Probing clarity: AI-generated simplified breast imaging reports for enhanced patient comprehension powered by ChatGPT-4o.
Artificial intelligence
Breast radiology
Large language models
Natural language processing
Patient-centered care
Journal
European radiology experimental
ISSN: 2509-9280
Titre abrégé: Eur Radiol Exp
Pays: England
ID NLM: 101721752
Informations de publication
Date de publication:
30 Oct 2024
30 Oct 2024
Historique:
received:
17
06
2024
accepted:
16
10
2024
medline:
31
10
2024
pubmed:
31
10
2024
entrez:
31
10
2024
Statut:
epublish
Résumé
To assess the reliability and comprehensibility of breast radiology reports simplified by artificial intelligence using the large language model (LLM) ChatGPT-4o. A radiologist with 20 years' experience selected 21 anonymized breast radiology reports, 7 mammography, 7 breast ultrasound, and 7 breast magnetic resonance imaging (MRI), categorized according to breast imaging reporting and data system (BI-RADS). These reports underwent simplification by prompting ChatGPT-4o with "Explain this medical report to a patient using simple language". Five breast radiologists assessed the quality of these simplified reports for factual accuracy, completeness, and potential harm with a 5-point Likert scale from 1 (strongly agree) to 5 (strongly disagree). Another breast radiologist evaluated the text comprehension of five non-healthcare personnel readers using a 5-point Likert scale from 1 (excellent) to 5 (poor). Descriptive statistics, Cronbach's α, and the Kruskal-Wallis test were used. Mammography, ultrasound, and MRI showed high factual accuracy (median 2) and completeness (median 2) across radiologists, with low potential harm scores (median 5); no significant group differences (p ≥ 0.780), and high internal consistency (α > 0.80) were observed. Non-healthcare readers showed high comprehension (median 2 for mammography and MRI and 1 for ultrasound); no significant group differences across modalities (p = 0.368), and high internal consistency (α > 0.85) were observed. BI-RADS 0, 1, and 2 reports were accurately explained, while BI-RADS 3-6 reports were challenging. The model demonstrated reliability and clarity, offering promise for patients with diverse backgrounds. LLMs like ChatGPT-4o could simplify breast radiology reports, aid in communication, and enhance patient care. Simplified breast radiology reports generated by ChatGPT-4o show potential in enhancing communication with patients, improving comprehension across varying educational backgrounds, and contributing to patient-centered care in radiology practice. AI simplifies complex breast imaging reports, enhancing patient understanding. Simplified reports from AI maintain accuracy, improving patient comprehension significantly. Implementing AI reports enhances patient engagement and communication in breast imaging.
Sections du résumé
BACKGROUND
BACKGROUND
To assess the reliability and comprehensibility of breast radiology reports simplified by artificial intelligence using the large language model (LLM) ChatGPT-4o.
METHODS
METHODS
A radiologist with 20 years' experience selected 21 anonymized breast radiology reports, 7 mammography, 7 breast ultrasound, and 7 breast magnetic resonance imaging (MRI), categorized according to breast imaging reporting and data system (BI-RADS). These reports underwent simplification by prompting ChatGPT-4o with "Explain this medical report to a patient using simple language". Five breast radiologists assessed the quality of these simplified reports for factual accuracy, completeness, and potential harm with a 5-point Likert scale from 1 (strongly agree) to 5 (strongly disagree). Another breast radiologist evaluated the text comprehension of five non-healthcare personnel readers using a 5-point Likert scale from 1 (excellent) to 5 (poor). Descriptive statistics, Cronbach's α, and the Kruskal-Wallis test were used.
RESULTS
RESULTS
Mammography, ultrasound, and MRI showed high factual accuracy (median 2) and completeness (median 2) across radiologists, with low potential harm scores (median 5); no significant group differences (p ≥ 0.780), and high internal consistency (α > 0.80) were observed. Non-healthcare readers showed high comprehension (median 2 for mammography and MRI and 1 for ultrasound); no significant group differences across modalities (p = 0.368), and high internal consistency (α > 0.85) were observed. BI-RADS 0, 1, and 2 reports were accurately explained, while BI-RADS 3-6 reports were challenging.
CONCLUSION
CONCLUSIONS
The model demonstrated reliability and clarity, offering promise for patients with diverse backgrounds. LLMs like ChatGPT-4o could simplify breast radiology reports, aid in communication, and enhance patient care.
