Prediction of hot spot areas of hemorrhagic fever with renal syndrome in Hunan Province based on an information quantity model and logistical regression model

Chen, Zixi; Liu, Fuqiang; Li, Bin; Peng, Xiaoqing; Lin, Fan; Luo, Aijing

doi:10.1371/journal.pntd.0008939

Cited by 13 publications

(31 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…IV [ 13 ] uses the frequency or density of schistosomiasis occurrence to reflect the risk effect of different influencing factors and their sub-intervals. An IV is calculated that represents the contribution of different influencing factors related to the occurrence of schistosomiasis.…”

Section: Methodsmentioning

confidence: 99%

“…An IV is calculated that represents the contribution of different influencing factors related to the occurrence of schistosomiasis. A regional risk assessment for schistosomiasis transmission is realized through the spatial superposition of multi-factor information [ 13 ]. The formula is as follows: …”

Section: Methodsmentioning

confidence: 99%

“…IV and classification algorithms can predict vector-borne infectious disease during the initial stage. For example, Chen et al [ 13 ] used a coupled model of IV and LR (IV + LR) to predict hot spots of hemorrhagic fever with renal syndrome in Hunan Province of China, resulting in more accurate prediction. The application of information value combines with other models for risk assessment of infectious diseases is also increasing, which makes up for the lack of simple information value model, and simple machine learning.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Identification of the high-risk area for schistosomiasis transmission in China based on information value and machine learning: a newly data-driven modeling attempt

Gong

Zhu

et al. 2021

Infect Dis Poverty

View full text Add to dashboard Cite

Background Schistosomiasis control is striving forward to transmission interruption and even elimination, evidence-lead control is of vital importance to eliminate the hidden dangers of schistosomiasis. This study attempts to identify high risk areas of schistosomiasis in China by using information value and machine learning. Methods The local case distribution from schistosomiasis surveillance data in China between 2005 and 2019 was assessed based on 19 variables including climate, geography, and social economy. Seven models were built in three categories including information value (IV), three machine learning models [logistic regression (LR), random forest (RF), generalized boosted model (GBM)], and three coupled models (IV + LR, IV + RF, IV + GBM). Accuracy, area under the curve (AUC), and F1-score were used to evaluate the prediction performance of the models. The optimal model was selected to predict the risk distribution for schistosomiasis. Results There is a more prone to schistosomiasis epidemic provided that paddy fields, grasslands, less than 2.5 km from the waterway, annual average temperature of 11.5–19.0 °C, annual average rainfall of 1000–1550 mm. IV + GBM had the highest prediction effect (accuracy = 0.878, AUC = 0.902, F1 = 0.920) compared with the other six models. The results of IV + GBM showed that the risk areas are mainly distributed in the coastal regions of the middle and lower reaches of the Yangtze River, the Poyang Lake region, and the Dongting Lake region. High-risk areas are primarily distributed in eastern Changde, western Yueyang, northeastern Yiyang, middle Changsha of Hunan province; southern Jiujiang, northern Nanchang, northeastern Shangrao, eastern Yichun in Jiangxi province; southern Jingzhou, southern Xiantao, middle Wuhan in Hubei province; southern Anqing, northwestern Guichi, eastern Wuhu in Anhui province; middle Meishan, northern Leshan, and the middle of Liangshan in Sichuan province. Conclusions The risk of schistosomiasis transmission in China still exists, with high-risk areas relatively concentrated in the coastal regions of the middle and lower reaches of the Yangtze River. Coupled models of IV and machine learning provide for effective analysis and prediction, forming a scientific basis for evidence-lead surveillance and control. Graphic Abstract

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of the high-risk area for schistosomiasis transmission in China based on information value and machine learning: a newly data-driven modeling attempt

Gong

Zhu

et al. 2021

Infect Dis Poverty

View full text Add to dashboard Cite

show abstract

“…PCA is one of the effective ways to reduce dimensionality and minimize multicollinearity. Currently published articles of logistical regression based on PCA are focused on genome-wide association studies [ 37 ] and disease research, such as gestational diabetes mellitus [ 38 ] and nephropathy [ 39 ]. Health care accessibility for the Texas Medicaid Gap took advantage of principal component analysis (PCA) to eliminate multicollinearity negative effects and to compare comprehensive social-economic impacts between unadjusted conditions and adjusted conditions.…”

