en.Wedoany.com Reported - NodeAI recently launched a clinical trial at the University Health Network (UHN) to validate the ability of its AI algorithm to predict lymph node malignancy in real time during endobronchial ultrasound (EBUS) procedures. The trial is being conducted at Toronto General Hospital, the institution where EBUS technology was first validated through a landmark clinical trial in 2011.
Each year, over 270,000 patients in North America alone undergo endobronchial ultrasound. This minimally invasive biopsy technique, known as EBUS-TBNA, was pioneered at Toronto General Hospital in the late 1990s and revolutionized lung cancer diagnosis. It has largely eliminated the need for open-chest surgery and is now the global standard of care. However, approximately 40% of cases yield inconclusive results because the procedure's effectiveness heavily depends on the operator's experience and training. Inconclusive results lead to diagnostic delays and repeat biopsies, adversely affecting patient outcomes.
Hamilton-based healthcare AI startup NodeAI was founded to address this issue. Dr. Kazuhiro (Kazu) Yasufuku, a co-developer of the EBUS-TBNA technique and currently the Director of Endoscopy and Interventional Thoracic Surgery at UHN and a member of NodeAI's advisory board, is also involved. He participated in the landmark 2011 clinical trial that validated EBUS technology. The EBUS-TBNA pioneered by Dr. Yasufuku at Toronto General Hospital replaced mediastinoscopy—a procedure requiring general anesthesia, a neck incision, and the use of rigid steel instruments to access the chest cavity. EBUS reduces the procedure time to under 15 minutes, allows patients to go home the same day, and became the global gold standard within a decade. By 2020, an estimated 650,000 lung cancer cases had been diagnosed using this technique. Dr. Yasufuku was awarded the Japan Prize for Medical Research and Development by then-Prime Minister Shinzo Abe.
"As a co-developer of EBUS-TBNA, it is exciting to see AI help unlock the next generation of precision diagnostics. NodeAI's approach is scientifically credible because it is built on validated surgical anatomy, real imaging data, and clinically meaningful patterns that experienced bronchoscopists recognize every day. NodeAI has the potential to improve diagnostic yield, accelerate the dissemination of expertise, and ultimately benefit patient care globally," said Dr. Yasufuku.
The NodeAI platform integrates directly into existing EBUS clinical workflows through a cloud-based interface. During the procedure, the AI analyzes ultrasound video in real time, detects lymph node anatomy, identifies nodal stations, and generates malignancy predictions before the biopsy needle is deployed. The system is vendor-agnostic and requires no hardware changes. The algorithm is based on over seven years of clinical research and one of the world's largest EBUS video datasets, co-developed by thoracic surgeon Dr. Waël Hanna and AI scientist Anthony Gatti, both co-founders of NodeAI.
"EBUS changed everything about how we stage lung cancer," said Dr. Hanna. "But the procedure's effectiveness depends on the operator, which creates an equity issue. A patient at a large academic center with an experienced bronchoscopist gets a different outcome than a patient at a community hospital. AI can close that gap. This trial is designed to prove that."
The trial will enroll 100 patients at Toronto General Hospital over three months. The primary endpoint is NodeAI's ability to successfully process EBUS images and return real-time predictions at a rate exceeding 90%, meaning over 90% of all images captured during the procedure. The trial will assess whether NodeAI's real-time AI guidance improves diagnostic yield compared to standard EBUS practice, with a focus on reducing inconclusive results and minimizing variability between operators.
"There is no more credible place in the world to validate EBUS technology than Toronto General Hospital," said Dr. Hanna. "This is where the technology was born. Conducting this trial under Dr. Yasufuku's leadership provides the scientific foundation we need to ensure we are creating a technology that can help every patient fighting lung cancer."
Lung cancer kills more people in Canada than any other cancer, with an estimated 33,000 new diagnoses expected in 2025. Globally, it is the leading cause of cancer-related death. Accurate and timely staging determines whether a patient receives surgery, chemotherapy, radiation, or palliative care. NodeAI's broader ambition is to make expert-level EBUS accessible everywhere—not just in academic medical centers. The company's subscription-based model is designed for deployment in high-volume hospitals as well as smaller community sites that perform EBUS but have limited expertise.
This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com
