Rad AI's New Tool Aims to Improve Accuracy, Quality ...

Rad AI announced its latest speech recognition technology that it says will improve the speed and accuracy of diagnostic reporting.

The new capabilities will be embedded directly into clinicians’ workflow. It will not only transcribe words, but will understand clinical context, recognize uniqueness and adapt to how each radiologist works, the company said.

Rad AI is a generative AI solutions company focused on automative healthcare workflow, specifically in radiology, to save time, reduce burnout and improve patient care.

Why It Matters

This latest advancement reflects Rad AI’s goal of solving the biggest bottlenecks in radiology: time, accuracy and documentation quality.

In a press release, Rad AI CEO Doktor Gurson said radiologists are limited by reporting tools that transcribe words but don’t understand the user behind them.

“[These tools are] still missing subtleties, struggling with clinical terminology and forcing radiologists to spend valuable time correcting basic errors,” he said. “We built this technology to understand context so that radiologists can return focus to diagnosis, not documentation."

At last year's Radiological Society of North America (RSNA) Annual Meeting, Dr. Nina Kottler, associate chief medical officer for clinical AI at Radiology Partners in El Segundo, California, said the current process and technologies in the field are not effective. She said AI tools can help eliminate bias and improve accuracy while also improving workflows to enable radiologists to focus on more complex decision-making.

"There’s a massive amount of information coming into the system, and our turnaround times are increasing," she said at the event. "The goal is an expert radiologist partnering with a transparent and explainable AI system. ... Instead of dictating and reviewing, AI will tell us what it sees and provide an interactive report while automatically performing administrative tasks."

What To Know

Rad AI said its new model can accommodate different accents, overlapping speech and complex medical terminology that often hinders other tools by combining multiple speech engines powered by Rad AI's proprietary modeling and unique "voting" algorithm that determines the most accurate understanding in real time.

The company said this approach will ensure consistent, high-fidelity results in different environments, including quiet reading rooms and louder emergency department workstations.

Early tests of the new model found reports of fewer dictation errors, more natural transcription flow and an overall smoother experience.

North Carolina-based imaging and diagnostics center ARA Health Specialists went live with Rad AI Reporting and AI-powered features in February. A recent analysis found that 79 percent of ARA radiologists improved on efficiency, as measured by median time spent on the report.

Some of the key advancements of the new model include multi-model precision with a proprietary algorithm that compares multiple transcriptions simultaneously to select he most accurate output; adaptive accuracy with custom language models fine-tuned for radiology vocabulary and syntax; workflow intelligence that provides real-time analytics that highlight opportunities to shorten dictation and streamline templates; and seamless integration within the existing Rad AI Reporting interface.

What Happens Next

Rad AI will showcase the new model at the 2025 RSNA Annual Meeting, which runs from November 30 to December 4 in Chicago, Illinois. This will include live demonstrations and interactive sessions throughout the event.

What People Are Saying

Rad AI CEO Doktor Gurson said in a statement: "Every innovation we build starts from the same question: what slows radiologists down? From AI-driven impression generation to now speech intelligence, we're removing friction from the reporting process so radiologists can spend more time on what matters most – their patients."

ARA Health Specialists Chief Operations Officer Joe Guiffrida said in a statement: "Moving to Rad AI was 100 percent the right move for ARA Health, and it's advancing the way that our physicians practice medicine. A transition like this requires a team that listens and responds with urgency. Rad AI has shown that level of partnership from day one. We are already seeing a meaningful impact that will shape how our physicians practice for years to come."

Newsweek reached out to Rad AI for further comment.

Have an announcement or news to share? Contact the Newsweek Health Care team at [email protected].

Request Reprint & LicensingSubmit CorrectionView Editorial & AI Guidelines