Other Titles
Enhancing Patient Safety with AI-Enhanced Anesthesia Eligibility Screening [Title Slide]
Abstract
Accurate screening for anesthesia eligibility criteria is crucial for pediatric ambulatory surgery centers (ASCs) to ensure patient safety and optimization of resources [1,3]. Traditional manual chart review by advanced practice providers (APPs) is labor-intensive and subject to variability [2, 3, 7]. Continued growth of the ASC patient volume creates challenges for the APP team to meet the patient safety needs without adding additional support. To address these challenges, we partnered with Brim Analytics (Brim), an Artificial Intelligence (AI) powered chart review tool built on a large language model. Brim interprets unstructured electronic medical record (EMR) data and applies our institutional ASC anesthesia criteria to flag cases that may require a higher level of care.
This retrospective observational validation study analyzed 2,158 pediatric patients scheduled for ASC anesthesia. For each case, Brim’s model returned a binary output: true or false, "Should this patient be rescheduled to the main campus?" These outputs were compared to the expert APP determinations across seven monthly validation cycles. Misclassification analysis informed iterative variable refinement, including adjustments for ambiguous shorthand, time-limited illness criteria, and differentiation of pertinent negatives from past medical history. Accuracy improved from 68% in the initial month cycle to 81%, then 96% before stabilizing at 98-99% alignment with clinician determinations over subsequent cycles, reflecting strong reliability.
Our findings underscore the importance of human-in-the-loop systems and continuous algorithm refinement for safe AI integration [5, 6, 8]. Brim offers a scalable decision-support tool to assist in ASC patient chart review to reduce manual workload, improve surgery scheduling practices, and enhance patient safety. While the goal of AI is not to replace the mandated APP clinical review, it can provide a smart assist to flag high-risk cases, improving efficiency and access to surgical care. Future research should evaluate prospective clinical implementation, workflow impact, and clinician trust to ensure ethical and effective adoption [3, 4, 8].
Notes
Presenter notes available in attached slide deck. To see the notes in Adobe Acrobat, go to Tools > Comment or look at your Layers Panel. If the notes were saved as comments or layers, you can toggle them visible.
References:
1. Bellini, V., Valente, M., Bertorelli, G., Pifferi, B., Craca, M., Mordonini, M., Lombardo, G., Bottani, E., Del Rio, P., & Bignami, E. (2022). Machine learning in perioperative medicine: a systematic review. Journal of Anesthesia, Analgesia and Critical Care, 2(1). https://doi.org/10.1186/s44158-022-00033-y
2. Lee, C., Vogt, K. A., & Kumar, S. (2024). Prospects for AI clinical summarization to reduce the burden of patient chart review. Frontiers in Digital Health, 6, 1–9. https://doi.org/10.3389/fdgth.2024.1475092
3. Maheshwari, K., Cywinski, J. B., Papay, F., Khanna, A. K., & Mathur, P. (2022). Artificial Intelligence for perioperative medicine: Perioperative Intelligence. Anesthesia & Analgesia, 136(4), 637–645. https://doi.org/10.1213/ane.0000000000005952
4. Ngiam K Y, & Khor I W. (2019). Big data and machine learning algorithms for health-care delivery. The Lancet Oncology, 20, e262–273. https://doi.org/10.1016/s1470-2045(19)30149-4
5. Patel M, & Nanji K C. (2025). Artificial Intelligence in perioperative medication-related clinical decision support. Anesthesiology Clinics, 43(3), 587–602. https://doi.org/10.1016/j.anclin.2025.05.009
6. Robinson J R, Stey A, Schneider D F, Kothari A N, Lindeman B, Kaafarani H M, & Haines K L. (2025). Generative Artificial Intelligence in academic surgery: Ethical implications and transformative potential. Journal of Surgical Research, 307. https://doi.org/10.1016/j.jss.2024.12.059
7. Siems A, Banks R, Holubkov R, Meert K L, Bauerfeld C, Beyda D, Berg R A, Bulut Y, Burd R S, Carcillo J, Dean J M, Gradidge E, Hall M W, McQuillen P S, Mourani P M, Newth C J L, Notterman D A, Priestley M A, Sapru A, & Wessel D L. (2020). Structured Chart Review: Assessment of a Structured Chart Review Methodology. Hospital Pediatrics, 10(1), 61–69. https://doi.org/10.1542/hpeds.2019-0225
8. Yin J, Ngiam K Y, & Teo H H. (2021). Role of artificial intelligence applications in real-life clinical practice: Systematic review. Journal of Medical Internet Research, 23(4), e25759. https://doi.org/10.2196/25759
Sigma Membership
Non-member
Type
Presentation
Format Type
Text-based Document
Study Design/Type
Retrospective
Research Approach
Quantitative Research
Keywords:
Instrument and Tool Development, Interprofessional Initiatives, Interprofessional and Interdisciplinary, Pediatric Anesthesia, Patient Selection, Artificial Intelligence, Machine Learning
Recommended Citation
Bass, Mary Beth; Kinch, Jill; and Isenberg, Kimberly, "Machine Learning in Pediatric Surgery: Validation for Ambulatory Screening" (2026). International Nursing Research Congress (INRC). 255.
