Lassa fever cases and mortality in Nigeria: Quantile Regression vs. Machine Learning Models

Lassa fever (LF) is caused by the Lassa fever virus (LFV). It is endemic in West Africa, of which % of the infections are ascribed to Nigeria. This disease affects mostly the productive age and hence a proper understanding of the dynamics of this disease will help in formulating policies that would help in curbing the spread of LF. The objective of this study is to compare the performance of quantile regression models with that of Machine Learning models in. Data between between 7th January 2018 2018 and 17th December, 2022 on suspected cases, confirmed cases and deaths resulting from LF were retrieved from the Nigeria Centre for Disease Control (NCDC). The data obtained were fitted to quantile regression models (QRM) at 25, 50 and 75% as well as to Machine learning models. The response variable being confirmed cases and mortality due to Lassa fever in Nigeria while the independent variables were total confirmed cases, the week, month and year. Result showed that the highest monthly mean confirmed cases (56) and mortality (9) from LF were reported in February. The first quarter of the year reported the highest cases of both confirmed cases and deaths in Nigeria. Result also revealed that for the confirmed cases, quantile regression at 50% outperformed the best of the MLM, Gaussian-matern5/2 GPR (RMSE=10.3393 vs. 11.615), while for mortality, the medium Gaussian SVM (RMSE=1.6441 vs. 1.8352) outperformed QRM. Quantile regression model at 50% better captured the dynamics of the confirmed cases of LF in Nigeria while the medium Gaussian SVM better captured the mortality of LF in Nigeria. Among the features selected, confirmed cases was found to be the most important feature that drive its mortality with the implication that as the confirmed cases of Lassa fever increases, is a significant increase in its mortality. This therefore necessitates a need for a better intervention measures that will help curb Lassa fever mortality as a result of the increase in the confirmed cases. There is also a need for promotion of good community hygiene which could include; discouraging rodents from entering homes and putting food in rodent proof containers to avoid contamination to help hart the spread of Lassa fever in Nigeria.

The impact of democracy and income on CO2 emissions in MINT countries: evidence from quantile regression model

This study analyses the relationship between democracy and environmental pollution in the MINT countries using a panel data spanning 1971-2016. It also investigates the interactive effect of income and democracy on CO2 emissions. We used various estimation techniques for the analysis, ranging from the quantile regression, OLS-fixed effect and GLS-random effect regressions with Driscoll-Kraay standard errors to control for cross-sectional dependence while a panel threshold regression is used for robustness check. The results showed existence of long-run relationship between CO2 emissions and the explanatory variables. The quantile regression results for interaction model indicate that economic growth, democracy and trade openness promote environmental pollution via their positive effects on CO2 emissions. Primary energy however reduces pollution across the lower and middle quantiles but enhances it in higher quantiles. The interaction effect is negative and statistically significant across all quantiles. This implies that democracy has a significant role in moderating the impact of income on CO2 emission in the MINT countries. It thus follows that if the MINT countries radically strengthen democracy and enhance income, it would be possible for them to achieve greater economic development and reduce CO2. In addition, a single threshold model is used to identify the asymmetry in response to CO2 emissions at lower and upper levels of democratic regimes. The results showed that once the degree of democracy is above the threshold level, an increase in income would reduce CO2 emissions but once it is below the threshold level, the effect of income becomes insignificant. Based on these results, the MINT countries need to strengthen democracy, enhance income level and relax trade barriers.