Section: Methodsmentioning

confidence: 99%

Predict Health Care Accessibility for Texas Medicaid Gap

Zhang

2021

Healthcare

View full text Add to dashboard Cite

Medicaid is a unique approach in ensuring the below poverty population obtains free insurance coverage under federal and state provisions in the United States. Twelve states without expanded Medicaid caused two million people who were under the poverty line into health insecurity. Principal Component-based logistical regression (PCA-LA) is used to consider health status (HS) as a dependent variable and fourteen social-economic indexes as independent variables. Four composite components incorporated health conditions (i.e., “no regular source of care” (NRC), “last check-up more than a year ago” (LCT)), demographic impacts (i.e., four categorized adults (AS)), education (ED), and marital status (MS). Compared to the unadjusted LA, direct adjusted LA, and PCA-unadjusted LA three methods, the PCA-LA approach exhibited objective and reasonable outcomes in presenting an odd ratio (OR). They included that health condition is positively significant to HS due to beyond one OR, and negatively significant to ED, AS, and MS. This paper provided quantitative evidence for the Medicaid gap in Texas to extend Medicaid, exposed healthcare geographical inequity, offered a sight for the Centers for Disease Control and Prevention (CDC) to improve the Medicaid program and make political justice for the Medicaid gap.

show abstract

“…Principal Component Analysis (PCA) is one of the effective ways to reduce dimensionality and minimize multicollinearity. Currently published articles of logistical regression based on PCA are focused on genome−wide association studies [16] and diseases research such as gestational diabetes mellitus [17] and nephropathy [18], which is hard to see in medical gap research. PCA−based LA health access analysis of the medical gap aims to compare comprehensive social−economic impacts between unadjusted conditions and adjusted conditions.…”

Section: Introductionmentioning

confidence: 99%

Principal Component-Based Logistical Regression Algorithms to Predict Health care Accessibility for Texas Medicaid Gap

Zhang¹,

Wu²

2021

Preprint

View full text Add to dashboard Cite

Background12 states without expanded Medicaid caused 2 million people who were under the poverty line across the U.S to be in Medicaid limbo and not eligible for subsidized health plans on the Affordable Care Act insurance exchanges. In order to amplify geographic equity, this paper aims to explore the health access for Medicaid gaps in Texas. MethodsPrincipal Component-based logistical regression algorithms (PCA-LA) is provided data visualization and comparison in between unadjusted and adjusted Medicaid programs. Initially, Principal Component Analysis (PCA) eliminated well-known multiplicity problems between explanatory variables in the application of epidemiology. Optimized the traditional logistical Regression (LR), the PCA-LA method, is considered health status (HS) as a dependent variable with 0 (“poor” health) and 1 (“good” health), fourteen social-economic indexes as independent variables. ResultsAfter Principal Component Analysis (PCA), four composite components incorporated health conditions (i.e., “no regular source of care” (NRC), “Last check up more than a year ago” (LCT)), demographic impacts (i.e., four categorized adults (AS)), education (ED), and marital status (MS). Compared to the unadjusted LA, direct adjusted LA, and PCA-unadjusted LA three methods, the PCA-LA approach exhibited objective and reasonable outcomes in presenting an Odd Ratio (OR). They included that health condition is positively significant to HS due to beyond 1 OR, and negatively significant to ED, AS, and MS due to less than 1 OR. ConclusionsThis paper provided quantitative evidence for the Medicaid gap in Texas to extend Medicaid, exposed healthcare geographical inequity, offered a sight for the Centers for Disease Control and Prevention (CDC) to raise researchable direction of the Medicaid program and make a timely scientific judgment of Texas healthcare accessibility.

show abstract

Prediction of hot spot areas of hemorrhagic fever with renal syndrome in Hunan Province based on an information quantity model and logistical regression model

Cited by 13 publications

References 35 publications

Identification of the high-risk area for schistosomiasis transmission in China based on information value and machine learning: a newly data-driven modeling attempt

Identification of the high-risk area for schistosomiasis transmission in China based on information value and machine learning: a newly data-driven modeling attempt

Predict Health Care Accessibility for Texas Medicaid Gap

Principal Component-Based Logistical Regression Algorithms to Predict Health care Accessibility for Texas Medicaid Gap

Contact Info

Product

Resources

About