Outcomes of an Advanced Epic Personalization Course on Clinician Efficiency through Use of Electronic Medical Records: Retrospective Study
Bibliographic record
Abstract
Background: Since Singapore's first migration to Epic in 2022, we have been conducting an advanced Epic personalization course twice a year for health care professionals with at least 3 months of experience using the system. Electronic medical records education is an under-recognized pillar in reducing health information technology-related stress and clinician burnout. Objective: The intent of the course is to improve clinician efficiency through customization and personalization of Epic interfaces. We hypothesized that compared to their colleagues, trained clinicians would demonstrate significant quantitative improvements in use of the Epic system after our course. Methods: We performed a retrospective analysis from July 2022 to January 2024, including 17 clinicians among 77 individuals who attended our course. Recruitment was done through digital mailers sent out via the local hospital announcement channels. Interested clinicians were able to register for our course via the National University Of Singapore website. Our one-day course involves physical lessons and interprofessional, case-based discussions emphasizing a wide range of high-yield Epic functionalities with practice exercises, such as drafting referral letter templates. Three months of pre- and postcourse Epic usage statistics of the trained clinicians were retrieved based on aggregate data provided by Epic Singapore. Performance metrics included documentation length, time spent in Epic functionalities and use of SmartPhrases, order sets and preference lists. Results: At three months post-course, documentation length decreased by 45.8% (711.8 characters) compared to a 22.2% (126.4 characters) increase among controls. Trained clinicians demonstrated a 2.47-fold increase in use of order sets from 16.2% to 40%, and a 49.9% increase in orders from preference lists after the course, from 35.1% to 52.6%. In total, trained clinicians demonstrated a 1.8-fold increase in combined use of orders from preference lists or order sets after the course, from 51.4% to 92.6%. The number of SmartPhrases created by trained clinicians was 5.64 times higher than among controls, in addition to a 5.57-fold higher use of Quick Filters than controls. Moreover, time in the Chart Review section per day decreased by 29.3% (4.6 min) among trained clinicians versus an increase of 14.6% (2.8 min) among controls. Compared to controls, trained clinicians spent 36.7% (219.6 min) less time in the Epic system per day, 56.6% (29 min) less time on Notes per day, and 57.5% (10.7 min) less time on orders per day. Conclusions: Overall, trained clinicians demonstrated more efficiency in their use of Epic, with reduced time spent across various functionalities. Increased use of Smart Tools, including SmartPhrases and Quick Filters was also observed among trained clinicians, which indicated efficiency in reducing total usage time. These findings demonstrated broad improvements across multiple physician efficiency metrics among participating clinicians of our advanced Epic personalization course. These gains may contribute to improved mental health among health care professionals and enhanced productivity within health care systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".