Bayesian classification and regression trees for predicting incidence of cryptosporidiosis

Global climate change-driven impacts on the Asian distribution of Limassolla leafhoppers, with implications for biological and environmental conservation

Knowing the impacts of global climate change on the habitat suitability distribution of Limassolla leafhoppers contributes to understanding the feedback of organisms on climate change from a macroecological perspective, and provides important scientific basis for protecting the ecological environment and biodiversity. However, there is limited knowledge on this aspect. Thus, our study aimed to address this gap by analyzing Asian habitat suitability and centroid shifts of Limassolla based on 19 bioclimatic variables and occurrence records. Selecting five ecological niche models with the outstanding predictive performance (Maxlike, generalized linear model, generalized additive model, random forest, and maximum entropy) along with their ensemble model from 12 models, the current habitat suitability of Limassolla and its future habitat suitability under two Shared Socio-economic Pathways (SSP1-2.6 and SSP5-8.5) in the 2050s and 2090s were predicted. The results showed that the prediction results of the five models are generally consistent. Based on ensemble model, 11 potential biodiversity hotspots with high suitability were identified. With climate change, the suitable range of Limassolla will experience both expansion and contraction. In SSP5-8.52050s, the expansion area is 118.56 × 104 km2, while the contraction area is 25.40 × 104 km2; in SSP1-2.62090s, the expansion area is 91.71 × 104 km2, and the contraction area is 26.54 × 104 km2. Furthermore, the distribution core of Limassolla will shift toward higher latitudes in the northeast direction, and the precipitation of warmest quarter was found to have the greatest impact on the distribution of Limassolla. Our research results supported our four hypotheses. Finally, this research suggests establishing ecological reserves in identified contraction to prevent habitat loss, enhancing the protection of biodiversity hotspots, and pursuing a sustainable development path with reduced emissions.

Application of Bayesian Decision Tree in Hematology Research: Differential Diagnosis of β-Thalassemia Trait from Iron Deficiency Anemia

OBJECTIVE

Several discriminating techniques have been proposed to discriminate between β-thalassemia trait (βTT) and iron deficiency anemia (IDA). These discrimination techniques are essential clinically, but they are challenging and typically difficult. This study is the first application of the Bayesian tree-based method for differential diagnosis of βTT from IDA.

METHOD

This cross-sectional study included 907 patients with ages over 18 years old and a mean (±SD) age of 25 ± 16.1 with either βTT or IDA. Hematological parameters were measured using a Sysmex KX-21 automated hematology analyzer. Bayesian Logit Treed (BLTREED) and Classification and Regression Trees (CART) were implemented to discriminate βTT from IDA based on the hematological parameters.

RESULTS

This study proposes an automatic detection model of beta-thalassemia carriers based on a Bayesian tree-based method. The BLTREED model and CART showed that mean corpuscular volume (MCV) was the main predictor in diagnostic discrimination. According to the test dataset, CART indicated higher sensitivity and negative predictive value than BLTREED for differential diagnosis of βTT from IDA. However, the CART algorithm had a high false-positive rate. Overall, the BLTREED model showed better performance concerning the area under the curve (AUC).

CONCLUSIONS

The BLTREED model showed excellent diagnostic accuracy for differentiating βTT from IDA. In addition, understanding tree-based methods are easy and do not need statistical experience. Thus, it can help physicians in making the right clinical decision. So, the proposed model could support medical decisions in the differential diagnosis of βTT from IDA to avoid much more expensive, time-consuming laboratory tests, especially in countries with limited recourses or poor health services.

Short-term association between ambient air pollution and lung cancer mortality

RATIONALE

Long-term exposure to air pollution has been associated with increased lung cancer incidence and mortality. However, the short-term association between air pollution and lung cancer mortality (LCM) remains largely unknown.

METHODS

We collected daily data on particulate matter with diameter <2.5 μm (PM_2.5), particulate matter with diameter < 10 μm (PM₁₀), sulfur dioxide (SO₂), and ozone (O₃), and LCM in three of the biggest cities in China, i.e. Beijing, Chongqing, and Guangzhou, from 2013 to 2015. We first estimated city-specific relationships between air pollutants and LCM using time-series generalized linear models, adjusting for potential confounders. A classification and regression tree (CART) model was used to stratify LCM risk based on combinations of air pollutants and meteorological factors in each city. Then we pooled the city-specific associations using random-effects meta-analysis. Meta regression was used to explore if city-specific characteristics modified the air pollution-LCM association. Finally, we stratified the analyses by season, age, and sex.

RESULTS

Over the entire period, the current-day concentrations of PM_2.5 and PM₁₀ in Chongqing and PM_2.5, PM₁₀, and SO₂ in Guangzhou were positively associated with LCM (Excess risk ranged from 0.72% (95% CI 0.27%-1.17%) to 6.06% (95% CI 0.76%-11.64%) with each 10 μg/m³ increment in different pollutants), but the association between current-day air pollution and LCM in Beijing was not significant (P > 0.05). When considering the environmental and weather factors simultaneously, current-day PM_2.5, relative humidity, and PM₁₀ were the most important factors associated with LCM in Beijing, Chongqing, and Guangzhou, respectively. LCM risk related with daily PM_2.5, PM₁₀, and SO₂ significantly increased with the increasing annual mean temperature and humidity of the city, while LCM risk related with daily O₃ significantly increased with the increases of latitude, annual mean O₃ concentration, and socioeconomic level. After stratification, the current-day PM_2.5, PM₁₀, and O₃ during the warm season in Beijing and PM_2.5, PM₁₀, and SO₂ during the cool season in Chongqing and Guangzhou were positively associated with LCM (Excess risk ranged from 0.93% (95% CI 0.42%-1.45%) to 7.16% (95% CI 0.64%-14.09%) with each 10 μg/m³ increment in different pollutants). Male and the elderly lung cancer patients were more sensitive to the short-term effect of air pollution.

