Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1141
version: 2
kind: revised
reason: Direction audit: filed as a problem but describes a gain.
timestamp: 2026-10-26T06:38:44.082501Z
status: published
lens: g_space
sector: health
headline: Large Language Model Data Abstraction Demonstrates Accuracy and Reliability for NSQIP
dek: Background National Surgical Quality Improvement Program (NSQIP) data collection depends on labor-intensive manual chart abstraction, limiting efficiency, increasing cost, and necessitating patient sampling. This study evaluated whether a large language model (LLM) could accurately abstract unstructured NSQIP breast reconstruction variables compared with conventional human abstraction. Study design Clinical notes from patients enrolled in the NSQIP Breast Reconstruction pilot program (July 1, 2024-February 28, 2…
gain_title: A customized ChatGPT 4.1 workflow abstracted NSQIP surgical records with 99.33% accuracy versus 98.19% for human abstraction, beating the human baseline.
problem_title: (none)
trace_subject: (none)
gain_reading: A customized ChatGPT 4.1 workflow abstracted NSQIP surgical records with 99.33% accuracy versus 98.19% for human abstraction, beating the human baseline.
gain_evidence: (none)
problem_reading: (none)
problem_evidence: (none)
quick_read: Background National Surgical Quality Improvement Program (NSQIP) data collection depends on labor-intensive manual chart abstraction, limiting efficiency, increasing cost, and necessitating patient sampling. This study evaluated whether a large language model (LLM) could accurately abstract unstructured NSQIP breast reconstruction variables compared with conventional human abstraction.

Study design Clinical notes from patients enrolled in the NSQIP Breast Reconstruction pilot program (July 1, 2024-February 28, 2025) were manually de-identified and processed using a customized ChatGPT 4.1 workflow targeting individual variables. Overall accuracy of LLM and human abstraction was compared using McNemar's and Chi-square tests.
limitation: 
tag: Evidence-backed gain
key_points: Background National Surgical Quality Improvement Program (NSQIP) data collection depends on labor-intensive manual chart abstraction, limiting efficiency, increasing cost, and necessitating patient sampling. | This study evaluated whether a large language model (LLM) could accurately abstract unstructured NSQIP breast reconstruction variables compared with conventional human abstraction. | Study design Clinical notes from patients enrolled in the NSQIP Breast Reconstruction pilot program (July 1, 2024-February 28, 2025) were manually de-identified and processed using a customized ChatGPT 4.1 workflow targeting individual variables.
rundown: Background National Surgical Quality Improvement Program (NSQIP) data collection depends on labor-intensive manual chart abstraction, limiting efficiency, increasing cost, and necessitating patient sampling. This study evaluated whether a large language model (LLM) could accurately abstract unstructured NSQIP breast reconstruction variables compared with conventional human abstraction.

Study design Clinical notes from patients enrolled in the NSQIP Breast Reconstruction pilot program (July 1, 2024-February 28, 2025) were manually de-identified and processed using a customized ChatGPT 4.1 workflow targeting individual variables. A faculty plastic surgeon established the reference standard.
sources:
- peer_reviewed | Journal of the American College of Surgeons | https://doi.org/10.1097/xcs.0000000000002211 | 2026-09-18
prev: 05bacd8da620b511effe4805c9bd18ed6496dd81647e893fa0a4c2a33a3bf9b4

sha256

e53b58eb809449000852a2e04f22a8230a4a07a8528211aa2a7596d6de2f3eb4

previous

05bacd8da620b511effe4805c9bd18ed6496dd81647e893fa0a4c2a33a3bf9b4