Health system-scale language models are all-purpose prediction engines.
Nature
; 619(7969): 357-362, 2023 Jul.
Article
en En
| MEDLINE
| ID: mdl-37286606
ABSTRACT
Physicians make critical time-constrained decisions every day. Clinical predictive models can help physicians and administrators make decisions by forecasting clinical and operational events. Existing structured data-based clinical predictive models have limited use in everyday practice owing to complexity in data processing, as well as model development and deployment1-3. Here we show that unstructured clinical notes from the electronic health record can enable the training of clinical language models, which can be used as all-purpose clinical predictive engines with low-resistance development and deployment. Our approach leverages recent advances in natural language processing4,5 to train a large language model for medical language (NYUTron) and subsequently fine-tune it across a wide range of clinical and operational predictive tasks. We evaluated our approach within our health system for five such tasks 30-day all-cause readmission prediction, in-hospital mortality prediction, comorbidity index prediction, length of stay prediction, and insurance denial prediction. We show that NYUTron has an area under the curve (AUC) of 78.7-94.9%, with an improvement of 5.36-14.7% in the AUC compared with traditional models. We additionally demonstrate the benefits of pretraining with clinical text, the potential for increasing generalizability to different sites through fine-tuning and the full deployment of our system in a prospective, single-arm trial. These results show the potential for using clinical language models in medicine to read alongside physicians and provide guidance at the point of care.
Texto completo:
1
Banco de datos:
MEDLINE
Asunto principal:
Médicos
/
Procesamiento de Lenguaje Natural
/
Registros Electrónicos de Salud
/
Toma de Decisiones Clínicas
Tipo de estudio:
Guideline
/
Observational_studies
/
Prognostic_studies
/
Risk_factors_studies
Límite:
Humans
Idioma:
En
Revista:
Nature
Año:
2023
Tipo del documento:
Article
País de afiliación:
Estados Unidos