Evaluation of an AI-Powered Patient Education Application in Bariatric Surgery: A Prospective Mixed-Methods Feasibility Study
- 1Cedars-Sinai Medical Center
Abstract
BackgroundPatient education is critical to safe and effective postoperative bariatric surgery care. Large language models (LLMs) may improve access to personalized patient education but evidence regarding direct patient use in clinical settings remains limited. We evaluated BariBot, an LLM-powered educational application for patients undergoing bariatric surgery.
MethodsWe conducted a prospective, single-arm mixed-methods feasibility study at a tertiary academic medical center from May 2024 to May 2025. Adult patients undergoing bariatric surgery used BariBot independently on postoperative day 1. The application provided conversational postoperative education and adapted language complexity to participants educational attainment. Outcomes included feasibility, usability, acceptability, perceived trustworthiness, and anticipated future use. Usability was assessed using the System Usability Scale (SUS). Immediately after BariBot use, participants completed a semi-structured qualitative interview assessing acceptability, perceived trustworthiness, and anticipated future use. Interview transcripts underwent thematic analysis.
ResultsSixteen participants completed the BariBot use session, SUS assessment, and post-intervention interview. No technical failures prevented application use, and no participant requested early discontinuation. The median SUS score was 91.3 (IQR, 81.3-98.1), consistent with excellent perceived usability. Qualitative analysis showed that participants valued the applications immediacy, structured responses, conversational context, ability to address follow-up questions, judgement-free nature, and future availability between clinical encounters. Trust was strengthened by alignment with prior clinical guidance and perceived institutional association, although participants emphasized the need for transparency, clinician oversight, and use as an adjunct rather than a replacement of clinician guidance.
ConclusionsBariBot was feasible to implement and was associated with high perceived usability and acceptability postoperatively after bariatric surgery. Larger, longitudinal, and comparative studies are needed to evaluate safety during unsupervised use and determine whether LLM-based educational applications improve patient understanding, engagement, and clinical outcomes.
Related
- A prospective cross-sectional diagnostic feasibility study: musculoskeletal ultrasound for pediatric bone age evaluation
- The implementation and evaluation of an advance care planning education intervention in a long-term care facility: a feasibility study.
- Implementation feasibility and early outcome trends of a nursing-led multimodal recovery protocol after urgent abdominal surgery: a prospective single-group evaluation study
- Prospective evaluation of combination oral S-1 and intravenous cisplatin in cancer patients with severe hepatic dysfunction – a feasibility, safety, and pharmacokinetic study
- Short‐ and Long‐Term Control of Hypertension After Bariatric Surgery: A 10‐Year Prospective Study
BibTeX
@misc{samaan2026evaluation,
title = {{Evaluation of an AI-Powered Patient Education Application in Bariatric Surgery: A Prospective Mixed-Methods Feasibility Study}},
author = {J. S. Samaan and S. T. Nguyen and S. Hamamah and A. Tran and R. C. Ceasar and N. Wolfe and T. Yu and D. Chavez and N. Rajeev and R. Advani and R. Watson and B. Abu Dayyeh and K. Sandhu and H. J. Wong and N. P. Tatonetti and K. Samakar},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.16.26363276},
url = {https://www.medrxiv.org/content/10.64898/2026.09.16.26363276v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Evaluation of an AI-Powered Patient Education Application in Bariatric Surgery: A Prospective Mixed-Methods Feasibility Study
AU - J. S. Samaan
AU - S. T. Nguyen
AU - S. Hamamah
AU - A. Tran
AU - R. C. Ceasar
AU - N. Wolfe
AU - T. Yu
AU - D. Chavez
AU - N. Rajeev
AU - R. Advani
AU - R. Watson
AU - B. Abu Dayyeh
AU - K. Sandhu
AU - H. J. Wong
AU - N. P. Tatonetti
AU - K. Samakar
PY - 2026
DA - 2026/09/16
PB - medRxiv
DO - 10.64898/2026.09.16.26363276
UR - https://www.medrxiv.org/content/10.64898/2026.09.16.26363276v1
AB - BackgroundPatient education is critical to safe and effective postoperative bariatric surgery care. Large language models (LLMs) may improve access to personalized patient education but evidence regarding direct patient use in clinical settings remains limited. We evaluated BariBot, an LLM-powered educational application for patients undergoing bariatric surgery. MethodsWe conducted a prospective, single-arm mixed-methods feasibility study at a tertiary academic medical center from May 2024 to May 2025. Adult patients undergoing bariatric surgery used BariBot independently on postoperative day 1. The application provided conversational postoperative education and adapted language complexity to participants educational attainment. Outcomes included feasibility, usability, acceptability, perceived trustworthiness, and anticipated future use. Usability was assessed using the System Usability Scale (SUS). Immediately after BariBot use, participants completed a semi-structured qualitative interview assessing acceptability, perceived trustworthiness, and anticipated future use. Interview transcripts underwent thematic analysis. ResultsSixteen participants completed the BariBot use session, SUS assessment, and post-intervention interview. No technical failures prevented application use, and no participant requested early discontinuation. The median SUS score was 91.3 (IQR, 81.3-98.1), consistent with excellent perceived usability. Qualitative analysis showed that participants valued the applications immediacy, structured responses, conversational context, ability to address follow-up questions, judgement-free nature, and future availability between clinical encounters. Trust was strengthened by alignment with prior clinical guidance and perceived institutional association, although participants emphasized the need for transparency, clinician oversight, and use as an adjunct rather than a replacement of clinician guidance. ConclusionsBariBot was feasible to implement and was associated with high perceived usability and acceptability postoperatively after bariatric surgery. Larger, longitudinal, and comparative studies are needed to evaluate safety during unsupervised use and determine whether LLM-based educational applications improve patient understanding, engagement, and clinical outcomes.
ER -