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.

Healthcare AI today: Bipartisan AI policy guidance, AI claims denials, LLM brain rot, more
Federal lawmakers have a fresh resource to keep them up on healthcare AI that falls outside of formal FDA oversight. It comes in the form of a new report from the nonprofit Bipartisan Policy Center.
Common features of breast cancers missed by AI
Imaging experts advocate for “meticulous assessments” of cases that include luminal cancer, dense breasts, and lesions located outside the mammary zone, among other factors.
Why do AI-savvy consumers harbor skepticism toward medical AI?
Patients who frequently use AI tend to readily trust AI-assisted diagnoses made by their physicians. Counterintuitively, however, those who would rank themselves among the very best-informed about AI tend to mistrust such diagnoses.
AAA detection gets boost from commercially available AI algorithm
The opportunistic screening helps identify patients in need of monitoring and/or intervention without disrupting workflows.
Healthcare AI today: Senate arguments, aging infrastructure, ‘elastic’ jobs, more
States’ rights or federal power? Senate Republicans are of two minds on AI regulation in the One Big Beautiful Bill.

Why AI models must always be tested on data from outside health systems

Artificial intelligence (AI) tools should always be tested across “a wide range of populations,” according to new research published in PLOS Medicine. The authors shared this warning after seeing some models perform worse when tested on data from an outside health system.

Beatboxers, real-time MRI make a rhythmic duo

Real-time MRI footage of beat boxers was recently presented at a joint meeting of the Acoustical Society of America and the Canadian Acoustical Association in Victoria, British Columbia, Canada on Nov. 7, according to a recent report by Popular Science.

Deep learning improves detection of polyps during colonoscopy

Researchers created and validated a deep learning algorithm to improve the detection of polyps during colonoscopy, according to a study published in the latest issue of Nature Biomedical Engineering.

AI performs poorly when tested on data from multiple health systems

Researchers at the Icahn School of Medicine at Mount Sinai in New York City found convolutional neural networks (CNNs) trained to detect pneumonia on chest x-rays performed poorly when tested on data from outside health systems, according to a study published online Nov. 6 in PLOS Medicine.

How AI can help overburdened radiologists in China

On average, China has two physicians for every 1,000 people and an upwards of 300 million people suffer from chronic diseases, thereby further burdening an already overworked workforce, according to a news report from digital outlet Brink Asia.

Imperial College London to open new medical imaging, AI research center

Imperial College London announced its plans to open the London Medical Imaging and Artificial Intelligence Center for Value-Based Healthcare thanks to £10 million ($13 million) in recently awarded funds, according to a university news release published Nov. 6.

Harvard researchers’ novel molecular imaging technique creates brain 'cellular atlas'

Harvard University researchers used novel molecular imaging technology to make a first-of-its-kind “cellular atlas,” covering a key area in the brain to help study the genetic makeup and function of cells, according to research published online Nov. 1 in Science.

AI tool predicts Alzheimer’s more than 6 years ahead of diagnosis

A deep learning algorithm developed using imaging data from more than 1,000 Alzheimer’s disease (AD) patients can accurately predict the presence of AD more than six years before a doctor finalizes a diagnosis, researchers reported in Radiology Nov. 6.

Artificial Intelligence

Healthcare AI today: Bipartisan AI policy guidance, AI claims denials, LLM brain rot, more

Common features of breast cancers missed by AI

Why do AI-savvy consumers harbor skepticism toward medical AI?

AAA detection gets boost from commercially available AI algorithm

Healthcare AI today: Senate arguments, aging infrastructure, ‘elastic’ jobs, more