Modeling diarrhea disease in children less than 5 years old

Statistical Analysis and Machine Learning Prediction of Disease Outcomes for COVID-19 and Pneumonia Patients

The Coronavirus Disease 2019 (COVID-19) has spread all over the world and impacted many people’s lives. The characteristics of COVID-19 and other types of pneumonia have both similarities and differences, which confused doctors initially to separate and understand them. Here we presented a retrospective analysis for both COVID-19 and other types of pneumonia by combining the COVID-19 clinical data, eICU and MIMIC-III databases. Machine learning models, including logistic regression, random forest, XGBoost and deep learning neural networks, were developed to predict the severity of COVID-19 infections as well as the mortality of pneumonia patients in intensive care units (ICU). Statistical analysis and feature interpretation, including the analysis of two-level attention mechanisms on both temporal and non-temporal features, were utilized to understand the associations between different clinical variables and disease outcomes. For the COVID-19 data, the XGBoost model obtained the best performance on the test set (AUROC = 1.000 and AUPRC = 0.833). On the MIMIC-III and eICU pneumonia datasets, our deep learning model (Bi-LSTM_Attn) was able to identify clinical variables associated with death of pneumonia patients (AUROC = 0.924 and AUPRC = 0.802 for 24-hour observation window and 12-hour prediction window). The results highlighted clinical indicators, such as the lymphocyte counts, that may help the doctors to predict the disease progression and outcomes for both COVID-19 and other types of pneumonia.

Association between Childhood Diarrhoeal Incidence and Climatic Factors in Urban and Rural Settings in the Health District of Mbour, Senegal

We assessed the association between childhood diarrhoeal incidence and climatic factors in rural and urban settings in the health district of Mbour in western Senegal. We used monthly diarrhoeal case records among children under five years registered in 24 health facilities over a four-year period (2011-2014). Climatic data (i.e., daily temperature, night temperature and rainfall) for the same four-year period were obtained. We performed a negative binomial regression model to establish the relationship between monthly diarrhoeal incidence and climatic factors of the same and the previous month. There were two annual peaks in diarrhoeal incidence: one during the cold dry season and one during the rainy season. We observed a positive association between diarrhoeal incidence and high average temperature of 36 °C and above and high cumulative monthly rainfall at 57 mm and above. The association between diarrhoeal incidence and temperature was stronger in rural compared to urban settings, while higher rainfall was associated with higher diarrhoeal incidence in the urban settings. Concluding, this study identified significant health-climate interactions and calls for effective preventive measures in the health district of Mbour. Particular attention should be paid to urban settings where diarrhoea was most common in order to reduce the high incidence in the context of climatic variability, which is expected to increase in urban areas in the face of global warming.

Exploration of diarrhoea seasonality and its drivers in China

This study investigated the diarrhoea seasonality and its potential drivers as well as potential opportunities for future diarrhoea control and prevention in China. Data on weekly infectious diarrhoea cases in 31 provinces of China from 2005 to 2012, and data on demographic and geographic characteristics, as well as climatic factors, were complied. A cosinor function combined with a Poisson regression was used to calculate the three seasonal parameters of diarrhoea in different provinces. Regression tree analysis was used to identify the predictors of diarrhoea seasonality. Diarrhoea cases in China showed a bimodal distribution. Diarrhoea in children <5 years was more likely to peak in fall-winter seasons, while diarrhoea in persons > = 5 years peaked in summer. Latitude was significantly associated with spatial pattern of diarrhoea seasonality, with peak and trough times occurring earlier at high latitudes (northern areas), and later at low latitudes (southern areas). The annual amplitudes of diarrhoea in persons > = 5 years increased with latitude (r = 0.62, P<0.001). Latitude 27.8° N and 38.65° N were the latitudinal thresholds for diarrhoea seasonality in China. Regional-specific diarrhoea control and prevention strategies may be optimal for China. More attention should be paid to diarrhoea in children <5 years during fall-winter seasons.

Climate change is likely to worsen the public health threat of diarrheal disease in Botswana

Diarrheal disease is an important health challenge, accounting for the majority of childhood deaths globally. Climate change is expected to increase the global burden of diarrheal disease but little is known regarding climate drivers, particularly in Africa. Using health data from Botswana spanning a 30-year period (1974–2003), we evaluated monthly reports of diarrheal disease among patients presenting to Botswana health facilities and compared this to climatic variables. Diarrheal case incidence presents with a bimodal cyclical pattern with peaks in March (ANOVA p < 0.001) and October (ANOVA p < 0.001) in the wet and dry season, respectively. There is a strong positive autocorrelation (p < 0.001) in the number of reported diarrhea cases at the one-month lag level. Climatic variables (rainfall, minimum temperature, and vapor pressure) predicted seasonal diarrheal with a one-month lag in variables (p < 0.001). Diarrheal case incidence was highest in the dry season after accounting for other variables, exhibiting on average a 20% increase over the yearly mean (p < 0.001). Our analysis suggests that forecasted climate change increases in temperature and decreases in precipitation may increase dry season diarrheal disease incidence with hot, dry conditions starting earlier and lasting longer. Diarrheal disease incidence in the wet season is likely to decline. Our results identify significant health-climate interactions, highlighting the need for an escalated public health focus on controlling diarrheal disease in Botswana. Study findings have application to other arid countries in Africa where diarrheal disease is a persistent public health problem.

