Neurosurgery· 2026Q1
Automated Case Logging for Surgical Residency Training Using the Electronic Health Record: A Pilot Study
- 0citations
- Q1SCImago
- 2026year
Short summary
An automated system extracted 94.8% accurate neurosurgery case logs from EHRs, reducing logging time by 66% (68.4s/case vs. 199.9s/case) and saving residents 58 hours over 5 years.
AI-generated from the title and abstract; the full text is not read.
Key points
- Automated EHR extraction achieved 94.8% accuracy in logging neurosurgery cases compared to manual methods.
- Reviewing automated logs took an average of 68.4 seconds per case, a 66% reduction from manual logging (199.9 seconds).
- The system is projected to save neurosurgery residents 58 hours over 5 operative years.
- Automated logging demonstrated 98.9% precision and 95.8% sensitivity.
AI-generated from the title and abstract; the full text is not read.
Abstract
BACKGROUND AND OBJECTIVES: Case logging is essential for competency-based evaluation in residency but requires manual entry, which is susceptible to error, leading to delayed submission and underreporting. We present a novel, fully automated electronic health record (EHR)-integrated platform that extracts data from clinical documentation and logs it into the Accreditation Council for Graduate Medical Education (ACGME) case log system. We aim to evaluate the feasibility and effectiveness of an automated EHR extraction and case-logging system linked to the ACGME. METHODS: We evaluated case logs from 20 residents (post-graduate year 1-7) at an academic neurosurgery department from June to September 2025. Automated case logs were extracted from our digital EHR data warehouse, current procedural terminology codes were mapped to procedure code IDs, and residents verified automated logs before ACGME transmission. Manual case logs were extracted from operative reports in Epic by 2 staff members for comparison. Accuracy, precision, and sensitivity were assessed by comparing automated logs against manual logs. Time savings was estimated by comparing manual and automated per case-logging time across clinical residency years. RESULTS: A total of 1977 cases were automatically pulled compared with 2041 cases pulled from manual chart review. After review by each resident, 1955 of the automatically pulled cases were correctly logged and categorized when compared with manual cases (94.8% accuracy), with a 98.9% precision and 95.8% sensitivity. Traditional self-reported case logging took, on average, 199.9 ± 99.1 seconds per case. In comparison, reviewing and confirming automated case logs required an average of 68.4 ± 75.1 seconds per case. Per ACGME case minimums, automated logging reduced time by 66%, saving a neurosurgical resident 58 hours over the course of 5 operative, clinical years. CONCLUSION: Automated case logs provide an accurate, time-effective tool that can reduce administrative burden. Future studies should evaluate how to further improve and broaden the application of automated case logs to other specialties.
The authors' abstract, as published at the source. Neurosurgery, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Health Information Management
Health Information ManagementHealth Professions