A novel clinical decision support algorithm for constructing complete medication histories. (July 2017)

• Record Type: Journal Article
• Authors: Long, Ju; Yuan, Michael Juntao
• Is Part Of: Computer methods and programs in biomedicine. Volume 145(2017)
• Page Start: 127
• Page End: 133
• Publication Date: 2017-07
• Subjects: Medication history -- Clinical decision support algorithm -- Medication consolidation -- Medication management; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2017.04.004
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We describe an accurate, computationally efficient, and scalable algorithm to construct the medication history timeline. The algorithm is validated based on 1 million random prescription records. The algorithm is suitable for delivery in a cloud-computing environment. The cloud-based medication history computation service could potentially be integrated into electronic medical records. The algorithm could potentially enable informed clinical decision making at the point of care. Abstract: A patient's complete medication history is a crucial element for physicians to develop a full understanding of the patient's medical conditions and treatment options. However, due to the fragmented nature of medical data, this process can be very time-consuming and often impossible for physicians to construct a complete medication history for complex patients. In this paper, we describe an accurate, computationally efficient and scalable algorithm to construct a medication history timeline. The algorithm is developed and validated based on 1 million random prescription records from a large national prescription data aggregator. Our evaluation shows that the algorithm can be scaled horizontally on-demand, making it suitable for future delivery in a cloud-computing environment. We also propose that this cloud-based medication history computation algorithm could be integrated into Electronic Medical Records, enabling informed clinical decision-making at the point of care.