The Use of Big Data and Efficiency in Pharmaceutical Dispensing

An optimized technique has been developed that determines prescribed medication associations within a high-volume pharmacy environment, reducing costs, saving time, and improving the management of medication inventories.

A study published in Expert Systems With Applications noted automated pharmacies are confronted with growing demands for prescription orders, including at central fill pharmacies distributing drugs to retail pharmacies. As a result, stakeholders must increase the output of prescriptions in automated pharmacies via the Robotic Prescription Dispensing System (RPDS).

The study noted numerous pharmacies ignore hidden patterns and knowledge that can be found in a transactional database.

“In this research, we applied big-data analytics to enhance the efficiency of pharmacy automation and management by finding different rules and patterns of subscribed medications,” said researcher Sang Won Yoon. “Additionally, we can apply this research to both enhance pharmacy automation and management, and to help us understand patients' medication adherence and compliance issues in the future.”

The study addressed the issues that automated pharmacies are beginning to face regarding the high demand of prescription orders through the RPDS.

To enhance the efficiency of pharmacy automation and management, researchers applied big-data analytics by finding different patterns of medications.

“We can apply this research to both enhance pharmacy automation and management, and to help us understand patients' medication adherence and compliance issues in the future,” Yoon said.

The researchers concluded that the growth in the use pharmacy services requires new approaches to meet the growing demand.

“The work published in this paper provides a great example of how industry and academia can work together to solve complex real-life challenges,” said Mohammad Khasawneh. “Our partnership with Innovation, a leader in pharmacy automation, provides our graduate students and faculty with great opportunities to test some of their newly developed algorithms. In addition to accomplishing significant return on investment for our industry partners, collaborative efforts like this are indeed critical to our educational mission at the university.”