EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Responsible AI for Personalized Patient Education and Engagement Across Medical Conditions: Leveraging Multi-Agent LLMs, Ambient Technology, and NotebookLM—A Case Study in Diabetes Education and Limb Preservation

Shayan Mashatian, Shu-Fen Wung iD, Aaron Ritter iD, Jessica Fishman, Jeffrey Robbins, Shereen Aziz, Michelle Huo, David G Armstrong iD

Journal of the American Podiatric Medical Association · 08.05.2026 · 116 (3) · 30

DOI: 10.3390/japma116030030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Podiatric Medical Association, online erschienen am 08.05.2026. Verfasst von Shayan Mashatian und 7 weiteren Autor:innen. Beteiligte Einrichtung: Silverberry Group, Inc., Vancouver, BC V3H 5L1, Canada. Hauptthemen laut MEDLINE: Patient Education as Topic, Diabetic Foot, Artificial Intelligence, Patient Participation. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institutes of Health, National Institute of Diabetes the National Science Foundation (NSF) Center to Stream Healthcare in Place (#C2SHiP)and and Diges…, Silverberry Group, Inc., National Institutes of Health, National Institute of Diabetes and Digestive and Kidney Diseases Award.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Effective communication with patients is vital for improving health outcomes in chronic disease management. In this study, we investigated WoundScribeAI’s Scribe AI, also known as Ambient Technology, and its patient education and engagement app, Pingoo.AI. It employed a multi-agent AI model that leveraged Large Language Models (LLMs) and NotebookLM to enhance patient communication in clinical settings.

Methods

The system comprised specialized agents that transcribed healthcare provider–patient conversations through ambient dictation. This transcription generated medical notes that followed the Subjective, Objective, Assessment, and Plan (SOAP) format—a structured document used by healthcare providers to record and communicate information about patient encounters. Simultaneously, comprehensive visit summaries were also created. In the next step, these visit summaries were used to produce conversational and educational content by leveraging NotebookLM, an AI model introduced by Google that can generate podcast-style conversations from provided information. Integrating these agents allows clinicians to deliver engaging, empathetic, and actionable information to patients. Medical experts conducted a two-phase evaluation of the system’s performance based on multiple criteria, with a particular focus on diabetes education and diabetic foot care. The first phase used pre-recorded training videos, while the second phase involved simulated consultations by clinicians using the system. To validate the AI-generated educational content, we used several established frameworks in health communication that closely align with our enhancement goals.

Results

The results showed that the AI model generated accurate clinical documentation and met the criteria for accurate SOAP Notes, visit summaries, and engaging educational content for patients. Given that hallucination is a significant concern related to large language models, especially in critical fields like healthcare, we meticulously analyzed the generated outputs to identify any signs of hallucinated information. Three outcomes successfully passed the validation criteria, including accuracy, completeness, comprehensiveness, absence of potential harm, and no hallucination. Additionally, the Conversational Education content was confirmed against established patient education frameworks and met criteria such as the use of metaphors, empathetic tone, and appropriate language, providing additional detail to help manage the condition.

Conclusions

By providing specific instructions and prompts to NotebookLM to transform visit summaries into educational conversations, we significantly enhanced the comprehensiveness and engagement of the content for patients. In contrast to a traditional summary of the clinical visit, the podcast-style conversation enriched the content with background information, encouraging language, an empathetic tone, and helpful metaphors. Our analysis confirmed that the system did not exhibit any hallucinations, highlighting the effectiveness of our approach in mitigating this risk. These findings support the use of multi-agent AI models, combined with ambient dictation and tools like NotebookLM, to improve patient communication that surpasses traditional paper-based brochures, which are often impersonal, minimal, and do not always adhere to recommended factors for health literacy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Patient Education as TopicDiabetic FootArtificial IntelligencePatient ParticipationHumansLarge Language ModelsDigital HealthCommunication

Stichwörter der Autor:innen

LLMNotebookLMSOAP noteambient AIambient dictationdiabetes self-carediabetic foot ulcergenerative AIlarge language modelpatient communicationpatient education and engagementprompt engineeringpromptingresponsible AItrustworthy AI

Autor:innen und Institutionen

  • Silverberry Group, Inc., Vancouver, BC V3H 5L1, Canada.
  • College of Nursing, University of Arizona, Tucson, AZ 85721, USA.
  • John L. McClellan Memorial Veteran's Hospital, Little Rock, AR 72205, USA.
  • Leonard Davis Institute of Health Economics, University of Pennsylvania, Philadelphia, PA 19104, USA.
  • College of Osteopathic Medicine, California Health Sciences University, Clovis, CA 93611, USA.
  • Weiss School of Natural Sciences, Rice University, Houston, TX 77005, USA.

ORCID-Profile: Shu-Fen Wung, Aaron Ritter, David G Armstrong

Förderung

  • National Institutes of Health, National Institute of Diabetes the National Science Foundation (NSF) Center to Stream Healthcare in Place (#C2SHiP)and and Diges…
  • Silverberry Group, Inc.
  • National Institutes of Health, National Institute of Diabetes and Digestive and Kidney Diseases Award
  • National Science Foundation (NSF) Center to Stream Healthcare in Place

Zitieren

APA

Mashatian, S., Wung, S. F., Ritter, A., Fishman, J., Robbins, J., Aziz, S., Huo, M., & Armstrong, D. G. (2026). Responsible AI for Personalized Patient Education and Engagement Across Medical Conditions: Leveraging Multi-Agent LLMs, Ambient Technology, and NotebookLM—A Case Study in Diabetes Education and Limb Preservation. Journal of the American Podiatric Medical Association, 116(3), 30. https://doi.org/10.3390/japma116030030

Vancouver

Mashatian S, Wung SF, Ritter A, Fishman J, Robbins J, Aziz S, et al. Responsible AI for Personalized Patient Education and Engagement Across Medical Conditions: Leveraging Multi-Agent LLMs, Ambient Technology, and NotebookLM—A Case Study in Diabetes Education and Limb Preservation. Journal of the American Podiatric Medical Association. 2026;116(3):30. doi:10.3390/japma116030030

BibTeX
@article{Mashatian2026,
  author = {Mashatian, Shayan and Wung, Shu-Fen and Ritter, Aaron and Fishman, Jessica and Robbins, Jeffrey and Aziz, Shereen and Huo, Michelle and Armstrong, David G},
  title = {Responsible AI for Personalized Patient Education and Engagement Across Medical Conditions: Leveraging Multi-Agent LLMs, Ambient Technology, and NotebookLM—A Case Study in Diabetes Education and Limb Preservation},
  journal = {Journal of the American Podiatric Medical Association},
  year = {2026},
  volume = {116},
  number = {3},
  pages = {30},
  doi = {10.3390/japma116030030}
}
Kostenlos starten →