Big data analysis techniques to address polypharmacy in patients - a scoping review

Area of Science:

• Health Informatics
• Computational Medicine
• Data Science in Healthcare

Background:

• Polypharmacy, the concurrent use of multiple medications, poses a significant challenge in healthcare, particularly for elderly and multimorbid patients.
• It increases the risk of adverse drug interactions and the prescription of potentially inappropriate medications.
• eHealth solutions, especially those leveraging big data analysis, are increasingly recognized for their potential to address these issues.

Purpose of the Study:

• To review existing big data analysis techniques for identifying patients with polypharmacy.
• To evaluate the potential of these techniques in reducing polypharmacy.
• To explore the application of computational analysis of large datasets in managing complex medication regimens.

Main Methods:

• A systematic literature search was conducted across PubMed, Web of Science, and Cochrane Library databases (February 2019, updated May 2020).
• Studies evaluating big data analytics for patients with multiple drug use were included.
• Data extraction was performed by two independent researchers following a standardized protocol.

Main Results:

• Out of 327 identified studies, only three specifically addressed big data analysis techniques in the context of polypharmacy.
• These studies included analyses of antipsychotic polypharmacy, a decision support system for side-effect evaluation, and a system for identifying polypharmacy-related problems.
• The limited number of studies highlights a gap in current research.

Conclusions:

• Current research on using big data analysis for polypharmacy identification and management is scarce.
• There is a need for enhanced interdisciplinary collaboration between computer scientists and healthcare professionals.
• Developing and evaluating robust big data analysis techniques is crucial for effective polypharmacy management.