Artificial Intelligence

Artificial intelligence (AI) is becoming a crucial component of healthcare to help augment physicians and make them more efficient. In medical imaging, it is helping radiologists more efficiently manage PACS worklists, enable structured reporting, auto detect injuries and diseases, and to pull in relevant prior exams and patient data. In cardiology, AI is helping automate tasks and measurements on imaging and in reporting systems, guides novice echo users to improve imaging and accuracy, and can risk stratify patients. AI includes deep learning algorithms, machine learning, computer-aided detection (CAD) systems, and convolutional neural networks. 

Man vs. Machine artificial intelligence AI

Radiologists debate the merits of AI for work list triage in emergency settings

Physicians with two academic institutions made their cases in dueling opinion pieces published in the American Journal of Roentgenology Wednesday. 

colorectal cancer colon CTC CRC colonoscopy

AI spots missed colorectal cancers on routine CT scans

Rates of colorectal cancer are on the rise, most notably in younger adults, who have seen CRC diagnoses double over the last decade.

Harrison.ai cofounders Tran

Radiology artificial intelligence firm Harrison.ai raises $112M, opens US office

The Australian company offers Annalise Enterprise CXR, which leaders believe is the most comprehensive decision aid for X-ray reading, able to identify up to 124 findings. 

healthcare AI newsmakers

Healthcare AI newswatch: End-of-life AI, deepfake healthcare workers, AI drug prescribers, more

End-of-life decisions are often anything but easy. AI might be able to help. 

artificial intelligence AI healthcare FUTURE-AI consortium

Global consortium: The future of AI in healthcare is dynamic—and demanding

An international cluster of 117 researchers from 50 countries has arrived at a consensus on six principles that, in the team’s considered view, ought to guide the use of AI across healthcare worldwide. 

Thumbnail

Gottlieb: Let’s not slap the label ‘medical device’ on AI software that only helps clinicians make care decisions

Standing FDA guidance reflects concern over physicians deferring to AI-aided CDS recommendations when pressed for time or uncertain of their own judgments. Is that stance outdated? 

Thumbnail

Perplexity scores improve identification of fraudulent AI writings

Though numerous web-based tools have been created to flag published works that appear suspicious for AI authorship, the performances of these tools has been inconsistent thus far. 

radiology residents give back

Deep learning model enables routine radiographs to be used for osteoporosis screening

Many people with low bone mineral density are not aware of their condition because they fail to get screened through DXA or are not eligible due to age.