Modeling the impact of climate variability on diarrhea-associated diseases in Taiwan (1996-2007)

Diarrhea is an important public health problem in Taiwan. Climatic changes and an increase in extreme weather events (extreme heat, drought or rainfalls) have been strongly linked to the incidence of diarrhea-associated disease. This study investigated and quantified the relationship between climate variations and diarrhea-associated morbidity in subtropical Taiwan. Specifically, this study analyzed the local climatic variables and the number of diarrhea-associated infection cases from 1996 to 2007. This study applied a climate variation-guided Poisson regression model to predict the dynamics of diarrhea-associated morbidity. The proposed model allows for climate factors (relative humidity, maximum temperature and the numbers of extreme rainfall), autoregression, long-term trends and seasonality, and a lag-time effect. Results indicated that the maximum temperature and extreme rainfall days were strongly related to diarrhea-associated morbidity. The impact of maximum temperature on diarrhea-associated morbidity appeared primarily among children (0-14years) and older adults (40-64years), and had less of an effect on adults (15-39years). Otherwise, relative humidity and extreme rainfall days significantly contributed to the diarrhea-associated morbidity in adult. This suggested that children and older adults were the most susceptible to diarrhea-associated morbidity caused by climatic variation. Because climatic variation contributed to diarrhea morbidity in Taiwan, it is necessary to develop an early warning system based on the climatic variation information for disease control management.

Acute gastroenteritis in a pediatric hospital in rio de janeiro in pre- and post-rotavirus vaccination settings

A 4½-year hospital-based survey was conducted in Rio de Janeiro to determine baseline rates of gastroenteritis-related cases, hospitalizations, and deaths; to examine the prevalence of rotavirus strains causing admissions; and to assess the immediate impact of the nationwide rotavirus immunization program launched in March 2006. From August 2002 to May 2007, 14,473 (10.4%) of the 139,747 consultations had AGE as primary diagnosis, 491 (3.4%) children required hospitalization and two (0.4%) dehydrated children died. Gastroenteritis contribution to hospitalizations varied from ~2.3% in 2004 and 2006 to 6.4% in 2005, being roughly half of them rotavirus-related cases. A gradual decrease in rotavirus strain diversity was observed from 2002 to 2005 when a single G9P[8] prevailed until April 2006. Then only short profile G9P[4] and G2P[4] strains were detected. Gastroenteritis cases were distributed year-round in a trimodal pattern with major winter peaks. Local climate apparently affected the incidence of gastroenteritis: reduction in dry years (2004 and 2007) and explosive outbreaks caused by multiple agents during the heavy rainfalls and recurrent floods of the 2005-early 2006 period. Besides rotavirus, adenovirus and calicivirus were major gastroenteritis agents of these seemingly waterborne outbreaks. In conclusion, rotavirus vaccination impacted marginally, if at all, on the incidence of childhood gastroenteritis, as favorable results obtained by comparing data from the post-vaccine period to the preceding unusual 2005 year all but disappeared when comparing to previous pre-vaccination periods, and the shift towards G2P[4] rotavirus strains may be a global trend unrelated to vaccination.

[Profile of paediatric admissions and emergencies during an epidemic period of rotavirus in Valladolid [Spain]. Utility of a predictive model]

INTRODUCTION

The aim of this study was to determine the weeks of high rotavirus circulation in Valladolid (Spain) and to compare the characteristics of hospitalizations and emergencies in epidemic and nonepidemic periods.

METHODS

The information sources consisted of the weekly notifications to the Microbiological Information System, the Minimum Data Set, and the Emergency Registry. Expected cases for 2006 were calculated using a previously developed model. Weeks with observed cases over the upper limit of the 95% confidence interval for expected cases were considered epidemic periods. Hospitalization and emergencies in epidemic and nonepidemic periods were compared.

RESULTS

The number of cases in 2006 was 42% less than the expected number. The mean number of daily admissions was higher in epidemic periods (d=1.49; p=0.01) and the length of admissions was longer.

CONCLUSION

The activity of the paediatric service increased during the epidemic period. Consequently, implementation of surveillance activities and prevention and control programs for rotavirus in hospitals would seem advisable.