COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence

Dorr, Francisco; Cháves, Hernán; Serra, Mercedes; Ramírez, Andrés Hernández; Costa, Martín Elías; Seia, Joaquín; Cejas, Claudia; Castro, Marcelo; Eyheremendy, Eduardo; Slezak, Diego Fernández; Farez, Mauricio

doi:10.1016/j.ibmed.2020.100014

Cited by 18 publications

(21 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A study published in October 2020 showed that chest radiographs may be reliable in predicting results from definitive COVID-19 diagnostic methods, particularly in places with limited resources and a high number of cases[ 38 ]. Radiography is the fastest and cheapest method to evaluate COVID-19 patients and it is broadly available in clinics, emergency rooms, and hospitals worldwide[ 39 , 40 ]. Moreover, this method is associated with a low exposure to ionizing radiation in users.…”

Section: What Do the Imaging Exams Show About The Disease?mentioning

confidence: 99%

“…Thus, the analysis of imaging patterns on chest radiography in SARS-CoV-2 infection is complex, time-consuming, and prone to error. This evaluation is a challenge that must be considered, mainly due to the lack of specialized radiologists[ 39 , 41 ]. Therefore, an artificial intelligence (AI) algorithm could be used and programmed to distinguish COVID-19 pneumonia from non-COVID-19 pneumonia through CXR images[ 44 ].…”

Section: What Do the Imaging Exams Show About The Disease?mentioning

confidence: 99%

“…In November 2020, an evaluation of the CXR associated with AI support for COVID-19 detection reported an increase in the diagnostic sensibility from 47% to 61%, even though the specificity reduced from 79% to 75%. This is a promising result for the possible use of AI to enhance the accuracy of this exam[ 39 ]. In conclusion, the CXR may be indicated in situations of low resources and high prevalence of the disease.…”

Section: What Do the Imaging Exams Show About The Disease?mentioning

confidence: 99%

See 2 more Smart Citations

Highlighting COVID-19: What the imaging exams show about the disease

Carvalho

Júnior

Oliveira

et al. 2021

WJR

View full text Add to dashboard Cite

Coronavirus disease 2019 (COVID-19), a global emergency, is caused by severe acute respiratory syndrome coronavirus 2. The gold standard for its diagnosis is the reverse transcription polymerase chain reaction, but considering the high number of infected people, the low availability of this diagnostic tool in some contexts, and the limitations of the test, other tools that aid in the identification of the disease are necessary. In this scenario, imaging exams such as chest X-ray (CXR) and computed tomography (CT) have played important roles. CXR is useful for assessing disease progression because it allows the detection of extensive consolidations, besides being a fast and cheap method. On the other hand, CT is more sensitive for detecting lung changes in the early stages of the disease and is also useful for assessing disease progression. Of note, ground-glass opacities are the main COVID-19-related CT findings. Positron emission tomography combined with CT can be used to evaluate chronic and substantial damage to the lungs and other organs; however, it is an expensive test. Lung ultrasound (LUS) has been shown to be a promising technique in that context as well, being useful in the screening and monitoring of patients, disease classification, and management related to mechanical ventilation. Moreover, LUS is an inexpensive alternative available at the bedside. Finally, magnetic resonance imaging, although not usually requested, allows the detection of pulmonary, cardiovascular, and neurological abnormalities associated with COVID-19. Furthermore, it is important to consider the challenges faced in the radiology field in the adoption of control measures to prevent infection and in the follow-up of post-COVID-19 patients.

show abstract

Section: What Do the Imaging Exams Show About The Disease?mentioning

confidence: 99%

Section: What Do the Imaging Exams Show About The Disease?mentioning

confidence: 99%

Section: What Do the Imaging Exams Show About The Disease?mentioning

confidence: 99%

See 1 more Smart Citation

Highlighting COVID-19: What the imaging exams show about the disease

Carvalho

Júnior

Oliveira

et al. 2021

WJR

View full text Add to dashboard Cite

show abstract

“…Furthermore, DL algorithms proved to be effective in the recognition of traumatic bone fractures with human-level performances [ 57 , 58 ]. The recent Coronavirus disease 2019 (COVID-19) pandemic, which caused millions of deaths worldwide, led to ML algorithms’ application to detect and quantify pulmonary involvement in patients with pneumonia [ 59 , 60 , 61 , 62 ]. A DL algorithm for automatic detection of abnormalities in chest CT images from COVID-19 patients [ 62 ] showed higher sensitivity in comparison to radiology residents’ assessments and improved diagnosis efficiency by shortening the processing time.…”

Section: How Machine Learning Might Help the Emergency Physicianmentioning

confidence: 99%

Machine Learning and Syncope Management in the ED: The Future Is Coming

Dipaola

Shiffer

Gatti³

et al. 2021

Medicina

View full text Add to dashboard Cite

In recent years, machine learning (ML) has been promisingly applied in many fields of clinical medicine, both for diagnosis and prognosis prediction. Aims of this narrative review were to summarize the basic concepts of ML applied to clinical medicine and explore its main applications in the emergency department (ED) setting, with a particular focus on syncope management. Through an extensive literature search in PubMed and Embase, we found increasing evidence suggesting that the use of ML algorithms can improve ED triage, diagnosis, and risk stratification of many diseases. However, the lacks of external validation and reliable diagnostic standards currently limit their implementation in clinical practice. Syncope represents a challenging problem for the emergency physician both because its diagnosis is not supported by specific tests and the available prognostic tools proved to be inefficient. ML algorithms have the potential to overcome these limitations and, in the future, they could support the clinician in managing syncope patients more efficiently. However, at present only few studies have addressed this issue, albeit with encouraging results.

show abstract

“…No COVID-19 antibodies are available, while vaccines or methods used in the past to improve SARS-CoV immunization may be potent [6]. No effective vaccine and medication has been developed yet, despite the fact that different countries and agencies are trying to find effective medicine which can be useful for preventing and curing COVID-19 [7].…”

Section: Iintroductionmentioning

confidence: 99%

The Avoidance And Detection Function Of Artificial Intelligence In Covid-19

Abdulateef¹,

Mohammed

Abdulateef

2021

2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)

View full text Add to dashboard Cite

The whole planet today is having to fight COVID-19 with big obstacles. The COVID-19 influenced several countries around the world between December 2019 and the present day. Many organisations and scientists seek to find a vaccine and to minimize the spread of COVID-19. Artificial Intelligence is one technology that can successfully address this virus (AI). In the case of other pathogens, artificial intelligence performed very well and could help us cope with the virus COVID-19, too. It is the imagination and the information of the people who use it which will help to overcome this dilemma. In some previous instances AI played a major role in virus prevention and identification. We have an ability to detect certain aspects of the AI because of the COVID-19 crisis. Machine learning that an AI subclass is used to identify patterns and to plan valuable knowledge based on recorded data sets. At the point where used entirely, AI can exceed human efforts by speed and differentiate designs from knowledge previously ignored. However many correct and appropriate data are needed for effective implementation of AI systems. This paper discusses the AI's role in COVID-19 prevention and detection and examines numerous technological aspects of AI. This paper would also clarify where AI will contribute with likely solutions to stop the spread of COVID-19.

show abstract

COVID-19 pneumonia accurately detected on chest radiographs with artificial intelligence

Cited by 18 publications

References 30 publications

Highlighting COVID-19: What the imaging exams show about the disease

Highlighting COVID-19: What the imaging exams show about the disease

Machine Learning and Syncope Management in the ED: The Future Is Coming

The Avoidance And Detection Function Of Artificial Intelligence In Covid-19

Contact Info

Product

Resources

About