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.

Newswatch: AI-eager doctors, AI-reticent buyers, AI cost worriers, more
In medicine’s next chapter, AI literacy will separate physician leaders from peer followers.
7 pointers for AI-driven quality control in medicine
By automating repetitive tasks and ensuring consistent “QC,” well-deployed AI not only unburdens healthcare professionals but also sets new standards for efficiency and reliability in medical practice.
AI-powered risk model evaluates long-term risk of coronary artery disease
The advanced machine learning model tracks more than 50 different factors to make its predictions. It has already been found to be more accurate than popular prediction methods for heart disease that are currently available.
Enforcement of rule regulating discrimination in AI use will start May 1, ACR warns
However, it’s still uncertain whether the Trump administration will follow through with the new HHS policy update.
Only 4% of women comfortable with AI serving as sole reader of mammograms
“Incorporating patient perspectives into AI implementation strategies ensures that these technologies improve and not hinder patient care," one expert contends.

artificial intelligence robot evaluates healthcare data

Rad AI announces new artificial intelligence-powered software for radiology reports

After previewing the new software in September, Rad AI will make it commercially available throughout the United States at RSNA 2023 in Chicago.

FDA clears AI-powered software that pinpoints suspicious findings on chest X-rays

VisiRad XR was developed using curated data sets from across the globe, developer Imidex said in an announcement.

GPT-4, a new upgrade from the team behind ChatGPT, can help doctors with difficult diagnoses

The new and improved AI-based language model outperformed human clinicians in a new study published in JAMA Network Open.

artificial intelligence AI deep learning ChatGPT OpenAI Microsoft Google

AI spots critical heart defects missed by the human eye

“If we can deploy our model on a population-level ECG screening, we would be able to pick up many more of these patients before they have irreversible damage,” a cardiologist behind the new study explained.

Industry Watcher’s Digest

Buzzworthy developments of the past few days.

Race for AI dominance: 5 points to ponder about US v. China

AI that’s intended to let cars drive themselves can be repurposed to let tanks level cities. And AI can just as easily weaponize a virus as diagnose it. These are not secrets.

FDA clears 2 new AI models that help with the diagnosis and treatment of arrhythmias

The two algorithms are now commercially available on a price-per-use basis.

Video of Partho Sengupta, MD, explaining two major shifts in AI for echocardiography at ASE 2023. These include GPT and deep learning to automate measurements. #ASE23 #ASE2023 #ASE #AI

2 key reasons the use of AI in echocardiography is growing

Partho Sengupta, MD, an expert on the use of AI in cardiology, says some of the technologies being developed today will fundamentally change how cardiologists and sonographers do their jobs.

Artificial Intelligence

Newswatch: AI-eager doctors, AI-reticent buyers, AI cost worriers, more

7 pointers for AI-driven quality control in medicine

AI-powered risk model evaluates long-term risk of coronary artery disease

Enforcement of rule regulating discrimination in AI use will start May 1, ACR warns

Only 4% of women comfortable with AI serving as sole reader of mammograms