RELEVANCE STATEMENT
CONCLUSIONS
Simplified breast radiology reports generated by ChatGPT-4o show potential in enhancing communication with patients, improving comprehension across varying educational backgrounds, and contributing to patient-centered care in radiology practice.
KEY POINTS
CONCLUSIONS
AI simplifies complex breast imaging reports, enhancing patient understanding. Simplified reports from AI maintain accuracy, improving patient comprehension significantly. Implementing AI reports enhances patient engagement and communication in breast imaging.
Identifiants
pubmed: 39477904
doi: 10.1186/s41747-024-00526-1
pii: 10.1186/s41747-024-00526-1
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
124Informations de copyright
© 2024. The Author(s).
Références
ChatGPT: optimizing language models for dialogue (2022) OpenAI [cited 2022 Dec 28]. https://openai.com/blog/chatgpt/ . Accessed 28 Dec 2022
Hello ChatGPT-4o (2024) OpenAI [cited 2024 May 13]. https://openai.com/index/hello-gpt-4o/ . Accessed 13 May 2024
Mallio CA, Sertorio AC, Bernetti C, Beomonte Zobel B (2023) Large language models for structured reporting in radiology: performance of GPT-4, ChatGPT-3.5, Perplexity and Bing. Radiol Med 128:808–812. https://doi.org/10.1007/s11547-023-01651-4
doi: 10.1007/s11547-023-01651-4
pubmed: 37248403
Mezrich JL (2022) Immediate radiology report release to patients: point-radiologists should embrace this opportunity to provide patient-centered care while improving the specialty’s profile. AJR Am J Roentgenol 219:555–556. https://doi.org/10.2214/AJR.21.27084
doi: 10.2214/AJR.21.27084
pubmed: 35319913
Ali K, Barhom N, Tamimi F, Duggal M (2024) ChatGPT-A double-edged sword for healthcare education? Implications for assessments of dental students. Eur J Dent Educ 28:206–211. https://doi.org/10.1111/eje.12937
doi: 10.1111/eje.12937
pubmed: 37550893
Liu J, Wang C, Liu S (2023) Utility of ChatGPT in clinical practice. J Med Internet Res 25:e48568. https://doi.org/10.2196/48568
doi: 10.2196/48568
pubmed: 37379067
pmcid: 10365580
Jeblick K, Schachtner B, Dexl J et al (2023) ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports. Eur Radiol. https://doi.org/10.1007/s00330-023-10213-1
D’Orsi CJ, Sickles EA, Mendelson EB et al (2013) ACR BI-RADS® atlas, breast imaging reporting and data system. American College of Radiology, Reston
International Standard Classification of Education (ISCED) (2011) UNESCO. UNESCO Institute for Statistics. https://uis.unesco.org/en/topic/international-standard-classification-education-isced
Srivastav S, Chandrakar R, Gupta S et al (2023) ChatGPT in radiology: The advantages and limitations of artificial intelligence for medical imaging diagnosis. Cureus 15:e41435. https://doi.org/10.7759/cureus.41435
Pesapane F, Tantrige P, De Marco P et al (2023) Advancements in standardizing radiological reports: a comprehensive review. Medicina (Kaunas) 59:1679. https://doi.org/10.3390/medicina59091679
Burnside ES, Sickles EA, Bassett LW et al (2009) The ACR BI-RADS® experience: learning from history. J Am Coll Radiol 6:851–860. https://doi.org/10.1016/j.jacr.2009.07.023
Fowles JB, Kind AC, Craft C et al (2004) Patients’ interest in reading their medical record: relation with clinical and sociodemographic characteristics and patients’ approach to health care. Arch Intern Med 164:793–800. https://doi.org/10.1001/archinte.164.7.793
doi: 10.1001/archinte.164.7.793
pubmed: 15078650
Tonsaker T, Bartlett G, Trpkov C (2014) Health information on the internet. Can Fam Physician 60:407–408
pubmed: 24828994
pmcid: 4020634
Cascella M, Semeraro F, Montomoli J et al (2024) The breakthrough of large language models release for medical applications: 1-year timeline and perspectives. J Med Syst 48:22. https://doi.org/10.1007/s10916-024-02045-3
doi: 10.1007/s10916-024-02045-3
pubmed: 38366043
pmcid: 10873461
European Commission (2021) Proposal for a regulation of the European Parliament and of the council laying down harmonised rules on artificial intelligence (Artificial Intelligence Act) and amending certain Union legislative acts. EUR-Lex. Available via https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX%3A52021PC0206