EUVIMEDEUVIMED entdecken
Vergleichsstudie

A comparative assessment of AI and manual transcription quality in health data: insights from field observations

S M Akramul Kabir, Fareeha Ali, Ruqayya Sulaiman-Hill

New Zealand Medical Journal · 2025

DOI: 10.26635/6965.7024 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift New Zealand Medical Journal, 2025. Verfasst von S M Akramul Kabir und 2 weiteren Autor:innen. Beteiligte Einrichtung: Research Fellow, Department of Psychological Medicine, University of Otago Christchurch. Hauptthemen laut MEDLINE: Artificial Intelligence, Data Accuracy. Gefördert von: Canterbury Medical Research Foundation (CMRF) Major Project Grant (Sulaiman-Hill MPG 2022) funding for dual relationship study..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

aim: This study explores the semantic similarities between qualitative research transcripts produced by artificial intelligence (AI) and those transcribed manually, with a particular focus on challenges encountered when working with multicultural participants in health science research who are non-native English speakers. method: The analysis is based on an audio file from one representative participant in a qualitative study involving 20 participants. It compares transcripts generated by a professional audio transcriptionist with those produced by two AI platforms, Otter.ai and Avidnote. results: Findings reveal that while AI transcription has advantages in speed and cost-effectiveness, it can struggle with speaker differentiation and punctuation accuracy, necessitating manual review. Both platforms faced challenges with cultural terminology and accented speech, but Avidnote showed better performance in word recognition and comprehension. Limitations were primarily in the transcription of te reo Māori. conclusion: The study highlights the critical role of culturally competent researchers in reviewing transcripts to ensure accuracy and clarity. These findings contribute to a deeper understanding of the benefits and limitations of AI transcription tools in qualitative health research, especially when working with linguistically and culturally diverse populations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceData AccuracyHumansQualitative ResearchNew Zealand

Autor:innen und Institutionen

  • Research Fellow, Department of Psychological Medicine, University of Otago Christchurch.
  • Assistant Research Fellow & PhD Candidate, Department of Psychological Medicine, University of Otago Christchurch.
  • Senior Research Fellow, Department of Psychological Medicine, University of Otago Christchurch.

Förderung

  • Canterbury Medical Research Foundation (CMRF) Major Project Grant (Sulaiman-Hill MPG 2022) funding for dual relationship study.

Zitieren

APA

Akramul Kabir, S. M., Ali, F., & Sulaiman-Hill, R. (2025). A comparative assessment of AI and manual transcription quality in health data: insights from field observations. New Zealand Medical Journal. https://doi.org/10.26635/6965.7024

Vancouver

Akramul Kabir SM, Ali F, Sulaiman-Hill R. A comparative assessment of AI and manual transcription quality in health data: insights from field observations. New Zealand Medical Journal. 2025. doi:10.26635/6965.7024

BibTeX
@article{AkramulKabir2025,
  author = {Akramul Kabir, S M and Ali, Fareeha and Sulaiman-Hill, Ruqayya},
  title = {A comparative assessment of AI and manual transcription quality in health data: insights from field observations},
  journal = {New Zealand Medical Journal},
  year = {2025},
  doi = {10.26635/6965.7024}
}
Kostenlos starten →