Towards more efficient low-carbon agricultural technology extension in China: identifying lead smallholder farmers and their behavioral determinants

In the transition to low-carbon agriculture, smallholder farmers face more constraints. Identifying lead smallholder farmers and leveraging their peer effects can accelerate low-carbon agricultural technology extension among smallholder farmers. Based on survey data from 643 rice farmers in Zhejiang Province, China, this study constructs a finite mixture model (FMM) to identify lead smallholder farmers and then uses a quantile regression model (QRM) to explore their behavioral determinants. The main conclusions are as follows. First, despite the homogeneity in the production mode and resource constraints, lead smallholder farmers are younger and more open to risk, and they have higher educational levels and more family laborers. Second, a higher use efficiency of heterogeneous information is the key to differentiating lead smallholder farmers from other smallholder farmers. Third, green agricultural producer services can effectively alleviate resource constraints and contribute to the low-carbon transition of all smallholder farmers. These results can help redesign targeted extension policies to incentivize lead smallholder farmers.

Quantile regression for exposure data with repeated measures in the presence of non-detects

BACKGROUND

Exposure data with repeated measures from occupational studies are frequently right-skewed and left-censored. To address right-skewed data, data are generally log-transformed and analyses modeling the geometric mean operate under the assumption the data are log-normally distributed. However, modeling the mean of exposure may lead to bias and loss of efficiency if the transformed data do not follow a known distribution. In addition, left censoring occurs when measurements are below the limit of detection (LOD).

OBJECTIVE

To present a complete illustration of the entire conditional distribution of an exposure outcome by examining different quantiles, rather than modeling the mean.

METHODS

We propose an approach combining the quantile regression model, which does not require any specified error distributions, with the substitution method for skewed data with repeated measurements and non-detects.

RESULTS

In a simulation study and application example, we demonstrate that this method performs well, particularly for highly right-skewed data, as parameter estimates are consistent and have smaller mean squared error relative to existing approaches.

SIGNIFICANCE

The proposed approach provides an alternative insight into the conditional distribution of an exposure outcome for repeated measures models.

Application of machine learning technique for optimizing roadside design to decrease barrier crash costs, a quantile regression model approach

INTRODUCTION

In-transport vehicles often leave the travel lane and encroach onto natural objects on the roadsides. These types of crashes are called run-off the road crashes (ROR). Such crashes accounts for a significant proportion of fatalities and severe crashes. Roadside barrier installation would be warranted if they could reduce the severity of these types of crashes. However, roadside barriers still account for a significant proportion of severe crashes in Wyoming. The impact of the crash severity would be higher if barriers are poorly designed, which could result in override or underride barrier crashes. Several studies have been conducted to identify optimum values of barrier height. However, limited studies have investigated the monetary benefit associated with adjusting the barrier heights to the optimal values. In addition, few studies have been conducted to model barrier crash cost. This is because the crash cost is a heavily skewed distribution, and well-known distributions such as linear or poison models are incapable of capturing the distribution. A semi-parametric distribution such as asymmetric Laplace distribution can be used to account for this type of sparse distribution.

METHOD

Interaction between different predictors were considered in the analysis. Also, to account for exposure effects across various barriers, barrier lengths and traffic volumes were incorporated in the models. This study is conducted by using a novel machine-learning-based cost-benefit optimization to provide an efficient guideline for decision makers. This method was used for predicting barrier crash costs without barrier enhancement. Subsequently the benefit was obtained by optimizing traffic barrier height and recalculating the benefit and cost. The trained model was used for crash cost prediction on barriers with and without crashes.

RESULTS

The results of optimization clearly demonstrated the benefit of optimizing the heights of road barriers around the state. Practical Applications: The findings can be utilized by the Wyoming Department of Transportation (WYDOT) to determine the heights of which barriers should be optimized first. Other states can follow the procedure described in this paper to upgrade their roadside barriers.

Prediction of Hospitalization Length. Quantile Regression Predicts Hospitalization Length and its Related Factors better than Available Methods

BACKGROUND

Length of hospitalization is one of the most important indices in evaluating the efficiency and effectiveness of hospitals and the optimal use of resources. Identifying these indices' associated factors could be useful. This study aimed to investigate effective factors of the length of hospitalization in Zanjan teaching hospitals in 2018 using the Quantile regression model.

