Assessing and Implementing Artificial Intelligence in Radiology
In a recent video interview, Nina Kottler, MD, discussed the promise of artificial intelligence (AI) for improving workflow efficiency for radiologists, keys to assessing AI vendors and change management principles for facilitating implementation of AI into one’s practice.
There is fair amount of excitement and hype about the ongoing emergence of artificial intelligence (AI) and the potential promise of the technology in improving diagnostic accuracy and increasing workflow efficiencies in radiology.
However, as Nina Kottler, MD, points out in a recent video interview with Diagnostic Imaging, there are challenges as well when it comes to assessment and implementation of AI into one’s practice. While there are “hundreds of FDA-cleared and approved algorithms in radiology alone,” she notes that it is “early on in the maturity of the technology of AI with respect to health care” so choosing the right AI vendor for your practice is critical.
While technical prowess is important, 80 percent of what an AI vendor does is help create the workflow around the algorithm to ensure it works well, according to Dr. Kottler, the Associate Chief Medical Officer for Clinical AI and VP of Clinical Operations at Radiology Partners. Dr. Kottler says cultural alignment is an important consideration as you are seeking a vendor that values your input as a radiologist and is on a similar wavelength with you on future directions of AI in radiology.
For pertinent insights on the assessment and implementation of AI technology, watch the video below.
Can Emerging AI Software Offer Detection of CAD on CCTA on Par with Radiologists?
May 14th 2025In a study involving over 1,000 patients who had coronary computed tomography angiography (CCTA) exams, AI software demonstrated a 90 percent AUC for assessments of cases > CAD-RADS 3 and 4A and had a 98 percent NPV for obstructive coronary artery disease.
