California-based Sutter Health is improving how lung cancer is detected and treated. A cross-disciplinary initiative has empowered more than 500 radiologists throughout the system to track incidental pulmonary nodules—small spots in the lungs found on scans performed to detect issues other than lung cancer.
In doing so, Sutter Health’s physicians have doubled their rate of early-stage lung cancer diagnoses. Now, Sutter Health catches more than 70% of lung cancer cases in stages I or II, when patient survival rates are significantly higher.
Sutter Health is part of the AMA Health System Member Program, which provides enterprise solutions to equip leadership, physicians and care teams with resources to help drive the future of medicine.
“It takes my breath away to think about how we inverted that curve—from mostly late-stage diagnoses to now catching over 70% of cases early, when survival is vastly improved and many patients can be treated with curative intent,” said Jason Wiesner, MD, chief radiologist and director of imaging informatics at Sutter Health.
Recognizing the problem
Lung cancer is the deadliest form of cancer, killing more people each year than colon, breast and prostate cancers combined. When diagnosed at a later stage, the five-year survival rate is just 9%. Although early detection can significantly improve outcomes, fewer than one in three cases nationwide are caught early.
Low screening rates are among the challenges. Annual low-dose CT scans are recommended for certain patients who are high-risk, but many patients go unexamined. Even when they undergo imaging for other reasons, such as back pain, trauma or infection, incidental pulmonary nodules often go unnoticed and untracked.
“Radiologists can report on findings that deserve follow-up,, but ensuring that happens requires coordination—and busy primary care physicians can’t do it alone,” Dr. Wiesner said.
No closed-loop system existed to ensure that incidental nodules flagged in radiology reports got a second look.
“We needed a way to track patients with incidental findings so they wouldn’t fall through the cracks,” he said.
Building a closed-loop system
A breakthrough came through a coordinated effort within Sutter Health’s clinical and IT teams. They created a coordinated workflow using Epic’s Result Tracker and augmented intelligence (AI)—often called artificial intelligence.
An AI tool assists radiologists by highlighting nodules as small as 5 mm that could be easily overlooked. With a simple click inside Epic’s Study Review activity, radiologists can now flag those tiny nodules for follow-up. That, in turn, generates an alert in a shared and monitored tracking list.
“AI is crucial to the process,” Dr. Wiesner said. “It helps us make sure we’re not missing small nodules when radiologists are focused on something else on a CT scan, such as fractures or trauma.”
“We use a structured approach guided by the Fleischner Society Guidelines,” he said. “For instance, there’s a defined protocol for a 6 mm nodule in a patient without a smoking history—but not all nodules fit neatly into those criteria.”
Once a nodule is flagged, the review process determines if it should be elevated to a multidisciplinary tumor board. Thoracic surgeons, radiation oncologists and interventional radiologists review the patient’s chart and risk factors, along with the nodule’s location and characteristics.
Most lung nodules can be managed through well-established protocols based on the Fleischner Society Guidelines,” Dr. Wiesner explained. “But when a nodule doesn’t fit the typical pattern, our multidisciplinary team helps navigate the best next steps.”
Now, nearly three-quarters of Sutter Health patients diagnosed with early-stage lung cancer have a disease that is potentially curable with localized treatments such as wedge resection, stereotactic body radiation therapy (SBRT), or minimally invasive procedures like endobronchial resection.
Even more encouraging, the increase in early imaging has led Sutter Health radiologists to detect 31 additional cases of non-lung cancers—found incidentally while evaluating patients for lung cancer screening or follow-up.
From AI implementation to EHR adoption and usability, the AMA is fighting to make technology work for physicians, ensuring that it is an asset to doctors—not a burden.
Expansion of services
One of the program’s drivers is the active participation of nurse navigators who “are superheroes advocating for patients right from the beginning,” Dr. Wiesner said.
Stay up to date on AI
Follow the latest news on AI and its applications and effects for health care—delivered to your inbox.