METHODS

This cross-sectional study was conducted on 1,031 patients. The study population consisted of patients in orthopaedic, pediatric, internal, surgical and intensive care units. The samples were selected by multistage random sampling. The information was collected by a pre-designed checklist. The Quantile regression model and ordinary regression model were performed on the data.

RESULTS

Of the 1,031 patients admitted to different units, 624 (60.52%) were male. Mean and standard deviation of length of hospitalization for men, women and all patients were 7.25±5.48, 8.09±6.35 and 7.58±5.83 respectively. For 90 percent of patients the length of hospitalization was less than 14 days. Twenty-five percent of patients in pediatric and orthopedic units and ten percent of patients in internal and surgery units were hospitalized less than three days. In all quantiles, patients' length of hospitalization in surgery and orthopedic units, compared to the intensive care unit, and patients hospitalized for injuries and poisonings compared to other causes, had a statistically significant difference. (p<0.05).

CONCLUSION

Due to the heterogeneity (skewness) of the length of hospital stay in different units of the hospital, the quantile regression model predicts the length of hospital stay more precisely than the ordinary regression models.

Analysis of hospitalization costs related to fall injuries in elderly patients

BACKGROUND

With the aging world population, the incidence of falls has intensified and fall-related hospitalization costs are increasing. Falls are one type of event studied in the health economics of patient safety, and many developed countries have conducted such research on fall-related hospitalization costs. However, China, a developing country, still lacks large-scale studies in this area.

AIM

To investigate the factors related to the hospitalization costs of fall-related injuries in elderly inpatients and establish factor-based, cost-related groupings.

METHODS

A retrospective study was conducted. Patient information and cost data for elderly inpatients (age ≥ 60 years, n = 3362) who were hospitalized between 2016 and 2019 due to falls was collected from the medical record systems of two grade-A tertiary hospitals in China. Quantile regression (QR) analysis was used to identify the factors related to fall-related hospitalization costs. A decision tree model based on the chi-squared automatic interaction detector algorithm for hospitalization cost grouping was built by setting the factors in the regression results as separation nodes.

RESULTS

The total hospitalization cost of fall-related injuries in the included elderly patients was 180479203.03 RMB, and the reimbursement rate of medical benefit funds was 51.0% (92039709.52 RMB/180479203.03 RMB). The medical material costs were the highest component of the total hospitalization cost, followed (in order) by drug costs, test costs, treatment costs, integrated medical service costs and blood transfusion costs The QR results showed that patient age, gender, length of hospital stay, payment method, wound position, wound type, operation times and operation type significantly influenced the inpatient cost (P < 0.05). The cost grouping model was established based on the QR results, and age, length of stay, operation type, wound position and wound type were the most important influencing factors in the model. Furthermore, the cost of each combination varied significantly.

CONCLUSION

Our grouping model of hospitalization costs clearly reflected the key factors affecting hospitalization costs and can be used to strengthen the reasonable control of these costs.

Quantifying the dependence of cyanobacterial growth to nutrient for the eutrophication management of temperate-subtropical shallow lakes

The increasing global occurrence of cyanobacterial blooms, attributed primarily to human-induced nutrient enrichment, significantly degrades freshwater ecosystems and poses serious risks to human health. The current study examined environmental variables and cyanobacterial biovolume (B_Cyano) of 28 shallow lakes in the eastern China plains during the spring and summer of 2018. We used a 95% quantile regression model to explore season-specific response of B_Cyano to total nitrogen (TN), or total phosphorus (TP), and robust linear relationships were observed between log(B_Cyano+0.001) and log(TN), or log(TP) in both spring and summer periods. Based on these regressions, regional-scale and season-specific TN and TP thresholds are proposed for these lakes to ensure the safety for recreational waters and drinking water source. However, actual B_Cyano for a given concentration of TN (or TP) for many observations were considerably lower than the results of the 95% regression model predict, indicating that other factors significantly modulated nutrient limitation of B_Cyano. Generalized additive model and quantile regression model were used together to explore potentially significant modulating factors, of which lake retention time, macrophytes cover and N: P ratio were identified as most important. Thus, it is necessary to develop type-specific nutrient thresholds with the consideration of these significant modulating factors. Furthermore, nutrient-B_Cyano relationships of our studied lakes with lake retention time>100 days and no macrophyte were further explored and nutrient thresholds of this lake type were proposed. Nutrient thresholds proposed in this study may play an essential role in achieving a cost-effective eutrophication management for shallow lakes both in the eastern China plains and elsewhere with similar climatic background. On a broader scale, the approaches and findings of this study may provide valuable reference to formulate reasonable nutrient reduction targets for other ecoregions with different climatic conditions.