CONCLUSIONS

Lung cancer patients should enhance protection measures against air pollution. More attentions should be paid for the high PM_2.5, PM₁₀, and O₃ during the warm season in Beijing, and high PM_2.5, PM₁₀, and SO₂ during the cool season in Chongqing and Guangzhou.

A diagnostic model for minimal change disease based on biological parameters

Background

Minimal change disease (MCD) is a kind of nephrotic syndrome (NS). In this study, we aimed to establish a mathematical diagnostic model based on biological parameters to classify MCD.

Methods

A total of 798 NS patients were divided into MCD group and control group. The comparison of biological indicators between two groups were performed with t-tests. Logistic regression was used to establish the diagnostic model, and the diagnostic value of the model was estimated using receiver operating characteristic (ROC) analysis.

Results

Thirteen indicators including Anti-phospholipase A2 receptor (anti-PLA2R) (P = 0.000), Total protein (TP) (P = 0.000), Albumin (ALB) (P = 0.000), Direct bilirubin (DB) (P = 0.002), Creatinine (Cr) (P = 0.000), Total cholesterol (CH) (P = 0.000), Lactate dehydrogenase (LDH) (P = 0.007), High density lipoprotein cholesterol (HDL) (P = 0.000), Low density lipoprotein cholesterol (LDL) (P = 0.000), Thrombin time (TT) (P = 0.000), Plasma fibrinogen (FIB) (P = 0.000), Immunoglobulin A (IgA) (P = 0.008) and Complement 3 (C3) (P = 0.019) were significantly correlated with MCD. Furthermore, the area under ROC curves of CH, HDL, LDL, TT and FIB were more than 0.70. Logistic analysis demonstrated that CH and TT were risk factors for MCD. According to the ROC of “CH+TT”, the AUC was 0.827, with the sensitivity of 83.0% and the specificity of 69.8% (P = 0.000).

Conclusion

The established diagnostic model with CH and TT could be used for classified diagnosis of MCD.

Risk assessment of dengue fever in Zhongshan, China: a time-series regression tree analysis

Dengue fever (DF) is the most prevalent and rapidly spreading mosquito-borne disease globally. Control of DF is limited by barriers to vector control and integrated management approaches. This study aimed to explore the potential risk factors for autochthonous DF transmission and to estimate the threshold effects of high-order interactions among risk factors. A time-series regression tree model was applied to estimate the hierarchical relationship between reported autochthonous DF cases and the potential risk factors including the timeliness of DF surveillance systems (median time interval between symptom onset date and diagnosis date, MTIOD), mosquito density, imported cases and meteorological factors in Zhongshan, China from 2001 to 2013. We found that MTIOD was the most influential factor in autochthonous DF transmission. Monthly autochthonous DF incidence rate increased by 36·02-fold [relative risk (RR) 36·02, 95% confidence interval (CI) 25·26–46·78, compared to the average DF incidence rate during the study period] when the 2-month lagged moving average of MTIOD was >4·15 days and the 3-month lagged moving average of the mean Breteau Index (BI) was ⩾16·57. If the 2-month lagged moving average MTIOD was between 1·11 and 4·15 days and the monthly maximum diurnal temperature range at a lag of 1 month was <9·6 °C, the monthly mean autochthonous DF incidence rate increased by 14·67-fold (RR 14·67, 95% CI 8·84–20·51, compared to the average DF incidence rate during the study period). This study demonstrates that the timeliness of DF surveillance systems, mosquito density and diurnal temperature range play critical roles in the autochthonous DF transmission in Zhongshan. Better assessment and prediction of the risk of DF transmission is beneficial for establishing scientific strategies for DF early warning surveillance and control.

A novel differential diagnostic model based on multiple biological parameters for immunoglobulin A nephropathy

BACKGROUND

Immunoglobulin A nephropathy (IgAN) is the most common form of glomerulonephritis in China. An accurate diagnosis of IgAN is dependent on renal biopsies, and there is lack of non-invasive and practical classification methods for discriminating IgAN from other primary kidney diseases. The objective of this study was to develop a classification model for the auxiliary diagnosis of IgAN using multiparameter analysis with various biological parameters.

METHODS

To establish an optimal classification model, 121 cases (58 IgAN vs. 63 non-IgAN) were recruited and statistically analyzed. The model was then validated in another 180 cases.

RESULTS

Of the 57 biological parameters, there were 16 parameters that were significantly different (P < 0.05) between IgAN and non-IgAN. The combination of fibrinogen, serum immunoglobulin A level, and manifestation was found to be significant in predicting IgAN. The validation accuracies of the logistic regression and discriminant analysis models were 77.5 and 77.0%, respectively at a predictive probability cut-off of 0.5, and 81.1 and 79.9%, respectively, at a predictive probability cut-off of 0.40. When the predicted probability of the equation containing the combination of fibrinogen, serum IgA level, and manifestation was more than 0.59, a patient had at least an 85.0% probability of having IgAN. When the predicted probability was lower than 0.26, a patient had at least an 88.5% probability of having non-IgAN. The results of the net reclassification improvement certificated serum Immunoglobulin A and fibrinogen had classification power for discriminating IgAN from non-IgAN.

CONCLUSIONS

These models possess potential clinical applications in distinguishing IgAN from other primary kidney diseases.