After a patient is flagged, the nurse navigators initiate contact, confirm appointments and coordinate referrals—proactive, hands-on follow-up that improves adherence and, when needed, speeds interventions.
Dr. Wiesner and his team developed the system with adaptability in mind, with the same infrastructure customized to track other high-risk findings, including brain aneurysms. A 2024 pilot program with neurointerventional radiologists found almost 200 incidental brain aneurysms, and those patients were offered treatment options before the aneurysms had a chance to rupture. Coronary calcifications are next on the list.
“The EHR is the backbone of this program,” he said. “Everyone working in the same instance, with a single medical record across the health system, allows for seamless handoffs.”
Dr. Wiesner also acknowledged that budgetary issues may drive reluctance for some. However, Sutter Health’s leadership believes that if the right care is provided, the return on investment will follow.
“We’re happy to share our results because this is the right thing to do in terms of quality. It also makes financial sense,” he said.
Rethinking radiology
Sutter Health’s embrace of AI-enhanced CTs has driven a cultural change among the radiologists. With AI highlighting possible nodules and Epic facilitating real-time flagging, radiologists now play a more proactive role in guiding patient outcomes.
“Historically, we were trained to complete the report and move on to the next case,” Dr. Wiesner explained. “But this program sparked a shift in mindset. Now, our role doesn’t end when we submit a report, and we are an integral part of a coordinated continuum of care.”
The integration of Epic and AI tools has also empowered radiologists to work more efficiently and with greater precision. The change in workflow has helped reduce variation across Sutter Health’s 10 radiology groups.
“By standardizing how we identify, flag and follow up on nodules, we’ve brought consistency and clarity to a process that used to vary widely,” Dr. Wiesner said.
Educating patients and physicians
Primary care physicians are largely unaware of how many incidental nodules can be cancerous, or how to interpret radiology reports with flagged findings. That made education key to the success of the program.
Sutter Health launched internal communications, organized training sessions and provided documentation to help physicians understand how the Result Tracker works, follow-up processes and how to talk to their patients about their findings.
Encouraging compliance among patients in a way that reduced fear and anxiety was also prioritized.
“We needed to reassure patients that not all nodules are dangerous, while making it clear that follow-up imaging was essential,” said Dr. Wiesner, who again cited the crucial role that nurse navigators play in guiding patients through their care journey. That includes making sure that they understand the doctors’ findings and recommendations, then coordinating next steps.
AI is increasingly used in health care administration or to reduce physician burden, and policy and guidance for both device and non-device use of health care AI is necessary. Recognizing this, the AMA has developed new policy (PDF) that addresses the development, deployment and use of health care AI.
A broader vision
The program's impact reaches beyond lung cancer detection. By developing a reliable, scalable workflow, Sutter Health is setting the foundation for a broader approach to managing incidental findings across all imaging specialties.
“We’re identifying things every day that are potentially life-altering in scans that were ordered for something else completely,” Dr. Wiesner said. “Now, we're turning what used to be missed opportunities into potentially lifesaving interventions.”
These expanded capabilities and insights align with Sutter Health’s commitment to continuous improvement and innovation in patient care. The team is studying how Epic’s AI-extracted findings may enhance tracking even further by turning free-text reports into actionable follow-ups that reduce manual steps for radiologists and coordinators.
A model for modern care
Sutter Health’s incidental pulmonary nodule tracking program demonstrates what is possible when technology, teamwork and patient-centered care are thoughtfully integrated with clear purpose. By investing in a closed-loop workflow, leveraging AI as part of a clinically guided framework, and empowering staff to actively cooperate outside of their traditionally accepted silos, Sutter Health has dramatically improved early lung cancer detection and patient outcomes.
“Invest in your infrastructure and empower your people,” Dr. Wiesner reiterated. “Don’t let these opportunities for early diagnosis slip through the cracks.”
By integrating AI tools, EHR workflows and empowering dedicated human navigators, Sutter Health has created a culture of vigilance, innovation and cooperation that has improved care and outcomes.
