Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 2 de 2
Filtrar
Mais filtros








Base de dados
Intervalo de ano de publicação
1.
Stud Health Technol Inform ; 310: 1456-1457, 2024 Jan 25.
Artigo em Inglês | MEDLINE | ID: mdl-38269694

RESUMO

To extract information from free-text in clinical records due to the patient's protected health information PHI in the records pre-processing of de-identification is required. Therefore we aimed to identify PHI list and fine-tune the deep learning BERT model for developing de-identification model. The result of fine-tuning the model is strict F1 score of 0.924. Due to the convinced score the model can be used for the development of a de-identification model.


Assuntos
Anonimização de Dados , Aprendizado Profundo , Humanos , República da Coreia
2.
J Cardiovasc Pharmacol ; 82(4): 318-326, 2023 10 01.
Artigo em Inglês | MEDLINE | ID: mdl-37437526

RESUMO

ABSTRACT: Abnormal myocardial metabolism is a common pathophysiological process underlying ischemic heart disease and heart failure (HF). Trimetazidine is an antianginal agent with a unique mechanism of action that regulates myocardial energy metabolism and might have a beneficial effect in preventing HF in patients undergoing myocardial revascularization. We aimed to evaluate the potential benefit of trimetazidine in preventing incident hospitalization for HF after myocardial revascularization. Using the common data model, we identified patients without prior HF undergoing myocardial revascularization from 8 hospital databases in Korea. To compare clinical outcomes using trimetazidine, database-level hazard ratios (HRs) were estimated using large-scale propensity score matching for each database and pooled using a random-effects model. The primary outcome was incident hospitalization for HF. The secondary outcome of interest was major adverse cardiac events (MACEs). After propensity score matching, 6724 and 11,211 patients were allocated to trimetazidine new-users and nonusers, respectively. There was no significant difference in the incidence of hospitalization for HF between the 2 groups (HR: 1.08, 95% confidence interval [CI], 0.88-1.31; P = 0.46). The risk of MACE also did not differ between the 2 groups (HR: 1.07, 95% CI, 0.98-1.16; P = 0.15). In conclusion, the use of trimetazidine did not reduce the risk of hospitalization for HF or MACE in patients undergoing myocardial revascularization. Therefore, the role of trimetazidine in contemporary clinical practice cannot be expanded beyond its current role as an add-on treatment for symptomatic angina.


Assuntos
Insuficiência Cardíaca , Trimetazidina , Humanos , Trimetazidina/efeitos adversos , Vasodilatadores/efeitos adversos , Vasos Coronários , Angina Pectoris , Insuficiência Cardíaca/diagnóstico , Insuficiência Cardíaca/epidemiologia , Insuficiência Cardíaca/prevenção & controle , Resultado do Tratamento
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA