrach

Keyword(s):

Chemical Properties ◽

Foot And Mouth Disease ◽

Mouth Disease ◽

Distilled Water ◽

Bovine Plasma ◽

Mouth Disease Virus ◽

Foot And Mouth ◽

Carbon Coated ◽

Rna Fragments ◽

Physical And Chemical

Continuing studies on the physical and chemical properties of foot-and-mouth disease virus (FMDV) have included electron microscopy of RNA strands released when highly purified virus (1) was dialyzed against demlneralized distilled water. The RNA strands were dried on formvar-carbon coated electron microscope screens pretreated with 0.1% bovine plasma albumin in distilled water. At this low salt concentration the RNA strands were extended and were stained with 1% phosphotungstic acid. Random dispersions of strands were recorded on electron micrographs, enlarged to 30,000 or 40,000 X and the lengths measured with a map-measuring wheel. Figure 1 is a typical micrograph and Fig. 2 shows the distributions of strand lengths for the three major types of FMDV (A119 of 6/9/72; C3-Rezende of 1/5/73; and O1-Brugge of 8/24/73.

Download Full-text

High resolution surface structure of foot-and-mouth disease virus

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100082741 ◽

1978 ◽

Vol 36 (2) ◽

pp. 376-377

Author(s):

S. S. Breese ◽

H. L. Bachrach

Keyword(s):

Electron Microscopy ◽

High Resolution ◽

Surface Structure ◽

Disease Virus ◽

Potassium Phosphate ◽

Foot And Mouth Disease ◽

Mouth Disease ◽

Physical Measurements ◽

Mouth Disease Virus ◽

Foot And Mouth

Models for the structure of foot-and-mouth disease virus (FMDV) have been proposed from chemical and physical measurements (Brown, et al., 1970; Talbot and Brown, 1972; Strohmaier and Adam, 1976) and from rotational image-enhancement electron microscopy (Breese, et al., 1965). In this report we examine the surface structure of FMDV particles by high resolution electron microscopy and compare it with that of particles in which the outermost capsid protein VP3 (ca. 30, 000 daltons) has been split into smaller segments, two of which VP3a and VP3b have molecular weights of about 15, 000 daltons (Bachrach, et al., 1975).Highly purified and concentrated type A12, strain 119 FMDV (5 mg/ml) was prepared as previously described (Bachrach, et al., 1964) and stored at 4°C in 0. 2 M KC1-0. 5 M potassium phosphate buffer at pH 7. 5. For electron microscopy, 1. 0 ml samples of purified virus and trypsin-treated virus were dialyzed at 4°C against 0. 2 M NH4OAC at pH 7. 3, deposited onto carbonized formvar-coated copper screens and stained with phosphotungstic acid, pH 7. 3.

Download Full-text