Aplicação de inteligência artificial como suporte pós-operatório para pacientes submetidos à cirurgia torácica

Beatriz D’Ávila Pereira da Silva; Ernesto Evangelista Neto; João Aléssio Juliano Perfeito; André Miotto

doi:10.1590/0100-6991e-2026000425

Original Article

Aplicação de inteligência artificial como suporte pós-operatório para pacientes submetidos à cirurgia torácica

Application of artificial intelligence as postoperative support for patients undergoing thoracic surgery

Beatriz D’Ávila Pereira da Silva; Ernesto Evangelista Neto; João Aléssio Juliano Perfeito; André Miotto

http://dx.doi.org/10.1590/0100-6991e-2026000425 RCBC, vol.53, e2026000425, 2026

PDF

SciELO

Downloads: 0

Resumo

Introdução: A inteligência artificial (IA) tem desempenhado um papel cada vez mais significativo na medicina, desde o diagnóstico por imagens até tratamentos personalizados. No pós-operatório, essa ferramenta pode otimizar o suporte ao paciente, esclarecendo dúvidas e reduzindo a necessidade de consultas presenciais. No entanto, sua confiabilidade e impacto na jornada do paciente ainda são pouco explorados. Esse estudo explorou o potencial da IA como artifício complementar ao cuidado de pacientes submetidos a cirurgia torácica, analisando a precisão das respostas, aceitação pelos pacientes e potencial para transformar o acompanhamento médico.

Métodos: Foram coletadas dúvidas reais de pacientes, que foram respondidas tanto pelo chatGPT quanto por médicos especialistas. As respostas foram comparadas quanto à clareza, acurácia e completude. Os participantes avaliaram a satisfação com as informações fornecidas, a necessidade de buscar mais detalhes e o conforto em utilizar a IA sem supervisão médica.

Resultados: Dos pacientes avaliados, 74,3% relataram que suas dúvidas foram completamente solucionadas pelo chatGPT, enquanto 91,4% consideraram a linguagem clara e acessível. No entanto, 62,8% ainda expressaram a necessidade de confirmação médica. Além disso, 51,4% dos participantes afirmaram que buscariam informações adicionais mesmo após a resposta da IA.

Conclusão: Os resultados apontam que a IA tem grande potencial para melhorar a experiência pós-operatória dos pacientes, oferecendo respostas rápidas e acessíveis. No entanto, sua aplicação deve ser integrada a um modelo híbrido de assistência, combinando tecnologia com individualização médica.

Palavras-chave

Cirurgia; Cirurgia Torácica; Cuidados Pós-Operatórios; Inteligência Artificial; Inteligência Artificial Generativa

Abstract

Introduction: Artificial intelligence (AI) is playing an increasingly significant role in medicine, from imaging-based diagnosis to personalized treatment. In the postoperative period, it may enhance patient support by answering questions more clearly and reducing the need for in-person visits. However, its reliability and effects on the patient experience remain insufficiently studied. This study examined the potential of AI as a complementary tool in the care of patients undergoing thoracic surgery, assessing response accuracy, patient acceptance, and its potential to reshape postoperative follow-up.

Methods: Real patient questions were collected and answered by both ChatGPT and specialist physicians. The responses were compared in terms of clarity, accuracy, and completeness. Participants evaluated their satisfaction with the information provided, their need to seek additional details, and their comfort level with using AI without medical supervision.

Results: Among the patients evaluated, 74.3% reported that ChatGPT fully addressed their questions, and 91.4% found the language clear and accessible. However, 62.8% still indicated a need for medical confirmation. In addition, 51.4% of participants stated that they would seek additional information even after receiving an AI-generated response.

Conclusion: The findings suggest that AI has strong potential to enhance patients’ postoperative experience by providing rapid, accessible answers. However, its use should be integrated into a hybrid care model that combines technology with individualized medical oversight.

Keywords

Surgery; Thoracic Surgery; Postoperative Care; Artificial Intelligence; Generative Artificial Intelligence

References

1 Mintz Y, Brodie R. Introduction to artificial intelligence in medicine. Minim Invasive Ther Allied Technol. 2019;28(2):73-81. doi:10.1080/13645706.2019.1575882.

2 Gupta R, Srivastava D, Sahu M, Tiwari S, Ambasta RK, Kumar P. Artificial intelligence to deep learning: machine intelligence approach for drug discovery. Mol Divers. 2021;25(3):1315-60. doi:10.1007/s11030-021-10217-3.

3 Biswas SS. Role of chatGPT in Public Health. Ann Biomed Eng. 2023;51(5):868-9. doi:10.1007/s10439-023-03172-7.

4 Roose K. The brilliance and weirdness of ChatGPT. The New York Times [Internet]. 2022 Dec 5 [cited 2025 Apr 29]. Available from: https://www.nytimes.com/2022/12/05/technology/chatgpt-ai.html

5 Dave T, Athaluri SA, Singh S. ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations. Front Artif Intell. 2023;6:1169595. doi:10.3389/frai.2023.1169595.

6 Etienne H, Hamdi S, Le Roux M, Camuset J, Khalife-Hocquemiller T, Giol M, et al. Artificial intelligence in thoracic surgery: past, present, perspective and limits. Eur Respir Rev. 2020;29(157):200010. doi:10.1183/16000617.0010-2020.

7 Tustumi F, Andreollo NA, Aguilar-Nascimento JE. Future of the language models in healthcare: the role of chatGPT. Arq Bras Cir Dig. 2023;36:e1727. doi:10.1590/0102-672020230002e1727.

8 Gore JC. Artificial intelligence in medical imaging. Magn Reson Imaging. 2020;68:A1-A4. doi:10.1016/j.mri.2019.12.006.

9 Drukker L, Noble JA, Papageorghiou AT. Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology. Ultrasound Obstet Gynecol. 2020;56(4):498-505. doi:10.1002/uog.22122.

10 Goodfellow I, Bengio Y, Courville A. Deep learning. Cambridge (MA). MIT Press; 2016.

11 Ferreres AR. Ethical aspects of artificial intelligence in general surgical practice. Rev Col Bras Cir. 2024;51:e20243762EDIT01. doi: 10.1590/0100-6991e-20243762EDIT01-en.

12 Cheng Q, Dong Y. Da Vinci Robot-Assisted Video Image Processing under Artificial Intelligence Vision Processing Technology. Comput Math Methods Med. 2022;2022:2752444. doi:10.1155/2022/2752444.

13 Goodfellow I, Bengio Y, Courville A. Deep Learning. MIT Press; 2016.

14 Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. In: Proceedings of the 30th Conference on Neural Information Processing Systems (NeurIPS 2017). 2017; Long Beach, CA. p. 5998-6008.

Submitted date:
07/07/2025

Accepted date:
12/23/2025