Location
Online
Event Website
https://hicss.hawaii.edu/
Start Date
3-1-2023 12:00 AM
End Date
7-1-2023 12:00 AM
Description
We aimed to explore the patterns of electronic medical records (EMR) adoption and its effects on hospital performance. We analyzed hospital-level panel data from 2008 to 2013 using Bayesian regression and the Naïve Bayes model. Our research analysis revealed 38 different adoption patterns for 1,919 hospitals that completed EMR implementation (having all of the four components) and 42 different investment patterns for 1,341 hospitals that could not complete the EMR implementation. We examined the hospitals’ EMR adoption patterns that were not completed; but predicted as completed using the Naïve Bayes model. Our results revealed that the hospitals that completed EMR adoption showed higher performance in terms of patient recommendation and net patient revenue than those that did not complete EMR adoption. More importantly, most of hospitals that observed as “not completed” but predicted as “completed” showed lower performance in terms of patient recommendation as well as net patient revenue.
Recommended Citation
Lee, Joonghee; Kim, Jin Sik; and Shin, Soo Il, "Does the Electronic Medical Record (EMR) Adoption Matter? Exploring Patterns of EMR Implementation and its Impact on Hospital Performance" (2023). Hawaii International Conference on System Sciences 2023 (HICSS-56). 5.
https://aisel.aisnet.org/hicss-56/hc/adoption/5
Does the Electronic Medical Record (EMR) Adoption Matter? Exploring Patterns of EMR Implementation and its Impact on Hospital Performance
Online
We aimed to explore the patterns of electronic medical records (EMR) adoption and its effects on hospital performance. We analyzed hospital-level panel data from 2008 to 2013 using Bayesian regression and the Naïve Bayes model. Our research analysis revealed 38 different adoption patterns for 1,919 hospitals that completed EMR implementation (having all of the four components) and 42 different investment patterns for 1,341 hospitals that could not complete the EMR implementation. We examined the hospitals’ EMR adoption patterns that were not completed; but predicted as completed using the Naïve Bayes model. Our results revealed that the hospitals that completed EMR adoption showed higher performance in terms of patient recommendation and net patient revenue than those that did not complete EMR adoption. More importantly, most of hospitals that observed as “not completed” but predicted as “completed” showed lower performance in terms of patient recommendation as well as net patient revenue.
https://aisel.aisnet.org/hicss-56/hc/adoption/5