https://www.sigmarepository.org/inrc/2026/presentations_2026/255
Conference Name
37th International Nursing Research Congress
Conference Host
Sigma Theta Tau International
Conference Location
Toronto, Ontario, Canada
Conference Year
2026
Rights Holder
All rights reserved by the author(s) and/or publisher(s) listed in this item record unless relinquished in whole or part by a rights notation or a Creative Commons License present in this item record. All permission requests should be directed accordingly and not to the Sigma Repository. All submitting authors or publishers have affirmed that when using material in their work where they do not own copyright, they have obtained permission of the copyright holder prior to submission and the rights holder has been acknowledged as necessary.
Review Type
Abstract Review Only: Reviewed by Event Host
Acquisition
Proxy-submission
Date of Issue
2026-09-05
Machine Learning in Pediatric Surgery: Validation for Ambulatory Screening
Toronto, Ontario, Canada
Accurate screening for anesthesia eligibility criteria is crucial for pediatric ambulatory surgery centers (ASCs) to ensure patient safety and optimization of resources [1,3]. Traditional manual chart review by advanced practice providers (APPs) is labor-intensive and subject to variability [2, 3, 7]. Continued growth of the ASC patient volume creates challenges for the APP team to meet the patient safety needs without adding additional support. To address these challenges, we partnered with Brim Analytics (Brim), an Artificial Intelligence (AI) powered chart review tool built on a large language model. Brim interprets unstructured electronic medical record (EMR) data and applies our institutional ASC anesthesia criteria to flag cases that may require a higher level of care.
This retrospective observational validation study analyzed 2,158 pediatric patients scheduled for ASC anesthesia. For each case, Brim’s model returned a binary output: true or false, "Should this patient be rescheduled to the main campus?" These outputs were compared to the expert APP determinations across seven monthly validation cycles. Misclassification analysis informed iterative variable refinement, including adjustments for ambiguous shorthand, time-limited illness criteria, and differentiation of pertinent negatives from past medical history. Accuracy improved from 68% in the initial month cycle to 81%, then 96% before stabilizing at 98-99% alignment with clinician determinations over subsequent cycles, reflecting strong reliability.
Our findings underscore the importance of human-in-the-loop systems and continuous algorithm refinement for safe AI integration [5, 6, 8]. Brim offers a scalable decision-support tool to assist in ASC patient chart review to reduce manual workload, improve surgery scheduling practices, and enhance patient safety. While the goal of AI is not to replace the mandated APP clinical review, it can provide a smart assist to flag high-risk cases, improving efficiency and access to surgical care. Future research should evaluate prospective clinical implementation, workflow impact, and clinician trust to ensure ethical and effective adoption [3, 4, 8].
Description
Discover how a pediatric pre-admission testing (PAT) team validated an AI-powered chart review tool to transform pediatric perioperative screening for ambulatory surgery center eligibility. This session will share lessons on how iterative model refinement and human-in-the-loop validation achieved near-perfect accuracy and explore strategies for safely adopting emerging technologies to improve patient safety, scheduling efficiency, and clinician workflow.