RESUMO
ChatGPT, a language model developed by OpenAI, uses a 175 billion parameter Transformer architecture for natural language processing tasks. This study aimed to compare the knowledge and interpretation ability of ChatGPT with those of medical students in China by administering the Chinese National Medical Licensing Examination (NMLE) to both ChatGPT and medical students. We evaluated the performance of ChatGPT in three years' worth of the NMLE, which consists of four units. At the same time, the exam results were compared to those of medical students who had studied for five years at medical colleges. ChatGPT's performance was lower than that of the medical students, and ChatGPT's correct answer rate was related to the year in which the exam questions were released. ChatGPT's knowledge and interpretation ability for the NMLE were not yet comparable to those of medical students in China. It is probable that these abilities will improve through deep learning.
Assuntos
Inteligência Artificial , Avaliação Educacional , Licenciamento , Medicina , Estudantes de Medicina , Humanos , Povo Asiático , China , Conhecimento , Idioma , Medicina/normas , Licenciamento/normas , Estudantes de Medicina/estatística & dados numéricos , Avaliação Educacional/normasRESUMO
To define the role of autologous stem cell transplantation (ASCT) in newly diagnosed multiple myeloma (MM) in the era of novel agents, we analyzed follow-up data of patients treated by these agents alone or followed by ASCT. From January, 2008 to December, 2012, 136 patients with de novo MM, aged <65 years, completed bortezomib- or thalidomide-based induction therapy and 114 patients achieved at least a partial response (PR). A total of 42 patients underwent ASCT. After a median follow-up of 39 months (range, 5-74 months), the median progression-free survival (PFS) was 23 months in the non-ASCT group vs. 42 months in the ASCT group (P=0.001), and the 5-year overall survival (OS) rate was 58.9 vs. 81.2%, respectively (P=0.03). The multivariate analysis revealed that complete response (CR) and maintenance therapy (MT) were independent factors of improved OS in both groups. Moreover, a subgroup analysis was performed according to the response status to evaluate the role of ASCT and MT. In the CR subgroup, neither ASCT nor MT exerted a significant effect on PFS or OS. In the very good PR subgroup, ASCT after MT (ASCT/MT) significantly improved PFS, but not OS. In patients exhibiting PR, ASCT/MT significantly prolonged PFS and OS. Therefore, ASCT in the era of novel agents maintains an important role in younger MM patients, particularly those achieving a PR after induction therapy. Furthermore, MT is a key factor associated with long-term survival in all MM patients.