Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 3 de 3
Filtrar
Mais filtros











Base de dados
Intervalo de ano de publicação
1.
Clin Gastroenterol Hepatol ; 22(9): 1917-1925.e17, 2024 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-38729387

RESUMO

BACKGROUND & AIMS: Large language models including Chat Generative Pretrained Transformers version 4 (ChatGPT4) improve access to artificial intelligence, but their impact on the clinical practice of gastroenterology is undefined. This study compared the accuracy, concordance, and reliability of ChatGPT4 colonoscopy recommendations for colorectal cancer rescreening and surveillance with contemporary guidelines and real-world gastroenterology practice. METHODS: History of present illness, colonoscopy data, and pathology reports from patients undergoing procedures at 2 large academic centers were entered into ChatGPT4 and it was queried for the next recommended colonoscopy follow-up interval. Using the McNemar test and inter-rater reliability, we compared the recommendations made by ChatGPT4 with the actual surveillance interval provided in the endoscopist's procedure report (gastroenterology practice) and the appropriate US Multisociety Task Force (USMSTF) guidance. The latter was generated for each case by an expert panel using the clinical information and guideline documents as reference. RESULTS: Text input of de-identified data into ChatGPT4 from 505 consecutive patients undergoing colonoscopy between January 1 and April 30, 2023, elicited a successful follow-up recommendation in 99.2% of the queries. ChatGPT4 recommendations were in closer agreement with the USMSTF Panel (85.7%) than gastroenterology practice recommendations with the USMSTF Panel (75.4%) (P < .001). Of the 14.3% discordant recommendations between ChatGPT4 and the USMSTF Panel, recommendations were for later screening in 26 (5.1%) and for earlier screening in 44 (8.7%) cases. The inter-rater reliability was good for ChatGPT4 vs USMSTF Panel (Fleiss κ, 0.786; 95% CI, 0.734-0.838; P < .001). CONCLUSIONS: Initial real-world results suggest that ChatGPT4 can define routine colonoscopy screening intervals accurately based on verbatim input of clinical data. Large language models have potential for clinical applications, but further training is needed for broad use.


Assuntos
Colonoscopia , Neoplasias Colorretais , Humanos , Colonoscopia/métodos , Colonoscopia/normas , Feminino , Masculino , Neoplasias Colorretais/diagnóstico , Pessoa de Meia-Idade , Idoso , Detecção Precoce de Câncer/métodos , Reprodutibilidade dos Testes , Inteligência Artificial
2.
Ann Otol Rhinol Laryngol ; 130(9): 1010-1015, 2021 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-33511847

RESUMO

OBJECTIVE: Surgery on the ossicular chain may impact its underlying mechanical properties. This study aims to investigate comparative differences in frequency-specific hearing outcomes for ossiculoplasty versus stapedotomy. METHODS: A retrospective chart review was conducted on subjects who underwent ossiculoplasty with partial ossicular replacement prosthesis (PORP) or laser stapedotomy with self-crimping nitinol/fluoroplastic piston, and achieved closure of postoperative pure tone average air-bone gap (PTA-ABG) ≤ 15 dB. 45 PORP and 38 stapedotomy cases were included, with mean length of follow-up of 7.6 months. RESULTS: The mean change in PTA-ABG was similar for the 2 procedures (-17.9 dB vs -18.1 dB, P = .98). Postoperative ABG closure for stapedotomy was superior at 1000 Hz (8.9 dB vs 13.9 dB, P = .0003) and 4000 Hz (11.8 dB vs 18.0 dB, P = .0073). Both procedures also had improved postoperative bone conduction (BC) thresholds at nearly all frequencies, but there was no statistical difference in the change in BC at any particular frequency between the 2 procedures. CONCLUSION: Both procedures achieved a similar mean change in PTA-ABG. Stapedotomy was superior to PORP at ABG closure at 1000 Hz and at 4000 Hz, with 1000 Hz the most discrepant. The exact mechanism responsible for these changes is unclear, but the specific frequencies affected suggest that differences in each procedure's respective impact on the native resonant frequency and mass load of the system could be implicated.


Assuntos
Perda Auditiva Condutiva/cirurgia , Substituição Ossicular/métodos , Cirurgia do Estribo/métodos , Adulto , Audiometria de Tons Puros , Feminino , Perda Auditiva Condutiva/fisiopatologia , Humanos , Masculino , Pessoa de Meia-Idade , Estudos Retrospectivos , Resultado do Tratamento , Adulto Jovem
3.
Cholesterol ; 2017: 3685265, 2017.
Artigo em Inglês | MEDLINE | ID: mdl-28761763

RESUMO

Valvular heart disease frequently occurs as a consequence of premature atherosclerosis in individuals with familial hypercholesterolemia (FH). Studies have primarily focused on aortic valve calcification in heterozygous FH, but there is paucity of data on the incidence of valvular disease in homozygous FH. We performed echocardiographic studies in 33 relatively young patients (mean age: 26 years) with homozygous FH (mean LDL of 447 mg/dL, 73% on LDL apheresis) to look for subclinical valvulopathy. Twenty-one patients had evidence of valvulopathy of the aortic or mitral valves, while seven subjects showed notable mitral regurgitation. Older patients were more likely to have aortic valve calcification (>21 versus ≤21 years: 59% versus 12.5%; p = 0.01) despite lower LDL levels at the time of the study (385 versus 513 mg/dL; p = 0.016). Patients with valvulopathy were older and had comparable LDL levels and a lower carotid intima-media thickness. Our data suggests that, in homozygous FH patients, valvulopathy (1) is present across a wide age spectrum and LDL levels and (2) is less likely to be influenced by lipid-lowering treatment. Echocardiographic studies that focused on aortic root thickening and stenosis and regurgitation are thus likely an effective modality for serial follow-up of subclinical valvular heart disease.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA