ASN's Mission

To create a world without kidney diseases, the ASN Alliance for Kidney Health elevates care by educating and informing, driving breakthroughs and innovation, and advocating for policies that create transformative changes in kidney medicine throughout the world.

learn more

Contact ASN

1401 H St, NW, Ste 900, Washington, DC 20005

email@asn-online.org

202-640-4660

The Latest on X

Kidney Week

Abstract: FR-PO0027

Artificial Intelligence (AI)-Assisted Video Education for Patients with Kidney Diseases

Session Information

Category: Artificial Intelligence, Digital Health, and Data Science

  • 300 Artificial Intelligence, Digital Health, and Data Science

Authors

  • Fichadiya, Harshil, Mayo Clinic Minnesota, Rochester, Minnesota, United States
  • Cheungpasitporn, Wisit, Mayo Clinic Minnesota, Rochester, Minnesota, United States
Background

The role of AI in patient education remains to understood. With AI platforms being able to creatively process and present data, we designed a short project to evaluate the efficacy of AI in patient education video making. These videos are intended to help patients better understand aspects of kidney disease and care.

Methods

We used Mayo patient education material on 20 varying topics (Fig 1A) to create 20 explainer videos using Notebook LM and graded their performance on a 5-point Likert scoring scale assessing content accuracy, completeness, ease of comprehension, graphics and hallucinations (Fig 1B). In addition, 5 patients were asked to take a pre-and-post video survey to assess the efficacy of the videos at conveying important information.

Results

As in Table 1, Notebook LM did fairly well score ≥ 4.4/5 in all parameters. It did very well at presenting complex medical topics in a simplified manner for the patients, as evident by a 5/5 score on ease of comprehension. It occasionally missed a few minor details and some graphics were irrelevant, however these errors were not likely to impact patient care and overall message. On pre and post video survey of 5 patientsl, the average pre video score was 1.3/3 and post video score was 2.5/3.

Conclusion

AI tools can help with enhancing patient education, they can help with simplifying medical complex information and presenting it in a creative way for patient education. While not yet perfect, our study does indicate potential role of AI in enhancing patient education.

Average score (out of 5) on Rikert scoring scale
CategoryAverage score
Accuracy of content4.54
Hallucinations4.63
Completeness4.4
Ease of comprehension5
Relevant graphics4.4