EHR Adoption and Hospital Performance: Time-Related Effects

Abstract

Objective: To assess whether, 5 years into the HITECH programs, national data reflect a consistent relationship between EHR adoption and hospital outcomes across three important dimensions of hospital performance.

Data sources/study setting: Secondary data from the American Hospital Association and CMS (Hospital Compare and EHR Incentive Programs) for nonfederal, acute-care hospitals (2009-2012).

Study design: We examined the relationship between EHR adoption and three hospital outcomes (process adherence, patient satisfaction, efficiency) using ordinary least squares models with hospital fixed effects. Time-related effects were assessed through comparing the impact of EHR adoption pre (2008/2009) versus post (2010/2011) meaningful use and by meaningful use attestation cohort (2011, 2012, 2013, Never). We used a continuous measure of hospital EHR adoption based on the proportion of electronic functions implemented.

Data collection/extraction methods: We created a panel dataset with hospital-year observations.

Principal findings: Higher levels of EHR adoption were associated with better performance on process adherence (0.147; p < .001) and patient satisfaction (0.118; p < .001), but not efficiency (0.01; p = .78). For all three outcomes, there was a stronger, positive relationship between EHR adoption and performance in 2010/2011 compared to 2008/2009. We found mixed results based on meaningful use attestation cohort.

Conclusions: Performance gains associated with EHR adoption are apparent in more recent years. The large national investment in EHRs appears to be delivering more consistent benefits than indicated by earlier national studies.

Keywords: Health care organizations and systems; hospitals; information technology.

Figure 1

Predicted Standardized Outcomes for Average EHR Adoption among Hospitals with Less Than Basic EHR and At Least Basic EHR

1. Notes: Outcome values are predicted at 0.42 and 0.77 on our EHR adoption scale (the average of hospitals with less than basic EHR and at least basic EHR, respectively), with all control variables set at their mean.