Dataset Information

Comparison of three data mining models for prediction of advanced schistosomiasis prognosis in the Hubei province.

ABSTRACT: In order to better assist medical professionals, this study aimed to develop and compare the performance of three models-a multivariate logistic regression (LR) model, an artificial neural network (ANN) model, and a decision tree (DT) model-to predict the prognosis of patients with advanced schistosomiasis residing in the Hubei province.Schistosomiasis surveillance data were collected from a previous study based on a Hubei population sample including 4136 advanced schistosomiasis cases. The predictive models use LR, ANN, and DT methods. From each of the three groups, 70% of the cases (2896 cases) were used as training data for the predictive models. The remaining 30% of the cases (1240 cases) were used as validation groups for performance comparisons between the three models. Prediction performance was evaluated using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. Univariate analysis indicated that 16 risk factors were significantly associated with a patient's outcome of prognosis. In the training group, the mean AUC was 0.8276 for LR, 0.9267 for ANN, and 0.8229 for DT. In the validation group, the mean AUC was 0.8349 for LR, 0.8318 for ANN, and 0.8148 for DT. The three models yielded similar results in terms of accuracy, sensitivity, and specificity.Predictive models for advanced schistosomiasis prognosis, respectively using LR, ANN and DT models were proved to be effective approaches based on our dataset. The ANN model outperformed the LR and DT models in terms of AUC.

SUBMITTER: Li G

PROVIDER: S-EPMC5831639 | biostudies-literature | 2018 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparison of three data mining models for prediction of advanced schistosomiasis prognosis in the Hubei province.

Li Guo G Zhou Xiaorong X Liu Jianbing J Chen Yuanqi Y Zhang Hengtao H Chen Yanyan Y Liu Jianhua J Jiang Hongbo H Yang Junjing J Nie Shaofa S

PLoS neglected tropical diseases 20180215 2

<h4>Background</h4>In order to better assist medical professionals, this study aimed to develop and compare the performance of three models-a multivariate logistic regression (LR) model, an artificial neural network (ANN) model, and a decision tree (DT) model-to predict the prognosis of patients with advanced schistosomiasis residing in the Hubei province.<h4>Methodology/principal findings</h4>Schistosomiasis surveillance data were collected from a previous study based on a Hubei population samp ...[more]

PMID: 29447165

Similar Datasets

Project description:BackgroundSchistosomiasis remains a major public health problem in China. The major endemic areas are located in the lake and marshland regions of southern China, particularly in areas along the middle and low reach of the Yangtze River. Spatial analytical techniques are often used in epidemiology to identify spatial clusters in disease regions. This study assesses the spatial distribution of schistosomiasis and explores high-risk regions in Hubei Province, China to provide guidance on schistosomiasis control in marshland regions.MethodsIn this study, spatial autocorrelation methodologies, including global Moran's I and local Getis-Ord statistics, were utilized to describe and map spatial clusters and areas where human Schistosoma japonicum infection is prevalent at the county level in Hubei province. In addition, linear logistic regression model was used to determine the characteristics of spatial autocorrelation with time.ResultsThe infection rates of S. japonicum decreased from 2009 to 2013. The global autocorrelation analysis results on the infection rate of S. japonicum for five years showed statistical significance (Moran's I > 0, P < 0.01), which suggested that spatial clusters were present in the distribution of S. japonicum infection from 2009 to 2013. Local autocorrelation analysis results showed that the number of highly aggregated areas ranged from eight to eleven within the five-year analysis period. The highly aggregated areas were mainly distributed in eight counties.ConclusionsThe spatial distribution of human S. japonicum infections did not exhibit a temporal change at the county level in Hubei Province. The risk factors that influence human S. japonicum transmission may not have changed after achieving the national criterion of infection control. The findings indicated that spatial-temporal surveillance of S. japonicum transmission plays a significant role on schistosomiasis control. Timely and integrated prevention should be continued, especially in the Yangtze River Basin of Jianghan Plain area.

Project description:BACKGROUND:Cancer prognosis prediction is valuable for patients and clinicians because it allows them to appropriately manage care. A promising direction for improving the performance and interpretation of expression-based predictive models involves the aggregation of gene-level data into biological pathways. While many studies have used pathway-level predictors for cancer survival analysis, a comprehensive comparison of pathway-level and gene-level prognostic models has not been performed. To address this gap, we characterized the performance of penalized Cox proportional hazard models built using either pathway- or gene-level predictors for the cancers profiled in The Cancer Genome Atlas (TCGA) and pathways from the Molecular Signatures Database (MSigDB). RESULTS:When analyzing TCGA data, we found that pathway-level models are more parsimonious, more robust, more computationally efficient and easier to interpret than gene-level models with similar predictive performance. For example, both pathway-level and gene-level models have an average Cox concordance index of ~ 0.85 for the TCGA glioma cohort, however, the gene-level model has twice as many predictors on average, the predictor composition is less stable across cross-validation folds and estimation takes 40 times as long as compared to the pathway-level model. When the complex correlation structure of the data is broken by permutation, the pathway-level model has greater predictive performance while still retaining superior interpretative power, robustness, parsimony and computational efficiency relative to the gene-level models. For example, the average concordance index of the pathway-level model increases to 0.88 while the gene-level model falls to 0.56 for the TCGA glioma cohort using survival times simulated from uncorrelated gene expression data. CONCLUSION:The results of this study show that when the correlations among gene expression values are low, pathway-level analyses can yield better predictive performance, greater interpretative power, more robust models and less computational cost relative to a gene-level model. When correlations among genes are high, a pathway-level analysis provides equivalent predictive power compared to a gene-level analysis while retaining the advantages of interpretability, robustness and computational efficiency.

