Development of an electronic patient safety surveillance model to efficiently identify potential adverse events for gastrointestinal endoscopies.

Sullivan BA, Foster MV, Hwang A, Sturgeon DJ, Kit L, Hayward-Lundy SH, Lamkin RP, Redd A, Friedman HR, Mull HJ. Development of an electronic patient safety surveillance model to efficiently identify potential adverse events for gastrointestinal endoscopies. Gastrointestinal endoscopy. 2026 Jan 1; 103(1):60-70.e22, DOI: 10.1016/j.gie.2025.04.033.

Related HSR&D Project(s)

• IIR 18-034 – How Can We Make Invasive Non-Surgical Procedures Safer? Using Big Data to Identify Adverse Events and Opportunities to Mitigate Harm

Dimensions for VA is a web-based tool available to VA staff that enables detailed searches of published research and research projects.

If you have VA-Intranet access, click here for more information vaww.hsrd.research.va.gov/dimensions/

VA staff not currently on the VA network can access Dimensions by registering for an account using their VA email address.    Search Dimensions for VA for this citation
* Don't have VA-internal network access or a VA email address? Try searching the free-to-the-public version of Dimensions

Search for Abstract from PubMed

---

Abstract:

BACKGROUND AND AIMS: Tracking of adverse events (AEs) after GI endoscopy is endorsed by guideline committees yet remains challenging in practice. Our aim was to develop and validate an electronic surveillance model to systematically identify outpatient endoscopies with a likely AE. METHODS: We evaluated outpatient GI procedures across the Veterans Health Administration. We defined endoscopy-related AEs and reviewed a sample of charts with and without electronic trigger flags (eg, emergency department visit) for possible AEs from 2018 to 2020 to develop a surveillance model using relevant patient, procedure, and facility factors. The model''s optimal threshold for flagging potential AEs was determined to maximize performance characteristics. A second independent chart review was conducted from 2021 to 2022 to validate the model at this threshold. RESULTS: We reviewed the chart of 1085 cases (317 AEs) of 484,520 outpatient GI procedures for model development and 297 cases (167 AEs) of 20,849 procedures for model validation. At the optimal "AE flag" threshold, the model flagged 1.2% of all GI endoscopies with a potential AE. In the validation sample, the positive predictive value and false-negative rate were 69.6% and 26.0%, respectively. CONCLUSIONS: This electronic AE surveillance model can efficiently identify outpatient GI endoscopy cases with a high likelihood of patient harm to complement existing strategies for AE monitoring. Additionally, this methodology demonstrates flexibility to either maximize AE identification or minimize chart review burden by changing the "AE flag" threshold. Such tools should enhance quality improvement opportunities, patient safety, and understanding of AEs in routine GI endoscopy.