MedTok or MythTok? Classifying health misinformation on TikTok with AI

Elisavet Andrikopoulou; Nicholas Talam; Aikaterini Kanta

doi:10.3233/SHTI251497

MedTok or MythTok? Classifying health misinformation on TikTok with AI

Elisavet Andrikopoulou^*
, Nicholas Talam
, Aikaterini Kanta

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

79 Downloads (Pure)

Abstract

Social media platforms such as TikTok are increasingly used to access health information, particularly among younger and digitally connected populations. However, the unregulated nature of this content raises concerns about medical misinformation. This study applied an AI-assisted framework to evaluate the clinical accuracy of 619 TikTok transcripts related to diabetic foot care, using authoritative guidelines from the ADA, IWGDF, and IDSA. Findings show that while some videos convey partially accurate information, over 42% contained misleading or false claims, including advice that could delay treatment or worsen outcomes. Semantic analysis highlighted a prevailing focus on complications and amputation, with minimal attention given to preventive care and early intervention. These results underline the pressing need to address misinformation and promote responsible digital health education.

Original language	English
Title of host publication	Good Evaluation - Better Digital Health
Subtitle of host publication	Proceedings of the EFMI Special Topic Conference 2025
Editors	Ursula H. Hübner, Jan-David Liebe, Arriel Benis, Nicole Egbert, Thomas Engelsma, Parisis Gallos, Daniel Flemming, Valentina Lichtner, Romaric Marcilly, Oscar Tamburis, Sidsel Villumsen
Publisher	IOS Press
Pages	67-71
ISBN (Electronic)	9781643686295
DOIs	https://doi.org/10.3233/SHTI251497
Publication status	Published - 20 Oct 2025
Event	EFMI Special Topic Conference 2025 - Osnabrück, Germany Duration: 20 Oct 2025 → 22 Oct 2025 https://stc2025.efmi.org/

Publication series

Name	Studies in Health Technology and Informatics
Publisher	IOS Press
Volume	332
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Conference

Conference	EFMI Special Topic Conference 2025
Country/Territory	Germany
City	Osnabrück
Period	20/10/25 → 22/10/25
Internet address	https://stc2025.efmi.org/

Keywords

Medical Misinformation
TikTok Health Content
LLM
Misinformation Detection
NLP
AI-Driven Fact-Checking
Public Health Communication

Access to Document

10.3233/SHTI251497

MedTok or MythTok? Classifying Health Misinformation on TikTok with AI Final published version, 204 KBLicence: CC BY-NC

Preventing first-ever diabetic foot ulcers (DFU)
Andrikopoulou, E. (PI)
7/10/24 → 31/07/25
Project: Research

File

Cite this

Andrikopoulou, E., Talam, N., & Kanta, A. (2025). MedTok or MythTok? Classifying health misinformation on TikTok with AI. In U. H. Hübner, J.-D. Liebe, A. Benis, N. Egbert, T. Engelsma, P. Gallos, D. Flemming, V. Lichtner, R. Marcilly, O. Tamburis, & S. Villumsen (Eds.), Good Evaluation - Better Digital Health: Proceedings of the EFMI Special Topic Conference 2025 (pp. 67-71). (Studies in Health Technology and Informatics; Vol. 332). IOS Press. https://doi.org/10.3233/SHTI251497

Andrikopoulou, Elisavet ; Talam, Nicholas ; Kanta, Aikaterini. / MedTok or MythTok? Classifying health misinformation on TikTok with AI. Good Evaluation - Better Digital Health: Proceedings of the EFMI Special Topic Conference 2025. editor / Ursula H. Hübner ; Jan-David Liebe ; Arriel Benis ; Nicole Egbert ; Thomas Engelsma ; Parisis Gallos ; Daniel Flemming ; Valentina Lichtner ; Romaric Marcilly ; Oscar Tamburis ; Sidsel Villumsen. IOS Press, 2025. pp. 67-71 (Studies in Health Technology and Informatics).

@inproceedings{39e052c041694e01b89d694eb010d322,

title = "MedTok or MythTok? Classifying health misinformation on TikTok with AI",

abstract = "Social media platforms such as TikTok are increasingly used to access health information, particularly among younger and digitally connected populations. However, the unregulated nature of this content raises concerns about medical misinformation. This study applied an AI-assisted framework to evaluate the clinical accuracy of 619 TikTok transcripts related to diabetic foot care, using authoritative guidelines from the ADA, IWGDF, and IDSA. Findings show that while some videos convey partially accurate information, over 42\% contained misleading or false claims, including advice that could delay treatment or worsen outcomes. Semantic analysis highlighted a prevailing focus on complications and amputation, with minimal attention given to preventive care and early intervention. These results underline the pressing need to address misinformation and promote responsible digital health education.",

keywords = "Medical Misinformation, TikTok Health Content, LLM, Misinformation Detection, NLP, AI-Driven Fact-Checking, Public Health Communication",

author = "Elisavet Andrikopoulou and Nicholas Talam and Aikaterini Kanta",

year = "2025",

month = oct,

day = "20",

doi = "10.3233/SHTI251497",

language = "English",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "67--71",

