AI for radiographic COVID-19 detection selects shortcuts over signal. | PSNet

Provide Feedback |

Register

Study

AI for radiographic COVID-19 detection selects shortcuts over signal.

June 16, 2021

DeGrave AJ, Janizek JD, Lee S-I. Nat Mach Intell. 2021;3:610–619.

View more articles from the same authors.

Artificial intelligence (AI) systems can support diagnostic decision-making. This study evaluates diagnostic “shortcuts” learned by AI systems in detecting COVID-19 in chest radiographs. Results reveal a need for better training data, improved choice in the prediction task, and external validation of the AI system prior to dissemination and implementations in different hospitals.

Related Resources From the Same Author(s)

The Lancet Commission on lessons for the future from the COVID-19 pandemic.

October 12, 2022

Ethical considerations and patient safety concerns for cancelling non-urgent surgeries during the COVID-19 pandemic: a review.

May 12, 2021

The perception of patient safety in an alternate site of care for elective surgery during the first wave of the novel coronavirus pandemic in the United Kingdom: a survey of 158 patients.

March 24, 2021

Maternal and neonatal health care worker well-being and patient safety climate amid the COVID-19 pandemic.

March 31, 2021

Using social and behavioural science to support COVID-19 pandemic response.

June 3, 2020

An objective framework for evaluating unrecognized bias in medical AI models predicting COVID-19 outcomes.

June 1, 2022

The pharmacist-physician relationship in the detection of ambulatory medication errors.

June 28, 2010

The reduction of race and gender bias in clinical treatment recommendations using clinician peer networks in an experimental setting.

December 15, 2021

Nurses' perceptions and demands regarding COVID-19 care delivery in critical care units and hospital emergency services.

December 2, 2020

Predictive power of the "trigger tool" for the detection of adverse events in general surgery: a multicenter observational validation study.

March 9, 2022

View More

Related Resources

Using community detection techniques to identify themes in COVID-19-related patient safety event reports.

December 7, 2022

An objective framework for evaluating unrecognized bias in medical AI models predicting COVID-19 outcomes.

June 1, 2022

Remote patient monitoring during COVID-19: an unexpected patient safety benefit.

March 23, 2022

Harnessing event report data to identify diagnostic error during the COVID-19 pandemic.

December 15, 2021

COVID-19 and open notes: a new method to enhance patient safety and trust.

July 7, 2021

Machine learning is booming in medicine. It’s also facing a credibility crisis.

June 16, 2021

FDA Advise-ERR: reported medication errors with Veklury (remdesivir) emergency use authorization.

September 23, 2020

Bias at warp speed: how AI may contribute to the disparities gap in the time of COVID-19.

September 9, 2020

Psychological impact and coping strategies of frontline medical staff in Hunan between January and March 2020 during the outbreak of Coronavirus Disease 2019 (COVID‑19) in Hubei, China.

April 8, 2020

ACR Recommendations for the use of Chest Radiography and Computed Tomography (CT) for Suspected COVID-19 Infection.

April 1, 2020

View More

See More About The Topic

Intensive Care Units

Information Professionals

Infectious Diseases

To sign up for updates or to access your subscriber preferences, please enter your email address below.

5600 Fishers Lane
Rockville, MD 20857
Telephone: (301) 427-1364