A diagnosis model for survivability and medical expenditure of lung cancer patient by Conditional Gaussian Bayesian networks

碩士 === 國立臺灣科技大學 === 工業管理系 === 106 === In Taiwan, the statistics of the Ministry of Health and Welfare indicated lung cancer is the leading cause of cancer. About 10,000 new cases of lung cancer each year, which caused more than 7,000 people dead in 2016. In addition, lung cancer usually accompanied...

Full description

Bibliographic Details
Main Authors: Wan-Ping Chen, 陳婉平
Other Authors: Kung-Jeng Wang
Format: Others
Language:zh-TW
Published: 2018
Online Access:http://ndltd.ncl.edu.tw/handle/sqn4ey
Description
Summary:碩士 === 國立臺灣科技大學 === 工業管理系 === 106 === In Taiwan, the statistics of the Ministry of Health and Welfare indicated lung cancer is the leading cause of cancer. About 10,000 new cases of lung cancer each year, which caused more than 7,000 people dead in 2016. In addition, lung cancer usually accompanied with comorbidity which was negatively associated with survival and leaded to medical financial burden. This study used National Health Insurance Research Database from 1996 to 2010 who diagnosed lung cancer, and 85,745 cases were selected as experiment data. By using Kaplan-Meier estimation to get residual life of patient and used risk factors to construct Conditional Gaussian Bayesian network model of survivability and medical expenditure. The prediction R-square of survivability in stage I is 69.50%, stage II is 73.75%. The prediction R-square of medical expenditure in stage I is 93.95%, stage II is 74.77%. And proposed model not only can predict survivability and medical expenditure, but also can calculate the posterior probability of variety of medical related query.