Healthcare staff acceptance and satisfaction with automated medication dispensing cabinets: a neural network-based analysis.

BACKGROUND

The Automated Dispensing Cabinets (ADCs) represent one of the most widely deployed forms of technology integrated with today's medication-use systems. Despite the rise of ADC use and subsequent benefits, research exploring the impacts of ADCs on staff acceptance and satisfaction is still relatively limited and not thoroughly investigated. The present study aims to address this by assessing the impact of ADC implementation on healthcare staff satisfaction.

METHODS

This cross-sectional study was conducted in Almoosa Specialist hospital, Al-Ahsa, KSA, involving 203 healthcare staff participants selected through a convenience sampling approach considering the busy and tough schedule of staff. The questionnaire, named ADC User Acceptance Survey (ADC-UAS), was developed using a 10-item scale designed to measure Perceived Ease of Use (PEOU), Perceived Usefulness (PU), and Behavioral Intention to Use ADCs. This instrument employed a 7-point Likert scale and was based on the Modified Technology Acceptance Model (TAM). Pearson's correlation was computed to investigate the correlation between demographic and TAM factors. The Artificial Neural Network (ANN) model was applied to assess the influential factors, and results were declared statistically significant if p < 0.05.

RESULTS

Out of 203 healthcare professionals, the majority were nurses (82.8%) and females (86.7%), with a mean age of 31.94 ± 5.96 years. The findings demonstrated high ADC acceptance and satisfaction, with 87.2% of participants reporting improved efficiency and 92.1% acknowledging enhanced patient safety. The strong positive relationship between current unit experience and acceptance (r = 0.304, p = 0.000) showed that individuals with more experience in their current unit are more likely to accept the system. Acceptance of ADC was significantly correlated with its usefulness (r = 0.820, p = 0.000). Positive correlation was also observed between professional experience and the perceived usefulness of the system (r = 0.144, p = 0.040). The result of the ANN model identified professional experience (100%), current unit experience (99.9%), and automation experience (97.8%) as the strongest predictors of ADC acceptance.

CONCLUSION

The study revealed high acceptance and satisfaction with ADCs among Almoosa healthcare staff, emphasizing that these systems make work more manageable and efficient. Given the high levels of acceptance and satisfaction among healthcare professionals regarding ADCs, it is recommended that healthcare facilities continue to invest in and expand the use of ADC systems.