Meteorological and social conditions contribute to infectious diarrhea in China

AbstractInfectious diarrhea in China showed a significant pattern. Many researchers have tried to reveal the drivers, yet usually only meteorological factors were taken into consideration. Furthermore, the diarrheal data they analyzed were incomplete and the algorithms they exploited were inefficient of adapting realistic relationships. Here, we investigate the impacts of meteorological and social factors on the number of infectious diarrhea cases in China. A machine learning algorithm called the Random Forest is utilized. Our results demonstrate that nearly half of infectious diarrhea occurred among children under 5 years old. Generally speaking, increasing temperature or relative humidity leads to increased cases of infectious diarrhea in China. Nevertheless, people from different age groups or different regions own different sensitivities to meteorological factors. The weight of feces that are harmfully treated could be a possible reason for infectious diarrhea of the elderly as well as children under 5 years old. These findings indicate that infectious diarrhea prevention for children under 5 years old remains a primary task in China. Personalized prevention countermeasures ought to be provided to different age groups and different regions. It is essential to bring the weight of feces that are harmfully treated to the forefront when considering infectious diarrhea prevention.

Download Full-text

Abstract 17133: The Use of Novel Hematological Markers in Predicting Stroke After TAVR Using a Machine Learning Algorithm

Circulation ◽

10.1161/circ.142.suppl_3.17133 ◽

2020 ◽

Vol 142 (Suppl_3) ◽

Author(s):

Aliaskar Z Hasani ◽

Kusha Rahgozar ◽

Aaron Wengrofsky ◽

Narasimha Kuchimanchi ◽

Mohammad Hashim Mustehsan ◽

...

Keyword(s):

Machine Learning ◽

Learning Algorithm ◽

Medical Center ◽

Hematological Parameters ◽

Significant Risk ◽

The Elderly ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Machine Learning Algorithm ◽

Tree Algorithms

Introduction: Aortic Stenosis is the most common valvular disorder with a predominance in the elderly. Trans-Aortic Valve Replacement (TAVR) has been an effective procedure with marked improvement in quality of life for patients. The procedure carries a small, yet clinically significant risk of stroke. The use of Neutrophil-Lymphocyte Ratios (NLR) and Platelet-Lymphocyte Ratios (PLR) have been growing as novel markers of systemic inflammation. We investigated the ability of a machine learning algorithm (Light GBM) to predict and weigh these ratios along with other clinical parameters for prediction of stroke after TAVR. Objective: To demonstrate the efficacy of the Supervised Machine Learning algorithm, Light GBM, in identifying important variables to predict stroke after TAVR. Methods: We performed a retrospective analysis of 291 patients who underwent TAVR from 2015-2019 at Montefiore Medical Center. Age (80±8), 50.2% Female, BMI (28.7 ±6.3). Clinical data was collected through our Hospital EMR. NLR and PLR averages were obtained using the mean of baseline (prior to surgery), Immediate Post-operative, and Post-operative Day 1 values. A supervised machine learning algorithm, Light GBM, used decision tree algorithms with both level-wise growth and leaf-wise growth. The algorithm was trained on 80% of the data and internally validated on the other 20%. Results: We identified NLR and PLR as the second and third most important feature of importance (Table 1) Clinical and demographic features of importance included BMI, Age, and Sex. Our model when internally validated yield a Sensitivity of 75.0%, Specificity of 91.5%, Accuracy of 91.5%, and F1 of 0.75. The AUC for the model was 0.84. Conclusions: Using Novel hematological parameters in conjunction with machine learning algorithms have highlighted important variables in predicting stroke after TAVR. Extrapolated, average NLR and PLR can be an inexpensive tool in stratifying patients those patients most at risk.

Download Full-text

The Short-term Effects of Temperature on Infectious Diarrhea among Children under 5 Years Old in Jiangsu, China: A Time-series Study (2015–2019)

Current Medical Science ◽

10.1007/s11596-021-2338-x ◽

2021 ◽

Vol 41 (2) ◽

pp. 211-218

Author(s):

Nan-nan Huang ◽

Hao Zheng ◽

Bin Li ◽

Gao-qiang Fei ◽

Zhen Ding ◽

...

Keyword(s):

Meteorological Factors ◽

Reference Value ◽

Cold Weather ◽

Maximum Temperature ◽

Daily Maximum Temperature ◽

Daily Maximum ◽

Infectious Diarrhea ◽

Lag Effects ◽

Lag Effect ◽

Children Under 5

SummaryThe association between meteorological factors and infectious diarrhea has been widely studied in many countries. However, investigation among children under 5 years old in Jiangsu, China remains quite limited. Data including infectious diarrhea cases among children under five years old and daily meteorological indexes in Jiangsu, China from 2015 to 2019 were collected. The lag-effects up to 21 days of daily maximum temperature (Tmax) on infectious diarrhea were explored using a quasi-Poisson regression with a distributed lag non-linear model (DLNM) approach. The cases number of infectious diarrhea was significantly associated with seasonal variation of meteorological factors, and the burden of disease mainly occurred among children aged 0–2 years old. Moreover, when the reference value was set at 16.7°C, Tmax had a significant lag-effect on cases of infectious diarrhea among children under 5 years old in Jiangsu Province, which was increased remarkably in cold weather with the highest risk at 8°C. The results of DLNM analysis implicated that the lag-effect of Tmax varied among the 13 cities in Jiangsu and had significant differences in 8 cities. The highest risk of Tmax was presented at 5 lag days in Huaian with a maximum RR of 1.18 (95% CI: 1.09, 1.29). Suzhou which had the highest number of diarrhea cases (15830 cases), had a maximum RR of 1.04 (95% CI:1.03, 1.05) on lag 15 days. Tmax is a considerable indicator to predict the epidemic of infectious diarrhea among 13 cities in Jiangsu, which reminds us that in cold seasons, more preventive strategies and measures should be done to prevent infectious diarrhea.

