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

Abstract

BackgroundIn 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.Methodology/Principal findingsSchistosomiasis 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.Conclusions/SignificancePredictive 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.

Predictive Models for the Medical Diagnosis of Dengue: A Case Study in Paraguay

“…Artificial neural networks are, as their name indicates, computational networks which attempt to simulate, in a gross manner, the decision process in networks of nerve cell (neurons) of the biological (human or animal) central nervous system [17, 18].…”

Derivation and external validation of a model to predict 2-year mortality risk of patients with advanced schistosomiasis after discharge

“…We formed a derivation and a validation cohort using a previously constructed database of patients with advanced schistosomiasis from Hubei Province, China. The database was a population-based repository that included blood biochemical measurements from >4000 cases at admission [11]. Patients were diagnosed according to the Diagnostic Criteria for Schistosomiasis (WS261–2006) issued by China's Ministry of Health which covered: (1) the patient who had ever lived in S. japonicum endemic region and has contact history with S. japonicum ; (2) involvement of ascites, splenomegaly, portal hypertension and gastro-esophageal variceal bleeding, or with granulomatous lesion of the colon and rectum or severe growth retardation; (3) anti- S. japonicum antibody could be detected using at least one of the following tests: ELISA, IHA, DDI, COPT or DIFA; and (4) the result of stool examination or rectal biopsy was positive.…”

“…In addition to allowing clinicians to screen for patients with high 2-year mortality, the analysis also has the potential to clarify risk factors for morbidity in acute schistosomiasis patients, including co-morbidities. Furthermore, none of previous prognosis prediction studies on advanced schistosomiasis has attempted to predict the 2-year mortality risk after discharge based on commonly used clinical indicators at admission, or discussed the performance of different mortality risk prediction models [11,12].…”

Schistosoma japonicum infected sentinel mice surveillance and spatial point pattern analysis in Hubei province, China, 2010-2018

“…Over the past six decades, Hubei province has made remarkable progress in reducing S. japonicum infections in humans through a combination of chemotherapy and snail control.The goal of reducing human and bovine infection prevalence below 1% in every endemic region by 2013 was achieved [4]. On that occasion, the schistosomiasis control program shifted its focus from transmission control to the elimination of the disease [5]., Schistosomiasis has historically been highly endemic in Hubei Province, which is located in the middle and lower reaches of the Yangtze River [6,7]. The number of patients and cattle affected, and the relevant snail areas, have almost always been higher than in other schistosomiasis-endemic provinces in China [8].The O.hupensis in Hubei province are mainly distributed from the Yichang to the Wuxue segment of the Yangtze River, in the Jianghan Plain, and in the Hanbei, the Fushui, and other rivers connected to the Yangtze River.…”