A Collaborative Filtering Approach to Medication Reconciliation

Citation:

A physician’s prescribing decisions depend on knowledge of the patient’s medication list. This knowledge is often incomplete, and errors or omissions could result in adverse health outcomes. To address this problem, the Joint Commission on the Accreditation of Healthcare Organizations recommends medication reconciliation for creating a more accurate list of a patient’s medications. This paper describes techniques for automatic detection of omissions in medication lists, identifying drugs that the patient may be taking but are not on the patient’s current medication list. The key insight is that this problem is analogous to the collaborative filtering framework increasingly used by online retailers to recommend relevant products to customers. The collaborative filtering approach enables a variety of solution techniques, including nearest neighbor, co- occurrence, and logistic regression approaches.The effectiveness of these approaches using medication data from three long-term care centers in the Eastern United States is evaluated. Preliminary results suggest that this framework may become a valuable tool for medication reconciliation.
 

• View Full Text (.pdf)

Adobe .pdf files require the Adobe Acrobat Reader.
Download and install the Adobe Acrobat Reader.