Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 6 de 6
Filtrar
Más filtros












Base de datos
Intervalo de año de publicación
1.
J Am Med Inform Assoc ; 31(7): 1451-1462, 2024 Jun 20.
Artículo en Inglés | MEDLINE | ID: mdl-38719204

RESUMEN

OBJECTIVE: Natural language processing (NLP) algorithms are increasingly being applied to obtain unsupervised representations of electronic health record (EHR) data, but their comparative performance at predicting clinical endpoints remains unclear. Our objective was to compare the performance of unsupervised representations of sequences of disease codes generated by bag-of-words versus sequence-based NLP algorithms at predicting clinically relevant outcomes. MATERIALS AND METHODS: This cohort study used primary care EHRs from 6 286 233 people with Multiple Long-Term Conditions in England. For each patient, an unsupervised vector representation of their time-ordered sequences of diseases was generated using 2 input strategies (212 disease categories versus 9462 diagnostic codes) and different NLP algorithms (Latent Dirichlet Allocation, doc2vec, and 2 transformer models designed for EHRs). We also developed a transformer architecture, named EHR-BERT, incorporating sociodemographic information. We compared the performance of each of these representations (without fine-tuning) as inputs into a logistic classifier to predict 1-year mortality, healthcare use, and new disease diagnosis. RESULTS: Patient representations generated by sequence-based algorithms performed consistently better than bag-of-words methods in predicting clinical endpoints, with the highest performance for EHR-BERT across all tasks, although the absolute improvement was small. Representations generated using disease categories perform similarly to those using diagnostic codes as inputs, suggesting models can equally manage smaller or larger vocabularies for prediction of these outcomes. DISCUSSION AND CONCLUSION: Patient representations produced by sequence-based NLP algorithms from sequences of disease codes demonstrate improved predictive content for patient outcomes compared with representations generated by co-occurrence-based algorithms. This suggests transformer models may be useful for generating multi-purpose representations, even without fine-tuning.


Asunto(s)
Algoritmos , Registros Electrónicos de Salud , Procesamiento de Lenguaje Natural , Humanos , Estudios de Cohortes , Femenino , Masculino , Enfermedad/clasificación , Inglaterra
3.
Pol Przegl Chir ; 93(3): 1-5, 2021 Apr 14.
Artículo en Inglés | MEDLINE | ID: mdl-33949331

RESUMEN

Background Laparoscopic cholecystectomy is one of the most commonly performed operation. Various methods for securing the cystic artery and cystic duct are described in literature. We aim to compare intra-operative and early post-operative outcomes of laparoscopic cholecystectomy using polymeric locking Hem-o-lok clips versus metallic ligaclips . Patients and Methods Retrospective study of prospectively maintained single institutional data including all consecutive patients who underwent elective laparoscopic cholecystectomy from 2013 to 2018. Patients in whom metallic ligaclips were used were grouped as Group I and those with Hem-o-Lok were grouped as Group II. The early post-operative outcomes of the two groups were compared. Results Total 1496 patients were included in the study; 836 patients in Group I and 660 in Group II. Study included 29.1% males and 70.9% females with mean age of 43.6 years. Hem-o-lok clip was better in securing wide cystic duct compared to metallic clips. Metallic clip failed to secure 8 out of 44 wide cystic duct compared to 0 out 70 with Hem-o-lok clips (p=0.002). The post-operative outcomes of both groups were comparable. There were no cystic duct leak, post- operative bleeding or major bile duct injuries in either group. Conclusion Use of Hem-o-lok clip is safe in laparoscopic cholecystectomy due to ease of application and security. Hem-o-lok is more useful in patients with thick and wide cystic duct which are difficult to secure with metallic clips with low risk of leak. Key words: Laparoscopic Cholecystectomy, Hem-o-lok clip, Metallic clip, Wide cystic duct.


