Your browser doesn't support javascript.
loading
Length of Stay Prediction in Neurosurgery with Russian GPT-3 Language Model Compared to Human Expectations.
Danilov, Gleb; Kotik, Konstantin; Shevchenko, Elena; Usachev, Dmitriy; Shifrin, Michael; Strunina, Yulia; Tsukanova, Tatyana; Ishankulov, Timur; Lukshin, Vasiliy; Potapov, Alexander.
Afiliação
  • Danilov G; Laboratory of Biomedical Informatics and Artificial Intelligence, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.
  • Kotik K; Laboratory of Biomedical Informatics and Artificial Intelligence, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.
  • Shevchenko E; Laboratory of Biomedical Informatics and Artificial Intelligence, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.
  • Usachev D; Laboratory of Biomedical Informatics and Artificial Intelligence, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.
  • Shifrin M; Laboratory of Biomedical Informatics and Artificial Intelligence, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.
  • Strunina Y; Laboratory of Biomedical Informatics and Artificial Intelligence, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.
  • Tsukanova T; Laboratory of Biomedical Informatics and Artificial Intelligence, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.
  • Ishankulov T; Laboratory of Biomedical Informatics and Artificial Intelligence, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.
  • Lukshin V; Laboratory of Biomedical Informatics and Artificial Intelligence, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.
  • Potapov A; Laboratory of Biomedical Informatics and Artificial Intelligence, National Medical Research Center for Neurosurgery named after N.N. Burdenko, Moscow, Russian Federation.
Stud Health Technol Inform ; 289: 156-159, 2022 Jan 14.
Article em En | MEDLINE | ID: mdl-35062115
ABSTRACT
Patients, relatives, doctors, and healthcare providers anticipate the evidence-based length of stay (LOS) prediction in neurosurgery. This study aimed to assess the quality of LOS prediction with the GPT3 language model upon the narrative medical records in neurosurgery comparing to doctors' and patients' expectations. We found no significant difference (p = 0.109) between doctors', patients', and model's predictions with neurosurgeons tending to be more accurate in prognosis. The modern neural network language models demonstrate feasibility in LOS prediction.
Assuntos
Palavras-chave
Texto completo
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Neurocirurgia Tipo de estudo: Prognostic_studies / Risk_factors_studies Limite: Humans País/Região como assunto: Asia / Europa Idioma: En Revista: Stud Health Technol Inform Ano de publicação: 2022 Tipo de documento: Article
Texto completo
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Neurocirurgia Tipo de estudo: Prognostic_studies / Risk_factors_studies Limite: Humans País/Região como assunto: Asia / Europa Idioma: En Revista: Stud Health Technol Inform Ano de publicação: 2022 Tipo de documento: Article