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. 

Thumbnail

AI model could improve early detection of deadly pregnancy complication, new research suggests

Despite the dangers associated with the condition, its presence can often evade detection during pregnancy.

Breast cancer AI ribbon pink artificial intelligence

AI uses pre-op mammograms to predict post-op cancer recurrence

Experts believe the tool could better inform surveillance strategies in women who have been treated for breast cancer.

older basketball player

Cardiac imaging registry expands to include former NBA, NHL players

Former NBA player Muggsy Bogues, who also acted in the 1996 film Space Jam, is one of many athletes now participating in the registry. "I’ve lost too many friends to cardiovascular disease," he said. 

AI robot

3 accomplished AI innovators worry anew over their mind-of-its-own technology

Recent days have seen some nerve-rattling brain dumps about the near future—including five figurative minutes from now—authored by tech luminaries who specialize in AI innovation. 

Mayo clinic surgery workers

Massive strike of 31K workers at Kaiser Permanente enters third week with no end in sight

Contract negotiations began in September but have stalled. Workers walked off the job at dozens of Kaiser hospitals and clinics on Jan. 26. Now the scope of the strike is expanding and there are no new negotiations scheduled. 

lung cancer pulmonary nodule chest

AI-powered lung cancer screening support tool nabs FDA clearance

The software was designed to address issues with inter-reader variability common to LDCT screenings. 

LLM

Large-language AI models aren’t immune to medical misinformation, but they can learn to discern

Medical AI is likely to pass along potentially dangerous misinformation when the distortion comes to the model from a normally trustworthy source using a convincingly authoritative voice. 

New AI foundation model offers wide adaptability across neuroradiology

Unlike most AI tools that were built for specific applications like identifying stroke, the foundation model can be used for a wide array of tasks, as it can learn from other AI frameworks.