Asunto(s)
Colecistectomía Laparoscópica , Laparoscopía , Adulto , Procedimientos Quirúrgicos Electivos , Femenino , Humanos , Masculino , Estudios Retrospectivos , Instrumentos Quirúrgicos
4.
Malays J Med Sci ; 28(1): 27-34, 2021 Feb.
Artículo en Inglés | MEDLINE | ID: mdl-33679217

RESUMEN

BACKGROUND: Gallbladder polyps are considered pre-malignant lesions of gallbladder carcinoma. This study aims to highlight the role of early cholecystectomy in the management of gallbladder polyps in an endemic population. METHODS: A retrospective analysis of 2,076 lap cholecystectomy procedures performed at the Department of Surgical Gastroenterology at a tertiary referral centre in Northern India was conducted and incidental malignancy in gallbladder polyps analysed. The 8th edition of the American Joint Committee on Cancer for tumour-node-metastasis (TNM) staging of gallbladder carcinoma was used. RESULTS: Of 54 patients with gallbladder polyps, 53 had benign histology and one had malignant cells in the lamina propria suggestive of T1a adenocarcinoma. The patient with the malignant polyp was older (57 years old) than the patients in the non-cancer group, which had a mean age of 45 (P = 0.039). The size of the malignant polyp was approximately 4 mm, significantly smaller than the average 7.9 mm size of the benign polys (P = 0.031). CONCLUSION: Cholecystectomy needs to be considered early in the management of small-sized gallbladder polyps, particularly in areas endemic for gallbladder carcinoma.

5.
Funct Plant Biol ; 46(12): 1090-1102, 2019 11.
Artículo en Inglés | MEDLINE | ID: mdl-31665615

RESUMEN

Climatic variations along with a rise in temperature during the winter season impose severe heat stress during the anthesis stage of spring wheat, resulting in severe yield losses. The present study was conducted to evaluate the influence of heat stress on redox homeostasis in developing anthers and flag leaves of wheat. Five Indian bread wheat genotypes were studied under field conditions during the dry season, with two extreme sowing dates (timely and very late sown) to explore the effect of heat stress on anthesis stage. Results showed that elevated temperature during anthesis caused significant increase in reactive oxygen species (ROS) content and malondialdehyde (MDA) accumulation in developing anthers, triggering pollen mortality. Moreover, defective source (leaf) to the sink (anthers) mobilisation of starch also contributes in reducing pollen viability. However, ROS-induced oxidative damage of developing anthers under heat stress varied among the wheat genotypes depending upon differential antioxidant enzyme activities. Wheat genotype with enhanced antioxidant activities and reduced ROS built up in developing anthers sustained their grain yield, suggesting thermo-tolerance in wheat to be associated with antioxidant enzyme-mediated improved ROS-scavenging mechanism not only in leaves even in developing anther also. In the present study, heat stressed wheat genotype WH 730 exhibited effective source to sink mobilisation and sustainable grain yield with improved ROS scavenging, conferring greater potential for heat tolerance. We conclude that redox homeostasis and balanced source sink activity played a significant role for sustainable yield and heat tolerance in wheat.


Asunto(s)
Antioxidantes , Triticum , Grano Comestible , Respuesta al Choque Térmico , Hojas de la Planta
6.
Psychol Sci ; 26(2): 159-69, 2015 Feb.
Artículo en Inglés | MEDLINE | ID: mdl-25605707

RESUMEN

Hostility and chronic stress are known risk factors for heart disease, but they are costly to assess on a large scale. We used language expressed on Twitter to characterize community-level psychological correlates of age-adjusted mortality from atherosclerotic heart disease (AHD). Language patterns reflecting negative social relationships, disengagement, and negative emotions-especially anger-emerged as risk factors; positive emotions and psychological engagement emerged as protective factors. Most correlations remained significant after controlling for income and education. A cross-sectional regression model based only on Twitter language predicted AHD mortality significantly better than did a model that combined 10 common demographic, socioeconomic, and health risk factors, including smoking, diabetes, hypertension, and obesity. Capturing community psychological characteristics through social media is feasible, and these characteristics are strong markers of cardiovascular mortality at the community level.


Asunto(s)
Enfermedad de la Arteria Coronaria/mortalidad , Enfermedad de la Arteria Coronaria/psicología , Medios de Comunicación Sociales/estadística & datos numéricos , Estudios Transversales , Recolección de Datos/estadística & datos numéricos , Emociones , Femenino , Humanos , Lenguaje , Masculino , Modelos Psicológicos , Modelos Estadísticos , Análisis de Regresión , Factores de Riesgo , Estados Unidos/epidemiología
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA
...