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. 

Industry Watcher’s Digest

Buzzworthy developments of the past few days.

Center for AI Safety extinction statement

Tech thought leaders issue terse warning on humanity’s ‘risk of extinction’ at the hands of AI

Several hundred AI experts, stakeholders and commentators are alerting the world to the technology’s potential for widespread harm. 

artificial intelligence robot evaluates healthcare data

AI organizes heart failure patients into 5 distinct groups, helping cardiologists manage care

Researchers used multiple AI models to evaluate EHR data from more than 322,000 heart failure patients. By identifying these subtypes, the group thinks clinicians could perform better risk assessments and make more informed treatment decisions. 

artificial intelligence in radiology medical imaging interpretation

Interpretive AI for medical imaging: 5 points of skepticism, idealism

Surveying the landscape of interpretive AI in radiology, two researchers note a yawning gap between great expectations set in the recent past and actual clinical implementations as of spring 2023.

ChatGPT fails board certification exam

Industry Watcher’s Digest

Buzzworthy developments of the past few days.

biden administration artificial intelligence

White House spotlights 3 newly added items on AI to-do list

The Biden Administration has refreshed its efforts to encourage AI innovation while mitigating AI risks.

A comparison of standard 2D mammography (right) and digital breast tomosynthesis (DBT), or 3D mammography (left). The DBT creates a data set of 1 mm slices that the radiologist can look through to see more detail in suspect areas and determine if it dense breast tissue is masking a tumor.

Standalone AI excels at reading digital mammograms, but how does it hold up with DBT exams?

Standalone AI can significantly outperform radiologists' sensitivity in reading digital mammograms and has shown potential in DBT exams as well, but experts are not yet ready to hand over the reins.

Artificial intelligence (AI) analysis from a remote ECG monitor showing the AI generated report on the Philips Cardiologs system, during a demonstration of the technology at Heart Rhythm 2023. Photo by Dave Fornell

AI correctly IDs ventricular arrhythmias in 88% of patients with sustained VT

New research suggests AI could offer physicians a new, state-of-the-art approach to sudden cardiac arrest risk management.