You are here

  • Home
  • Archive
  • Volume 7, Issue 2
  • Deep learning model to predict the need for mechanical ventilation using chest X-ray images in hospitalised patients with COVID-19

Article Text

Article menu
Download PDFPDF
Artificial intelligence
Original research
Deep learning model to predict the need for mechanical ventilation using chest X-ray images in hospitalised patients with COVID-19
  1. Anoop R Kulkarni1,2,
  2. Ambarish M Athavale3,
  3. Ashima Sahni4,
  4. Shashvat Sukhal5,
  5. Abhimanyu Saini6,
  6. Mathew Itteera3,
  7. Sara Zhukovsky7,
  8. Jane Vernik3,
  9. Mohan Abraham3,
  10. Amit Joshi3,
  11. Amatur Amarah3,
  12. Juan Ruiz3,
  13. Peter D Hart3,
  14. Hemant Kulkarni2,8
  1. 1Innotomy Consulting, Bengaluru, India
  2. 2Lata Medical Research Foundation, Nagpur, India
  3. 3Department of Medicine, Division of Nephrology, Cook County Hospital, Chicago, Illinois, USA
  4. 4Division of Pulmonary, Critical Care, Sleep, and Allergy, University of Illinois Hospital and Health Sciences System, Chicago, Illinois, USA
  5. 5Department of Medicine, Division of Pulmonary and Critical Care, Cook County Hospital, Chicago, Illinois, USA
  6. 6Department of Medicine, Division of Cardiology, Cook County Hospital, Chicago, Illinois, USA
  7. 7Rush Medical College, Rush University Medical Center, Chicago, Illinois, USA
  8. 8M&H Research LLC, San Antonio, Texas, USA
  1. Correspondence to Dr Hemant Kulkarni, M&H Research LLC, San Antonio, TX 78249, USA; hemant.kulkarni{at}mnhresearch.com

Abstract

Objectives There exists a wide gap in the availability of mechanical ventilator devices and their acute need in the context of the COVID-19 pandemic. An initial triaging method that accurately identifies the need for mechanical ventilation in hospitalised patients with COVID-19 is needed. We aimed to investigate if a potentially deteriorating clinical course in hospitalised patients with COVID-19 can be detected using all X-ray images taken during hospitalisation.

Methods We exploited the well-established DenseNet121 deep learning architecture for this purpose on 663 X-ray images acquired from 528 hospitalised patients with COVID-19. Two Pulmonary and Critical Care experts blindly and independently evaluated the same X-ray images for the purpose of validation.

Results We found that our deep learning model predicted the need for mechanical ventilation with a high accuracy, sensitivity and specificity (90.06%, 86.34% and 84.38%, respectively). This prediction was done approximately 3 days ahead of the actual intubation event. Our model also outperformed two Pulmonary and Critical Care experts who evaluated the same X-ray images and provided an incremental accuracy of 7.24%–13.25%.

Conclusions Our deep learning model accurately predicted the need for mechanical ventilation early during hospitalisation of patients with COVID-19. Until effective preventive or treatment measures become widely available for patients with COVID-19, prognostic stratification as provided by our model is likely to be highly valuable.

  • critical care
  • COVID-19
  • radiology

Data availability statement

Data and code are available from the author on reasonable request.

This article is made freely available for use in accordance with BMJ’s website terms and conditions for the duration of the covid-19 pandemic or until otherwise determined by BMJ. You may use, download and print the article for any lawful, non-commercial purpose (including text and data mining) provided that all copyright notices and trade marks are retained.

https://bmj.com/coronavirus/usage

https://doi.org/10.1136/bmjinnov-2020-000593

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Data availability statement

    Data and code are available from the author on reasonable request.

    View Full Text

    Footnotes

    • Twitter @DrAnoopKulkarni

    • ARK and AMA contributed equally.

    • Contributors AMA and HK conceptualised the study; ARK and HK conceptualised the deep learning solution; ARK wrote Python scripts, trained and tested the model; AsS and SS provided expertise in pulmonary and critical care; AbS, MI, SZ, JV, MA, AJ, AA and JR participated in data collection along with AMA; HK conducted statistical analyses; AMA, ARK and HK wrote the first draft of the manuscript; all authors reviewed and approved the final manuscript. AMA and HK are the guarantors of this manuscript and take responsibility for data integrity, analytical accuracy and draft writing.

    • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

    • Competing interests None declared.

    • Provenance and peer review Not commissioned; externally peer reviewed.