Share this article and save a life!
AI is reading scans faster. But is it reading them better?
The radiology world is celebrating speed. AI triage tools now flag critical findings in seconds. Worklists are getting prioritized. Turnaround times are dropping.
And on the surface, that sounds like a win.
But a growing body of evidence is raising an uncomfortable question: when radiologists trust AI-flagged cases too heavily, do they spend less cognitive energy on the cases the AI calls clean?
This is called automation bias, and it is not a new concept in aviation or nuclear safety. It is, however, a newer conversation in diagnostic imaging.
Here is what the research is starting to show:
– AI models are trained on curated datasets. Real-world scans are messier, more diverse, and far less tidy.
– When an AI clears a scan as low priority, radiologists tend to review it faster and with less scrutiny.
– The result is that subtle findings, the ones AI was not trained to detect, slip through at higher rates in AI-assisted workflows than in traditional reads.
This is not an argument against AI in radiology. It is an argument for measuring the right things.
Most radiology AI vendors report performance metrics like sensitivity and specificity on benchmark datasets. What they rarely report is how radiologist behavior changes downstream of the AI recommendation.
That behavioral shift is where the real diagnostic risk lives.
For imaging center leaders and hospital radiology departments, this means the ROI conversation needs to evolve. Faster reads are not the finish line. Fewer missed diagnoses should be.
The most forward-thinking radiology programs right now are auditing AI-assisted reads against gold-standard re-reads. They are tracking not just time saved, but error rates by case priority bucket.
That is the accountability layer most AI implementations are still missing.
If your radiology AI vendor cannot show you miss rate data stratified by AI confidence score, that is a gap worth closing before you expand the deployment.
Speed is a feature. Accuracy is the product.
Are your AI radiology metrics measuring the right outcomes, or just the ones that look good in a board report?
👉 Follow Jonathan Govette, CEO of Oatmeal Health, for daily healthcare insights on LinkedIn. Deeper dives in The Oatmeal Bite on Substack: https://oatmealhealthjonathangovette.substack.com
Share this article and save a life!
Author:
Jonathan Govette is a seasoned healthcare and technology executive with more than two decades of experience building, scaling, and advising digital health companies. He is the Co-Founder and CEO of Oatmeal Health, an AI-driven Lung Cancer Screening and Diagnostics company focused on expanding access to early detection for underrepresented populations, particularly patients served by Federally Qualified Health Centers and value-based health plans.
With a background in engineering, product development, and strategic partnerships, Jonathan has founded and led multiple health technology ventures across clinical care delivery, regulated medical software, and AI-enabled diagnostics. His work sits at the intersection of medicine, technology, and health equity, with a consistent focus on translating complex clinical problems into scalable, real-world solutions.
Jonathan has spent much of his professional life dedicated to improving outcomes for marginalized and underserved communities. He has designed and implemented frameworks that align clinical quality, reimbursement, and technology to sustainably advance health equity at scale. This mission is deeply personal and informs his leadership philosophy and long-term vision for healthcare transformation.
In addition to his operating experience, Jonathan is an author and long-time writer in the healthcare domain, with over 20 years of published work covering digital health, medical innovation, and healthcare systems. He is a frequent mentor to early-stage founders and regularly advises startups on product strategy, partnerships, and go-to-market execution in regulated healthcare environments.
Before entering industry full-time, Jonathan nearly pursued a career in medicine with an early path toward cardiothoracic surgery, an experience that continues to shape his clinical perspective and respect for frontline care delivery.
CEO | Oatmeal Health | AI Lung Cancer Startup | Engineer | Writer | Almost Became a Doctor (Cardiac Thoracic Surgeon) | 3x Health Tech Founder | Startup Mentor | Follow to share what I’ve learned along the way.
