NC Health System Deploys AI to Predict, Diagnose Lung Cancer

North Carolina-based Atrium Health Wake Forest Baptist has implemented artificial intelligence (AI) and robotics tools to help clinicians predict and diagnose lung cancer to improve early detection.

The AI tool, developed by Optellum, predicts the likelihood of lung cancer based on imaging nodule characteristics. Using these insights, the tool classifies patients into high-risk, intermediate-risk, or low-risk categories. The press release states that Wake Forest Baptist is the first academic medical center in the US to deploy the tech, which is not yet widely available.

The tool, which was trained on over 70,000 computerized tomography (CT) scans, is designed to help radiologists and pulmonologists detect and track suspicious lung nodules, assign risk categories to patients, and verify which patients should receive biopsies and treatments.

By leveraging the tool, the health system also aims to reduce unnecessary biopsies for patients classified as low risk and decrease the number of false-positive results, which can lead to anxiety and additional follow-up imaging for patients.

“We are proud to be an early adopter of proven and innovative technologies that enable our clinicians to identify and treat lung cancer at their early stages when it’s possible to cure the cancer,” said Christina Bellinger, MD, director of Wake Forest Baptist’s interventional pulmonary program and associate professor of pulmonary, critical care, allergy, and immunologic diseases at Wake Forest University School of Medicine, in the press release. “The exciting part of this artificial intelligence lung cancer prediction tool is that it enhances our decision making, helping doctors intervene sooner and treat more lung cancers at an earlier stage.”

In a study published last year, researchers from Wake Forest University School of Medicine and the University of Pennsylvania found that AI-based, computer-aided diagnosis improves risk assessment for indeterminate pulmonary nodules and may help clinicians better recommend earlier treatment options for patients.

Alongside the AI model, the health system implemented a robotic bronchoscopy tool, which assists clinicians in identifying and reaching small or hard-to-reach lung nodules that could get missed or are difficult to access using traditional bronchoscopy.

“This technology is already changing lives,” Bellinger said. “We are getting better samples, diagnosing cancer earlier and improving patient outcomes.”

Other health systems are also turning to these advanced technologies to support their cancer detection and treatment efforts.

Last month, New Jersey-based AtlantiCare shared news of its deployment of AI and robotic bronchoscopy tools.

The health system plans to leverage Optellum’s Virtual Nodule Clinic within its early lung cancer diagnosis program at the heart and lung and cancer care institutes at AtlantiCare Regional Medical Center (ARMC). Care teams will use the tool to identify patient lung cancer risk, biopsy concerning lesions, begin treatments earlier, and improve patient outcomes.

The tool will also automatically alert AtlantiCare's interventional pulmonology team if it detects a nodule during a CT scan performed at ARMC through an integration with the Lung Nodule Clinic’s clinical workflow. This may help clinicians decide whether follow-up is appropriate. If bronchoscopy is needed, clinicians can utilize a robotic bronchoscopy tool to more effectively reach and biopsy suspicious tumors.