Fiche du document
1 août 2016
- handle: 10670/1.rkaohx
- hal: hal-01646565
- doi: 10.1007/978-3-319-42102-5_17
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-319-42102-5_17
http://creativecommons.org/licenses/by/ , info:eu-repo/semantics/OpenAccess
Sujets proches
Complications and sequelae Group dynamics Association Groups, Social illnessCiter ce document
Zhijun Yan et al., « A Study of Complication Identification Based on Weighted Association Rule Mining », HAL-SHS : sciences de l'information, de la communication et des bibliothèques, ID : 10.1007/978-3-319-42102-5_17
Métriques
Partage / Export
Résumé
With the fast development of big data technology, data mining algorithms are widely used to process the medical data and support clinical decision-making. In this paper, a new method is proposed to mine the disease association rule and predict the possible complications. The concept of disease concurrent weight is proposed and Back Propagation (BP) neural network model is applied to calculate the disease concurrent weight. Adopting the weighted association rule mining algorithm, diseases complication association rule are derived, which can help to remind doctors about patients’ potential complications. The empirical evaluation using hospital patients’ medical information shows that the proposed method is more effective than two baseline methods.