Download Full-text

The Effects of Significant International Sports Events on Hungarian Suicide Rates

Crisis ◽

10.1027/0227-5910/a000352 ◽

2016 ◽

Vol 37 (2) ◽

pp. 148-154 ◽

Cited By ~ 2

Author(s):

Karoly Bozsonyi ◽

Peter Osvath ◽

Sandor Fekete ◽

Lajos Bálint

Keyword(s):

Significant Relationship ◽

Olympic Games ◽

Arima Model ◽

Age Groups ◽

The Elderly ◽

Intervention Analysis ◽

Middle Aged ◽

Sports Events ◽

Sport Events ◽

The Olympic Games

Abstract. Background: Several studies found a significant relationship between important sport events and suicidal behavior. Aims: We set out to investigate whether there is a significant relationship between the raw suicide rate and the most important international sports events (Olympic Games, FIFA World Cup, UEFA European Championship) in such an achievement-oriented society as the Hungarian one, where these sport events receive great attention. Method: We examined suicide cases occurring over 15,706 days between January 1, 1970, and December 31, 2012 (43 years), separately for each gender. Because of the age-specific characteristics of suicide, the effects of these sport events were analyzed for the middle-aged (30–59 years old) and the elderly (over 60 years old) generations as well as for gender-specific population groups. The role of international sport events was examined with the help of time-series intervention analysis after cyclical and seasonal components were removed. Intervention analysis was based on the ARIMA model. Results: Our results showed that only the Olympic Games had a significant effect in the middle-aged population. Neither in the older male nor in any of the female age groups was a relationship between suicide and Olympic Games detected. Conclusion: The Olympic Games seem to decrease the rate of suicide among middle-aged men, slightly but significantly.

Download Full-text

Machine Learning Algorithm to Predict Early Complications after Brain Tumor Surgery

10.1055/s-0038-1660728 ◽

2018 ◽

Author(s):

C.H.B. van Niftrik ◽

F. van der Wouden ◽

V. Staartjes ◽

J. Fierstra ◽

M. Stienen ◽

...

Keyword(s):

Machine Learning ◽

Brain Tumor ◽

Learning Algorithm ◽

Machine Learning Algorithm ◽

Tumor Surgery ◽

Early Complications ◽

Brain Tumor Surgery

Download Full-text

Older workers in the Russian labor market: Trends in employment reallocation

Voprosy Ekonomiki ◽

10.32609/0042-8736-2019-11-5-34 ◽

2019 ◽

pp. 5-34

Author(s):

Anna L. Lukyanova ◽

Rostislav I. Kapeliushnikov

Keyword(s):

Older Workers ◽

Service Sector ◽

Age Groups ◽

The Elderly ◽

Education And Health ◽

Job Opportunities ◽

Intellectual Labor ◽

Market Trends ◽

Trade Education ◽

The One

The paper analyzes changes in job opportunities of older workers in Russia in the period 2005—2017. The study uses the data from the Russian Labor Force Survey conducted by Rosstat. Changes in the occupational and industrial composition of elderly workers follow the trends pursued by other age groups: employment shifts from low- to high-skilled occupations, from physical to intellectual labor, and from material production to the service sector. We find a stronger polarization among older workers as their occupational structure is biased in favor of, on the one hand, the most and, on the other hand, the least qualified types of jobs. Employment of the elderly has fallen sharply in agriculture and manufacturing with a significant increase in trade, education, and health. Although the employment structure of older workers is generally more “traditionalist”, recent decades have witnessed its transformation in “progressive” directions, similarly to other age groups. These findings suggest that the legislated increase in the state retirement age is not likely to give rise to sizeable unemployment among the elderly. Most of them will be able to work in the occupations and industries previously dominated by young and prime-age workers.

Download Full-text

Feature extraction and prediction of Dengue Outbreaks

International Journal of Scientific Research in Computer Science Engineering and Information Technology ◽

10.32628/cseit206544 ◽

2020 ◽

pp. 216-222

Author(s):

Kunal Parikh ◽

Tanvi Makadia ◽

Harshil Patel

Keyword(s):

Public Health ◽

Machine Learning ◽

Developing Countries ◽

Feature Extraction ◽

Predictive Analytics ◽

Learning Algorithm ◽

Machine Learning Algorithm ◽

Health Concerns ◽

The World ◽

Dengue Outbreaks

Dengue is unquestionably one of the biggest health concerns in India and for many other developing countries. Unfortunately, many people have lost their lives because of it. Every year, approximately 390 million dengue infections occur around the world among which 500,000 people are seriously infected and 25,000 people have died annually. Many factors could cause dengue such as temperature, humidity, precipitation, inadequate public health, and many others. In this paper, we are proposing a method to perform predictive analytics on dengue’s dataset using KNN: a machine-learning algorithm. This analysis would help in the prediction of future cases and we could save the lives of many.

Download Full-text