editor = "H{\"u}bner, \{Ursula H. \} and Liebe, \{Jan-David \} and Benis, \{Arriel \} and Egbert, \{Nicole \} and Engelsma, \{Thomas \} and Gallos, \{Parisis \} and Daniel Flemming and Lichtner, \{Valentina \} and Marcilly, \{Romaric \} and Tamburis, \{Oscar \} and Villumsen, \{Sidsel \}",

booktitle = "Good Evaluation - Better Digital Health",

address = "Netherlands",

note = "EFMI Special Topic Conference 2025 ; Conference date: 20-10-2025 Through 22-10-2025",

url = "https://stc2025.efmi.org/",

}

Andrikopoulou, E, Talam, N & Kanta, A 2025, MedTok or MythTok? Classifying health misinformation on TikTok with AI. in UH Hübner, J-D Liebe, A Benis, N Egbert, T Engelsma, P Gallos, D Flemming, V Lichtner, R Marcilly, O Tamburis & S Villumsen (eds), Good Evaluation - Better Digital Health: Proceedings of the EFMI Special Topic Conference 2025. Studies in Health Technology and Informatics, vol. 332, IOS Press, pp. 67-71, EFMI Special Topic Conference 2025, Osnabrück, Germany, 20/10/25. https://doi.org/10.3233/SHTI251497

MedTok or MythTok? Classifying health misinformation on TikTok with AI. / Andrikopoulou, Elisavet; Talam, Nicholas; Kanta, Aikaterini.
Good Evaluation - Better Digital Health: Proceedings of the EFMI Special Topic Conference 2025. ed. / Ursula H. Hübner; Jan-David Liebe; Arriel Benis; Nicole Egbert; Thomas Engelsma; Parisis Gallos; Daniel Flemming; Valentina Lichtner; Romaric Marcilly; Oscar Tamburis; Sidsel Villumsen. IOS Press, 2025. p. 67-71 (Studies in Health Technology and Informatics; Vol. 332).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - MedTok or MythTok? Classifying health misinformation on TikTok with AI

AU - Andrikopoulou, Elisavet

AU - Talam, Nicholas

AU - Kanta, Aikaterini

PY - 2025/10/20

Y1 - 2025/10/20

N2 - Social media platforms such as TikTok are increasingly used to access health information, particularly among younger and digitally connected populations. However, the unregulated nature of this content raises concerns about medical misinformation. This study applied an AI-assisted framework to evaluate the clinical accuracy of 619 TikTok transcripts related to diabetic foot care, using authoritative guidelines from the ADA, IWGDF, and IDSA. Findings show that while some videos convey partially accurate information, over 42% contained misleading or false claims, including advice that could delay treatment or worsen outcomes. Semantic analysis highlighted a prevailing focus on complications and amputation, with minimal attention given to preventive care and early intervention. These results underline the pressing need to address misinformation and promote responsible digital health education.

AB - Social media platforms such as TikTok are increasingly used to access health information, particularly among younger and digitally connected populations. However, the unregulated nature of this content raises concerns about medical misinformation. This study applied an AI-assisted framework to evaluate the clinical accuracy of 619 TikTok transcripts related to diabetic foot care, using authoritative guidelines from the ADA, IWGDF, and IDSA. Findings show that while some videos convey partially accurate information, over 42% contained misleading or false claims, including advice that could delay treatment or worsen outcomes. Semantic analysis highlighted a prevailing focus on complications and amputation, with minimal attention given to preventive care and early intervention. These results underline the pressing need to address misinformation and promote responsible digital health education.

KW - Medical Misinformation

KW - TikTok Health Content

KW - LLM

KW - Misinformation Detection

KW - NLP

KW - AI-Driven Fact-Checking

KW - Public Health Communication

U2 - 10.3233/SHTI251497

DO - 10.3233/SHTI251497

M3 - Conference contribution

T3 - Studies in Health Technology and Informatics

SP - 67

EP - 71

BT - Good Evaluation - Better Digital Health

A2 - Hübner, Ursula H.

A2 - Liebe, Jan-David

A2 - Benis, Arriel

A2 - Egbert, Nicole

A2 - Engelsma, Thomas

A2 - Gallos, Parisis

A2 - Flemming, Daniel

A2 - Lichtner, Valentina

A2 - Marcilly, Romaric

A2 - Tamburis, Oscar

A2 - Villumsen, Sidsel

PB - IOS Press

T2 - EFMI Special Topic Conference 2025

Y2 - 20 October 2025 through 22 October 2025

ER -

Andrikopoulou E, Talam N, Kanta A. MedTok or MythTok? Classifying health misinformation on TikTok with AI. In Hübner UH, Liebe JD, Benis A, Egbert N, Engelsma T, Gallos P, Flemming D, Lichtner V, Marcilly R, Tamburis O, Villumsen S, editors, Good Evaluation - Better Digital Health: Proceedings of the EFMI Special Topic Conference 2025. IOS Press. 2025. p. 67-71. (Studies in Health Technology and Informatics). doi: 10.3233/SHTI251497

MedTok or MythTok? Classifying health misinformation on TikTok with AI

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Projects

Preventing first-ever diabetic foot ulcers (DFU)

Cite this