Survivability Prognosis for Lung Cancer Patients at Different Severity Stages by a Risk Factor-Based Bayesian Network Modeling.

Lung cancer is a major reason of mortalities. Estimating the survivability for this disease has become a key issue to families, hospitals, and countries. A conditional Gaussian Bayesian network model was presented in this study. This model considered 15 risk factors to predict the survivability of a lung cancer patient at 4 severity stages. We surveyed 1075 patients. The presented model is constructed by using the demographic, diagnosed-based, and prior-utilization variables. The proposed model for the survivability prognosis at different four stages performed R2 of 93.57%, 86.83%, 67.22%, and 52.94%, respectively. The model predicted the lung cancer survivability with high accuracy compared with the reported models. Our model also shows that it reached the ceiling of an ideal Bayesian network.

Redundant and Nonredundant Information for Model Calibration or Hydraulic Tomography.

Drawdown data from independent pumping tests have widely been used to validate the estimated hydraulic parameters from inverse modeling or hydraulic tomography (HT). Yet, the independent pumping test has not been clearly defined. Therefore, the goal of this paper is to define this independent pumping test concept, based on the redundant or nonredundant information about aquifer heterogeneity embedded in the observed heads during cross-hole pumping tests. The definition of complete, moderate redundancy and high nonredundancy of information are stipulated using cross-correlation analysis of the relationship between the head and heterogeneity. Afterward, data from numerical experiments and field sequential pumping test campaigns reinforce the concept and the definition.

Medical expenditure estimation by Bayesian network for lung cancer patients at different severity stages.

Lung cancer is one of the leading causes of mortality, and its medical expenditure has increased dramatically. Estimating the expenditure for this disease has become an urgent concern of the supporting families, medial institutes, and government. In this study, a conditional Gaussian Bayesian network (CGBN) model was developed to incorporate the comprehensive risk factors to estimate the medical expenditure of a lung cancer patient at different stages. A total of 961 patients were surveyed by the four severity stages of lung cancer. The proposed CGBN model identified the correlation and association of 15 risk factors to the medical expenditure of different severity stages of lung cancer patients. The relationships among the demographic, diagnosed-based, and prior-utilization variables are constructed. The model predicted the lung cancer-related medical expenditure with high accuracy of 32.63%, 50.30%, 50.36%, and 66.58%, respectively for stages 1-4, as compared with the reported models. A greedy search was also applied to find the upper threshold of R2, while our model also shows that it approached the upper threshold.