The Evaluation of Occupational Injuries in Length-of-Stay
碩士 === 國立雲林科技大學 === 工業工程與管理研究所碩士班 === 100 === The Bureau of National Health Insurance pays for hospitalization costs. The cost of in-patient treatment is expensive and costly for the Bureau of National Health and for hospitals. If in-patient treatment could be reduced, it would positively affect t...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2012
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/52114749255657054080 |
| Summary: | 碩士 === 國立雲林科技大學 === 工業工程與管理研究所碩士班 === 100 === The Bureau of National Health Insurance pays for hospitalization costs. The cost of in-patient treatment is expensive and costly for the Bureau of National Health and for hospitals. If in-patient treatment could be reduced, it would positively affect the balance of payment problems hospitals face. Reducing the number of unnecessary hospitalizations is an important issue. This study used C5.0 decision tree, back-propagation neural network and support vector machine (SVM) to assess the length of hospital stays. The purpose of this study was to reduce the number errors of actual injuries requiring hospitalization and avoiding unnecessary hospitalizations. The SVM provided the best results with an accuracy rate of 90.98%. Our results show that SVM have good predictability.
|
|---|