Implementation of distributed automated medication dispensing units in a new hospital: Nursing and pharmacy experience

Innovation in hospital pharmacy: Modeling the installation of automated dispensing systems based on an oncology hospital experience transfer

OBJECTIVE

This study explores automated dispensing systems (ADS) implementation in hospitals, focusing on experience transfer between the National Institute of Oncology of Rabat (NIO) and the specialties hospital of Rabat (SHR) to develop a transferable ADS installation and management model.

METHOD

A retrospective implementation and experience data analysis of 3 years ADS implementation at NIO and a prospective planification for SHR new implementation on 6 months were employed. Data collection included pharmacist team reports, personnel interviews, direct observations, and information system data exports. The study focused on identifying challenges a plan-do-check-act (PDCA) cycle.

RESULTS

The analysis revealed overestimation in ADS needs at NIO about 42%, leading to: Resource exhaustion; Challenges in timeline installation staff training and management, Disruptions in data integration and Incident Reports. These issues underscored the importance of a phased, well-planned implementation process.

DISCUSSION

The study highlighted the crucial role of many comprehensive strategies. In accordance with the results of several studies, this work demonstrates the benefits of ADS in reducing medication errors and enhancing resource management, while also pointing out the necessity for accurate system sizing, effective integration with hospital information systems, and comprehensive staff training.

CONCLUSION

The experience transfer between NIO and SHR provides a valuable model for ADS implementation in hospital pharmacies, proposing optimizations on: Implementation process; Timelines and mapping; Risk management and incident reports; Staff training, sensibilization and change control.

Pill Detection Model for Medicine Inspection Based on Deep Learning

This paper proposes a deep learning algorithm that can improve pill identification performance using limited training data. In general, when individual pills are detected in multiple pill images, the algorithm uses multiple pill images from the learning stage. However, when there is an increase in the number of pill types to be identified, the pill combinations in an image increase exponentially. To detect individual pills in an image that contains multiple pills, we first propose an effective database expansion method for a single pill. Then, the expanded training data are used to improve the detection performance. Our proposed method shows higher performance improvement than the existing algorithms despite the limited imaging and data set size. Our proposed method will help minimize problems, such as loss of productivity and human error, which occur while inspecting dispensed pills.