nach oben

Erschienen in:

17.11.2023 | Gynecologic Oncology

Will I soon be out of my job? Quality and guideline conformity of ChatGPT therapy suggestions to patient inquiries with gynecologic symptoms in a palliative setting

verfasst von: Eva-Marie Braun, Ingolf Juhasz-Böss, Erich-Franz Solomayer, Daniel Truhn, Christiane Keller, Vanessa Heinrich, Benedikt Johannes Braun

Erschienen in: Archives of Gynecology and Obstetrics | Ausgabe 4/2024

Einloggen, um Zugang zu erhalten

Abstract

Purpose

The market and application possibilities for artificial intelligence are currently growing at high speed and are increasingly finding their way into gynecology. While the medical side is highly represented in the current literature, the patient's perspective is still lagging behind. Therefore, the aim of this study was to evaluate the recommendations of ChatGPT regarding patient inquiries about the possible therapy of gynecological leading symptoms in a palliative situation by experts.

Methods

Case vignettes were constructed for 10 common concomitant symptoms in gynecologic oncology tumors in a palliative setting, and patient queries regarding therapy of these symptoms were generated as prompts for ChatGPT. Five experts in palliative care and gynecologic oncology evaluated the responses with respect to guideline adherence and applicability and identified advantages and disadvantages.

Results

The overall rating of ChatGPT responses averaged 4.1 (5 = strongly agree; 1 = strongly disagree). The experts saw an average guideline conformity of the therapy recommendations with a value of 4.0. ChatGPT sometimes omits relevant therapies and does not provide an individual assessment of the suggested therapies, but does indicate that a physician consultation is additionally necessary.

Conclusions

Language models, such as ChatGPT, can provide valid and largely guideline-compliant therapy recommendations in their freely available and thus in principle accessible version for our patients. For a complete therapy recommendation, an evaluation of the therapies, their individual adjustment as well as a filtering of possible wrong recommendations, a medical expert's opinion remains indispensable.

Nur mit Berechtigung zugänglich

Ruby D (2023) 57+ ChatGPT Statistics 2023 (Updated Data With Infographics). https://www.demandsage.com/chatgpt-statistics/. Accessed 21 May 2023

Kung TH, Cheatham M, Medenilla A et al (2023) Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLoS digital health 2:e0000198CrossRefPubMedPubMedCentral

Kemp MW, Logan SJ, Dimri PS et al (2023) ChatGPT outscored human candidates in a virtual objective structured clinical examination (OSCE) in obstetrics and gynecology. Am J Obstet Gynecol. https://doi.org/10.1016/j.ajog.2023.04.020CrossRefPubMed

Sanchez-Ramos L, Lin L, Romero R (2023) Beware of references when using ChatGPT as a source of information to write scientific articles. Am J Obstet Gynecol. https://doi.org/10.1016/j.ajog.2023.04.004CrossRefPubMed

Levin G, Meyer R, Kadoch E, Brezinov Y (2023) Identifying ChatGPT-written OBGYN abstracts using a simple tool. Am J Obstet Gynecol 5(6):100936. https://doi.org/10.1016/j.ajogmf.2023.100936CrossRef

Lee P, Bubeck S, Petro J (2023) Benefits, limits, and risks of GPT-4 as an AI Chatbot for medicine. N Engl J Med 388:1233–1239CrossRefPubMed

Ray PP (2023) Bridging the gap: integrating ChatGPT into obstetrics and gynecology research—a call to action. Arch Gynecol Obstet. https://doi.org/10.1007/s00404-023-07129-yCrossRefPubMed

Grünebaum A, Chervenak J, Pollet SL et al (2023) The exciting potential for ChatGPT in obstetrics and gynecology. Am J Obstet Gynecol. https://doi.org/10.1016/j.ajog.2023.03.009CrossRefPubMedPubMedCentral

Lukac S, Dayan D, Fink V et al (2023) Evaluating ChatGPT as an adjunct for the multidisciplinary tumor board decision-making in primary breast cancer cases. Arch Gynecol Obstet. https://doi.org/10.1007/s00404-023-07130-5CrossRefPubMedPubMedCentral

10.

Li J, Dada A, Kleesiek J, Egger J (2023) ChatGPT in healthcare: a taxonomy and systematic review. medRxiv 9(1):e001568. https://doi.org/10.1101/2023.03.30.23287899CrossRef

11.

Radford A, Narasimhan K, Salimans T, Sutskever I (2018) Improving language understanding by generative pre-training. OpenAI, San Francisco

12.

Duong D, Solomon BD (2023) Analysis of large-language model versus human performance for genetics questions. medRxiv. https://doi.org/10.1038/s41431-023-01396-8CrossRefPubMedPubMedCentral

13.

Potapenko I, Boberg-Ans LC, Hansen S et al (2023) Artificial intelligence-based chatbot patient information on common retinal diseases using ChatGPT. Acta Ophthalmol. https://doi.org/10.1111/aos.15661CrossRefPubMed

14.

Bulatov A, Kuratov Y, Burtsev MS (2023) Scaling transformer to 1M tokens and beyond with RMT. arXiv Prepr arXiv:230411062ADS

15.

Xie Y, Seth I, Hunter-Smith DJ et al (2023) Aesthetic surgery advice and counseling from artificial intelligence: a rhinoplasty consultation with ChatGPT. Aesthetic Plast Surg 47(5):1985–1993. https://doi.org/10.1007/s00266-023-03338-7CrossRefPubMedPubMedCentral

16.

