Beyond adoption: data-driven insights into how EMR implementation sequences shape hospital outcomes

Research output: Contribution to journalArticlepeer-review

Abstract

Our study investigates the observable patterns related to the implementation of electronic medical records (EMR) and their subsequent effects on hospital performance. We conducted a comprehensive analysis utilizing longitudinal hospital-level data from 2008 to 2017, employing the Naïve Bayes Model and Euclidean distance approaches. We identified false-positive cases among hospitals initially classified as having completed EMR adoption. And, we found all the possible EMR adoption patterns using the Naïve Bayes Model. We provide statistical evidence supporting immediate EMR component adoption for these cases. We also suggest more effective EMR adoption patterns based on the characteristics of hospitals and find that the recommended patterns yield a potential increase in hospital performance in terms of net patient revenue and the number of discharges. Our analysis revealed that there were differences in hospital performance depending on the specific EMR adoption patterns they followed. This study offers substantial evidence and rationale to academia and practitioners, emphasizing not only the importance of complete EMR adoption but also the manner in which EMR adoption is executed.
Original languageEnglish
Pages (from-to)1
Number of pages30
JournalIndustrial Management & Data Systems
DOIs
StatePublished - Aug 6 2025

ASJC Scopus Subject Areas

  • Management Information Systems
  • EMR adoption Patterns
  • Naïve Bayes model
  • Electronic medical records

Keywords

  • Healthcare information technology
  • Electronic medical records
  • EMR adoption patterns
  • Naïve Bayes model

Fingerprint

Dive into the research topics of 'Beyond adoption: data-driven insights into how EMR implementation sequences shape hospital outcomes'. Together they form a unique fingerprint.

Cite this