Simultaneous quantile regression and determinants of under-five severe chronic malnutrition in Ghana

BACKGROUND

Under-five malnutrition is a major public health issue contributing to mortality and morbidity, especially in developing countries like Ghana where the rates remain unacceptably high. Identification of critical risk factors of under-five malnutrition using appropriate and advanced statistical methods can help formulate appropriate health programmes and policies aimed at achieving the United Nations SDG Goal 2 target 2. This study attempts to develop a simultaneous quantile regression, an in-depth statistical model to identify critical risk factors of under-five severe chronic malnutrition (severe stunting).

METHODS

Based on the nationally representative data from the 2014 Ghana Demographic and Health Survey, height-for-age z-score (HAZ) was estimated. Multivariable simultaneous quantile regression modelling was employed to identify critical risk factors for severe stunting based on HAZ (a measure of chronic malnutrition in populations). Quantiles of HAZ with focus on severe stunting were modelled and the impact of the risk factors determined. Significant test of the difference between slopes at different selected quantiles of severe stunting and other quantiles were performed. A quantile regression plots of slopes were developed to visually examine the impact of the risk factors across these quantiles.

RESULTS

Data on a total of 2716 children were analysed out of which 144 (5.3%) were severely stunted. The models identified child level factors such as type of birth, sex, age, place of delivery and size at birth as significant risk factors of under-five severe stunting. Maternal and household level factors identified as significant predictors of under-five severe stunting were maternal age and education, maternal national health insurance status, household wealth status, and number of children under-five in households. Highly significant differences exist in the slopes between 0.1 and 0.9 quantiles. The quantile regression plots for the selected quantiles from 0.1 to 0.9 showed substantial differences in the impact of the covariates across the quantiles of HAZ considered.

CONCLUSION

Critical risk factors that can aid formulation of child nutrition and health policies and interventions that will improve child nutritional outcomes and survival were identified. Modelling under-five severe stunting using multivariable simultaneous quantile regression models could be beneficial to addressing the under-five severe stunting.

A two decades study on ozone variability and trend over the main urban areas of the São Paulo state, Brazil

In this paper, we analyze the variability of the ozone concentration over São Paulo Macrometropolis, as well the factors, which determined the tendency observed in the last two decades. Time series of hourly ozone concentrations measured at 16 automated stations from an air quality network from 1996 to 2017 were analyzed. The temporal variability of ozone concentrations exhibits well-defined daily and seasonal patterns. Ozone presents a significant positive correlation between the number of cases (thresholds of 100-160 μg m^-3) and the fuel sales of gasohol and diesel. The ozone concentrations do not exhibit significant long-term trends, but some sites present positive trends that occurs in sites in the proximity of busy roads and negative trends that occurs in sites located in residential areas or next to trees. The effect of atmospheric process of transport and ozone formation was analyzed using a quantile regression model (QRM). This statistical model can deal with the nonlinearities that appear in the relationship of ozone and other variables and is applicable to time series with non-normal distribution. The resulting model explains 0.76% of the ozone concentration variability (with global coefficient of determination R¹ = 0.76) providing a better representation than an ordinary least square regression model (with coefficient of determination R² = 0.52); the effect of radiation and temperature are the most critical in determining the highest ozone quantiles.