Project description:High-resolution mass spectrometry (HRMS) data has revolutionized the identification of environmental contaminants through non-targeted analysis (NTA). However, chemical identification remains challenging due to the vast number of unknown molecular features typically observed in environmental samples. Advanced data processing techniques are required to improve chemical identification workflows. The ideal workflow brings together a variety of data and tools to increase the certainty of identification. One such tool is chromatographic retention time (RT) prediction, which can be used to reduce the number of possible suspect chemicals within an observed RT window. This paper compares the relative predictive ability and applicability to NTA workflows of three RT prediction models: (1) a logP (octanol-water partition coefficient)-based model using EPI Suite™ logP predictions; (2) a commercially available ACD/ChromGenius model; and, (3) a newly developed Quantitative Structure Retention Relationship model called OPERA-RT. Models were developed using the same training set of 78 compounds with experimental RT data and evaluated for external predictivity on an identical test set of 19 compounds. Both the ACD/ChromGenius and OPERA-RT models outperformed the EPI Suite™ logP-based RT model (R2 = 0.81-0.92, 0.86-0.83, 0.66-0.69 for training-test sets, respectively). Further, both OPERA-RT and ACD/ChromGenius predicted 95% of RTs within a ± 15% chromatographic time window of experimental RTs. Based on these results, we simulated an NTA workflow with a ten-fold larger list of candidate structures generated for formulae of the known test set chemicals using the U.S. EPA's CompTox Chemistry Dashboard (https://comptox.epa.gov/dashboard), RTs for all candidates were predicted using both ACD/ChromGenius and OPERA-RT, and RT screening windows were assessed for their ability to filter out unlikely candidate chemicals and enhance potential identification. Compared to ACD/ChromGenius, OPERA-RT screened out a greater percentage of candidate structures within a 3-min RT window (60% vs. 40%) but retained fewer of the known chemicals (42% vs. 83%). By several metrics, the OPERA-RT model, generated as a proof-of-concept using a limited set of open source data, performed as well as the commercial tool ACD/ChromGenius when constrained to the same small training and test sets. As the availability of RT data increases, we expect the OPERA-RT model's predictive ability will increase.

Project description:BackgroundFew studies have investigated the change in life expectancy (LE) and the healthy lifespan among patients with advanced schistosomiasis. This study was to evaluate the LE and healthy life expectancy (HLE) for patients and assess the mechanism responsible for the LE inequality.MethodsWe utilized data from a dynamic advanced schistosomiasis cohort (10,362 patients) for the period from January 2008 to December 2019 in Hunan Province, China, to calculate the LEs of patients, and made a comparison with that of general population (19,642 schistosomiasis-free individuals) in the schistosomiasis endemic areas. LEs were estimated from 15 years of age by constructing period life tables. Arriaga's decomposition method was applied to quantify the influence of the age structure on the difference in LE. HLE for advanced schistosomiasis patients was calculated by using Sullivan method with age-specific disability weight. The LE and HLE were calculated for both males and females to perform further analyses on gender gap.ResultsThe estimated LE for advanced schistosomiasis patients aged 15-19 was 49.51 years (48.86 years for males and 51.07 years for females), which was 20.14 years lower compared with general population (69.65 years), and the LE gap between patients and general population decreased with age. The largest age-specific mortality contribution to the gap (32.06%) occurred at age 80-84 years. Women had a lower LE and HLE than men at age ≥ 60 years (both gender gaps in LE and HLE < 0). For advanced schistosomiasis patients, the gender gap in LE was largely attributed to the difference in mortality among those under the age of 55; the age-specific mortality in women exerted positive influence on the gap at age 25-64 and 75-79 years, with the contribution rate ranging from 0.59% to 57.02%, and made the negative contribution at other age groups.ConclusionsThe LE of advanced schistosomiasis patients was still much lower compared with general population. Strengthened prevention strategies and targeted treatments are needed to reduce morbidity and mortality due to advanced schistosomiasis, especially for younger population and elderly female patients.

Dataset Information

Comparison of three data mining models for prediction of advanced schistosomiasis prognosis in the Hubei province.

Publications

Comparison of three data mining models for prediction of advanced schistosomiasis prognosis in the Hubei province.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets