Court Judgment Decision Support System Based on Medical Text Mining

Zhu, Qing and Wei, Kezhen and Ding, Lanlin and Lai, Kin Keung Kin Keung (2017) Court Judgment Decision Support System Based on Medical Text Mining. Wuhan International Conference on e-Business.

[img]
Preview
Text
Court Judgment Decision Support System Based on Medical Text Mini.pdf

Download (556kB) | Preview

Abstract

Medical damage is a common problem faced by hospitals around the world and is widely watched by countries and the World Health Organization. As the number of medical damage dispute lawsuit cases rapidly grows, many countries in the world face the problem how to improve the efficiency of the judicial system under the premise of guaranteeing the quality of the trial. Therefore, in addition to reforming the system, the decision support system will effectively improve judicial decisions. This paper takes medical damage judgment documents in China as example, and proposes a court judgment decision support system (CJ-DSS) based on medical text mining and the automatic classification technology. The system can predict the trail results of the new lawsuit documents according to the previous cases verdict - rejected and non-rejected. Combined with the cases, the study in this paper found that combined feature extraction method does improve the performance of three kinds of classifiers - Support Value Machine (SVM), Artificial Neural Network (ANN) and K-Nearest Neighbor (KNN), the degree of improved performance is different from using DF-CHI combined feature extraction method. In addition, integrated learning algorithm also improves the classification performance of the overall system.

Item Type: Article
Subjects: R Medicine > R Medicine (General)
T Technology > T Technology (General)
Divisions: Faculty of Industrial Engineering and Informatics > Information System
Depositing User: staff repository 1
Date Deposited: 20 Aug 2018 13:57
Last Modified: 20 Aug 2018 13:57
URI: http://repository.ittelkom-pwt.ac.id/id/eprint/3787

Actions (login required)

View Item View Item