[IMDS] Beyond adoption: data-driven insights into how EMR implementation sequences shape hospital outcomes (Copy)

Kim, J. S., Lee, J., Shin, S. I., & Sneha, S. (2025). Beyond adoption: data-driven insights into how EMR implementation sequences shape hospital outcomes. Industrial Management & Data Systems, pp.1-30.

https://doi.org/10.1108/IMDS-01-2024-0019

This study examines the implementation patterns of electronic medical records (EMR) and their impact on hospital performance, with particular attention to both the completion of adoption and the sequencing of component deployment. Using a longitudinal dataset of U.S. hospitals spanning 2008 to 2017, we employ a Naïve Bayes classification model in conjunction with Euclidean distance analysis to identify, validate, and evaluate distinct EMR adoption patterns. The results reveal false-positive classifications in hospitals initially labeled as having fully adopted EMR. For these cases, Bayesian regression analysis provides statistical evidence in support of the immediate adoption of remaining components. Furthermore, we propose pattern-specific adoption strategies tailored to hospital characteristics, demonstrating that these strategies are associated with potential performance improvements, including increased net patient revenue and higher discharge volumes. By moving beyond a binary perspective of adoption status to focus on the manner of adoption, this study offers robust empirical evidence that hospital performance outcomes are contingent upon specific EMR adoption patterns, thereby delivering actionable insights for healthcare administrators, policymakers, and scholars seeking to design more effective EMR implementation strategies.

#EMR #ElectronicMedicalRecords #EMRAdoptionPatterns #HospitalPerformance #NaiveBayesClassifier #EuclideanDistanceAnalysis #BayesianRegression #HealthcareITStrategy #longitudinaldata #HealthcareInformationSystems