Artificial intelligence software as diagnostic support tool in emergency room chest radiographs: a pictorial essay / Software de inteligência artificial como ferramenta de apoio ao diagnóstico em radiografias torácicas de salas de emergência: um ensaio pictórico

Fabricio Prospero Machado, Maria Fernanda Arruda Almeida, Edivaldo Nery de Oliveira Filho, Fabiano Castello, Paula Nicole Vieira Pinto Barbosa

Abstract


This pictorial essay aims to show scenarios where an Artificial Intelligence software (Lunit Insight CRX 3) was used as a diagnostic support tool in chest X-ray exams to detect significant upper abdominal or thoracic pathologies, frequently lost in the Emergency Room evaluations. The lesions studied were nodule, consolidation, pneumothorax, pneumoperitoneum, cardiomegaly, mediastinal enlargement, and atelectasis. The most frequently found radiological finding was consolidation (53,6%).Although radiography is an essential test of critical patient evaluation, specialists are often not available to provide reports so that the software can assist in non-radiologists physicians imaging evaluation.


Keywords


thoracic diseases, radiography, artificial intelligence.

References


Quekel LGBA, Kessels AGH, Goei R, et al. Miss rate of lung cancer on the chest radiograph in clinical practice. Chest. 1999 Mar 1;115(3):720–4.

UNSCEAR. SOURCES AND EFFECTS OF IONIZING RADIATION United Nations Scientific Committee on the Effects of Atomic Radiation. 2010;I(c):156. Available from: http://www.unscear.org/docs/reports/2008/09- 86753_Report_2008_GA_Report.pdf

Munera F, Infante JC. Deep learning for chest radiography in the emergency department. Radiology [Internet]. 2019;293(3):581–2. Available from: https://pubs.rsna.org/doi/pdf/10.1148/radiol.2019192079

Donald JJ, Barnard SA. Common patterns in 558 diagnostic radiology errors. J Med Imaging Radiat Oncol [Internet]. 2012;56(2):173–8. Available from: https://doi.org/10.1111/j.1754-9485.2012.02348.x

Waite S, Scott J, Gale B, et al. Interpretive error in radiology. Am J Roentgenol [Internet]. 2017;208(4):739–49. Available from: https://www.ajronline.org/doi/pdf/10.2214/AJR.16.16963?src=recsys

Hwang EJ, Park S, Jin KN, et al. Development and Validation of a Deep Learning-Based Automated Detection Algorithm for Major Thoracic Diseases on Chest Radiographs. JAMA Netw open. 2019;2(3):e191095.

Eng J, Mysko WK, Weller GER, et al. Comparison of Emergency Medicine. 2000;(November):1233–8. Available from: https://www.ajronline.org/doi/pdf/10.2214/ajr.175.5.1751233

Potchen EJ, Cooper TG, Sierra AE, et al. Measuring performance in chest radiography. Radiology. 2000

Potchen EJ. Measuring Observer Performance in Chest Radiology: Some Experiences. J Am Coll Radiol. 2006

Self WH, Courtney DM, McNaughton CD, et al. High discordance of chest x-ray and computed tomography for detection of pulmonary opacities in ED patients: Implications for diagnosing pneumonia. Am J Emerg Med. 2013 Feb 1;31(2):401–5.

Kollef MH. The effect of an increased index of suspicion on the diagnosis of pneumothorax in the critically ill. Mil Med. 1992 Nov;157(11):591-3. PMID: 1470353.

Baker SR, Shah S, Ghosh S. Radiology medical malpractice suits in gastrointestinal radiology: prevalence, causes, and outcomes.




DOI: https://doi.org/10.34119/bjhrv5n3-187

Refbacks

  • There are currently no refbacks.