Your browser doesn't support javascript.
Development and Prospective Validation of a Deep Learning Algorithm for Predicting Need for Mechanical Ventilation.
Shashikumar, Supreeth P; Wardi, Gabriel; Paul, Paulina; Carlile, Morgan; Brenner, Laura N; Hibbert, Kathryn A; North, Crystal M; Mukerji, Shibani S; Robbins, Gregory K; Shao, Yu-Ping; Westover, M Brandon; Nemati, Shamim; Malhotra, Atul.
  • Shashikumar SP; Department of Biomedical Informatics, University of California, San Diego, La Jolla, CA.
  • Wardi G; Department of Emergency Medicine, University of California, San Diego, La Jolla, CA; Division of Pulmonary, Critical Care, and Sleep Medicine, University of California, San Diego, La Jolla, CA.
  • Paul P; Department of Biomedical Informatics, University of California, San Diego, La Jolla, CA.
  • Carlile M; Department of Emergency Medicine, University of California, San Diego, La Jolla, CA.
  • Brenner LN; Division of Pulmonary and Critical Care Medicine, Massachusetts General Hospital, Boston, MA.
  • Hibbert KA; Division of Pulmonary and Critical Care Medicine, Massachusetts General Hospital, Boston, MA.
  • North CM; Division of Pulmonary and Critical Care Medicine, Massachusetts General Hospital, Boston, MA.
  • Mukerji SS; Department of Neurology, Massachusetts General Hospital, Boston, MA.
  • Robbins GK; Division of Infectious Diseases, Massachusetts General Hospital, Boston, MA.
  • Shao YP; Department of Neurology, Massachusetts General Hospital, Boston, MA.
  • Westover MB; Department of Neurology, Massachusetts General Hospital, Boston, MA.
  • Nemati S; Department of Biomedical Informatics, University of California, San Diego, La Jolla, CA.
  • Malhotra A; Division of Pulmonary, Critical Care, and Sleep Medicine, University of California, San Diego, La Jolla, CA. Electronic address: amalhotra@health.ucsd.edu.
Chest ; 159(6): 2264-2273, 2021 06.
Artículo en Inglés | MEDLINE | ID: covidwho-987252
ABSTRACT

BACKGROUND:

Objective and early identification of hospitalized patients, and particularly those with novel coronavirus disease 2019 (COVID-19), who may require mechanical ventilation (MV) may aid in delivering timely treatment. RESEARCH QUESTION Can a transparent deep learning (DL) model predict the need for MV in hospitalized patients and those with COVID-19 up to 24 h in advance? STUDY DESIGN AND

METHODS:

We trained and externally validated a transparent DL algorithm to predict the future need for MV in hospitalized patients, including those with COVID-19, using commonly available data in electronic health records. Additionally, commonly used clinical criteria (heart rate, oxygen saturation, respiratory rate, Fio2, and pH) were used to assess future need for MV. Performance of the algorithm was evaluated using the area under receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value.

RESULTS:

We obtained data from more than 30,000 ICU patients (including more than 700 patients with COVID-19) from two academic medical centers. The performance of the model with a 24-h prediction horizon at the development and validation sites was comparable (AUC, 0.895 vs 0.882, respectively), providing significant improvement over traditional clinical criteria (P < .001). Prospective validation of the algorithm among patients with COVID-19 yielded AUCs in the range of 0.918 to 0.943.

INTERPRETATION:

A transparent deep learning algorithm improves on traditional clinical criteria to predict the need for MV in hospitalized patients, including in those with COVID-19. Such an algorithm may help clinicians to optimize timing of tracheal intubation, to allocate resources and staff better, and to improve patient care.
Asunto(s)
Palabras clave

Texto completo: Disponible Colección: Bases de datos internacionales Base de datos: MEDLINE Asunto principal: Respiración Artificial / Aprendizaje Profundo / COVID-19 / Necesidades y Demandas de Servicios de Salud Tipo de estudio: Estudio de cohorte / Estudio experimental / Estudio observacional / Estudio pronóstico Tópicos: Covid persistente Límite: Anciano / Femenino / Humanos / Masculino / Middle aged Idioma: Inglés Revista: Chest Año: 2021 Tipo del documento: Artículo País de afiliación: J.chest.2020.12.009

Similares

MEDLINE

...
LILACS

LIS


Texto completo: Disponible Colección: Bases de datos internacionales Base de datos: MEDLINE Asunto principal: Respiración Artificial / Aprendizaje Profundo / COVID-19 / Necesidades y Demandas de Servicios de Salud Tipo de estudio: Estudio de cohorte / Estudio experimental / Estudio observacional / Estudio pronóstico Tópicos: Covid persistente Límite: Anciano / Femenino / Humanos / Masculino / Middle aged Idioma: Inglés Revista: Chest Año: 2021 Tipo del documento: Artículo País de afiliación: J.chest.2020.12.009