Fernández-Montes A, de Velasco G, Aguín S et al (2021) Insights into the use of peripherally acting μ-opioid receptor antagonists (PAMORAs) in oncologic patients: from scientific evidence to real clinical practice. Curr Treat Options Oncol 22:1–19CrossRef

17.

Bushuven S, Bentele M, Bentele S et al (2023) ChatGPT, can you help me save my child’s life?-Diagnostic accuracy and supportive capabilities to lay rescuers by ChatGPT in prehospital basic life support and paediatric advanced life support cases–an in-silico analysis. Res Square. https://doi.org/10.2120/rs.3.rs-2910261/v1CrossRef

18.

Liu S, Wright AP, Patterson BL et al (2023) Using AI-generated suggestions from ChatGPT to optimize clinical decision support. J Am Med Inform Assoc. https://doi.org/10.1093/jamia/ocad072CrossRefPubMedPubMedCentral

19.

Corrales DM, Wells AE, Radecki Breitkopf C et al (2018) Internet use by gynecologic oncology patients and its relationship with anxiety. J Health Commun 23:299–305CrossRefPubMed

20.

Lawrentschuk N, Abouassaly R, Hewitt E et al (2016) Health information quality on the internet in gynecological oncology: a multilingual evaluation. Eur J Gynaecol Oncol 37:478–483PubMed

21.

Ali SR, Dobbs TD, Hutchings HA, Whitaker IS (2023) Using ChatGPT to write patient clinic letters. Lancet Digit Health 5:e179–e181CrossRefPubMed

22.

Maboloc CR (2023) Chat GPT: the need for an ethical framework to regulate its use in education. J Public Health. https://doi.org/10.1093/pubmed/fdad125CrossRef

23.

Fournier-Tombs E, McHardy J (2023) A medical ethics framework for conversational artificial intelligence. J Med Internet Res 25:e43068CrossRefPubMedPubMedCentral

24.

King MR (2023) The future of AI in medicine: a perspective from a Chatbot. Ann Biomed Eng 51:291–295CrossRefPubMed

25.

Zhang J, Zhang Z (2023) Ethics and governance of trustworthy medical artificial intelligence. BMC Med Inform Decis Mak 23:1–15CrossRef

Titel: Will I soon be out of my job? Quality and guideline conformity of ChatGPT therapy suggestions to patient inquiries with gynecologic symptoms in a palliative setting
verfasst von: Eva-Marie Braun
Ingolf Juhasz-Böss
Erich-Franz Solomayer
Daniel Truhn
Christiane Keller
Vanessa Heinrich
Benedikt Johannes Braun
Publikationsdatum: 17.11.2023
Verlag: Springer Berlin Heidelberg
Erschienen in: Archives of Gynecology and Obstetrics / Ausgabe 4/2024
Print ISSN: 0932-0067
Elektronische ISSN: 1432-0711
DOI: https://doi.org/10.1007/s00404-023-07272-6

Neu im Fachgebiet Gynäkologie und Geburtshilfe

Alter der Mutter beeinflusst Risiko für kongenitale Anomalie

28.05.2024 Kinder- und Jugendgynäkologie Nachrichten

Welchen Einfluss das Alter ihrer Mutter auf das Risiko hat, dass Kinder mit nicht chromosomal bedingter Malformation zur Welt kommen, hat eine ungarische Studie untersucht. Sie zeigt: Nicht nur fortgeschrittenes Alter ist riskant.

Fehlerkultur in der Medizin – Offenheit zählt!

28.05.2024 Fehlerkultur Podcast

Darüber reden und aus Fehlern lernen, sollte das Motto in der Medizin lauten. Und zwar nicht nur im Sinne der Patientensicherheit. Eine negative Fehlerkultur kann auch die Behandelnden ernsthaft krank machen, warnt Prof. Dr. Reinhard Strametz. Ein Plädoyer und ein Leitfaden für den offenen Umgang mit kritischen Ereignissen in Medizin und Pflege.

Mammakarzinom: Brustdichte beeinflusst rezidivfreies Überleben

26.05.2024 Mammakarzinom Nachrichten

Frauen, die zum Zeitpunkt der Brustkrebsdiagnose eine hohe mammografische Brustdichte aufweisen, haben ein erhöhtes Risiko für ein baldiges Rezidiv, legen neue Daten nahe.

Mehr Lebenszeit mit Abemaciclib bei fortgeschrittenem Brustkrebs?

24.05.2024 Mammakarzinom Nachrichten

In der MONARCHE-3-Studie lebten Frauen mit fortgeschrittenem Hormonrezeptor-positivem, HER2-negativem Brustkrebs länger, wenn sie zusätzlich zu einem nicht steroidalen Aromatasehemmer mit Abemaciclib behandelt wurden; allerdings verfehlte der numerische Zugewinn die statistische Signifikanz.

Update Gynäkologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert – ganz bequem per eMail.

Newsletter bestellen

Live-Webinar "Urologie und Sexualmedizin in der Praxis"

Springer Medizin

Will I soon be out of my job? Quality and guideline conformity of ChatGPT therapy suggestions to patient inquiries with gynecologic symptoms in a palliative setting