Could ChatGPT Be a Potential Medical Information Source for Attention Deficit Hyperactivity Disorder?
Öz
Background: ChatGPT is a promising and innovative artificial intelligence program whose use case is rapidly expanding. In recent years, its use as a medical information tool by both health professionals and non-specialists has been increasing. However, there is still limited evidence assessing the quality of medical information provided by ChatGPT, particularly in the field of mental health.
Methods: In this study, questions most frequently asked by families to mental health professionals regarding Attention Deficit Hyperactivity Disorder (ADHD), a commonly observed neurodevelopmental disorder, were posed to ChatGPT 4.0 using two separate accounts defined as a parent/caregiver and as an experienced professional. The answers given by ChatGPT were independently evaluated by two experts for ‘Accuracy’, ‘Clarity’ and ‘Inclusivity’.
Results: Our study results indicate that the information provided by ChatGPT regarding Attention Deficit Hyperactivity Disorder (ADHD) is highly accurate and comprehensive. However, unlike the responses given to an experienced professional, the responses provided to a parent/caregiver seeking information about ADHD may be less clear and understandable due to the inclusion of medical jargon and excessive detail. This difference has been particularly evident in questions related to the diagnosis and treatment process (p<0.05).
Conclusions: While current findings suggest that ChatGPT can provide accurate and comprehensive information, concerns about its potential to cause health anxiety and confusion, particularly in the context of mental disorders, indicate that it is not yet suitable to be recommended as the sole source of medical information for non-experts and requires further development.
Anahtar Kelimeler
artificial intelligence, ChatGPT, attention deficit hyperactivity disorder
Destekleyen Kurum
Bu çalışma için destekleyen herhangi bir kurum bulunmamaktadır.
Etik Beyan
Bu çalışma, 1964 Helsinki Bildirgesi ve sonraki ekleri ya da karşılaştırılabilir etik standartlar doğrultusunda gerçekleştirilmiştir. Etik onay, Aksaray Üniversitesi İnsan Araştırmaları Etik Kurulu’ndan alınmıştır (Tarih: 7 Kasım 2024, Etik Kurul Onay Numarası: 2024/122)
Teşekkür
There are no acknowledgements to declare.
Kaynakça
- Pliszka S, AACAP Work Group on Quality Issues. Practice parameter for the assessment and treatment of children and adolescents with attention-deficit/hyperactivity disorder. J Am Acad Child Adolesc Psychiatry. 2007;46(7):894-921.
- Polanczyk G, De Lima MS, Horta BL, Biederman J, Rohde LA. The worldwide prevalence of ADHD: a systematic review and metaregression analysis. Am J Psychiatry. 2007;164(6):942-8.
- Salari N, Ghasemi H, Abdoli N, Rahmani A, Shiri MH, Hashemian AH, et al. The global prevalence of ADHD in children and adolescents: a systematic review and meta-analysis. Ital J Pediatr. 2023;49(1):48.
- Fayyad J, Sampson NA, Hwang I, Adamowski T, Aguilar-Gaxiola S, Al-Hamzawi A, et al. The descriptive epidemiology of DSM-IV adult ADHD in the world health organization world mental health surveys. ADHD Atten Deficit Hyperact Disord. 2017;9:47-65.
- Abdelnour E, Jansen MO, Gold JA. ADHD diagnostic trends: increased recognition or overdiagnosis? Mo Med. 2022;119(5):467.
- Hernandez CA, Gonzalez AEV, Polianovskaia A, Sanchez RA, Arce VM, Mustafa A, et al. The future of patient education: AI-driven guide for type 2 diabetes. Cureus. 2023;15(11).
- Zenone M, Ow N, Barbic S. TikTok and public health: a proposed research agenda. BMJ Glob Health. 2021;6(11):e007648.
- Yeung A, Ng E, Abi-Jaoude E. TikTok and attention-deficit/hyperactivity disorder: a cross-sectional study of social media content quality. Can J Psychiatry. 2022;67(12):899-906.
- van Schalkwyk G. Artificial intelligence in pediatric behavioral health. Child Adolesc Psychiatry Ment Health. 2023;17(1):38.
- Bennett M, Webster AA, Goodall E, Rowland S. Life on the autism spectrum: translating myths and misconceptions into positive futures. Cham: Springer; 2019. p. 1-15.