A vector space model for automatic indexing
Communications of the ACM
Computational information retrieval
Computational information retrieval
Distributional term representations: an experimental comparison
Proceedings of the thirteenth ACM international conference on Information and knowledge management
Tensor Decompositions and Applications
SIAM Review
Hi-index | 0.00 |
This paper addresses the task of analyzing healthcare data for medical decision making. We describe a method for ranking medications based on historical data of the outcomes recorded as part of a system of Electronic Medical Records (EMR). Medication ranking can be used to recommend medications for a given group of diagnoses. The ranking process captures the effects of medication and subsequent diagnoses. We used longitudinal electronic medical records of five test patients for the purpose of this study. More than 5000 medical visit documents are analyzed and the medication and diagnosis information are extracted to create a vector space model. The resulting matrix ranked 167 medications and 187 problems. This is designed to enable the decision making capabilities within EMRs. Similar approaches can be used to provide decision support towards preventive medication.