Diagnostic imaging is a common part of medicine today. It helps doctors find and diagnose many health issues. Sometimes, doctors find things they were not expecting. These are called incidental findings. They might show early signs of diseases like lung nodules or adrenal masses. These findings need follow-up checks.
In many U.S. health systems, such as hospitals and outpatient clinics, follow-up steps are often not connected well. This causes delays or no follow-up, which can make patients sicker. Studies show that missed follow-up on lung findings alone has caused $43 million a year in malpractice costs across the country. This shows why better, technology-based systems are needed.
One strength of the AI program at Northwestern Medicine is teamwork from many departments. Radiology, Quality, Safety, Process Improvement, Primary Care, Nursing, Informatics, and others worked together.
This teamwork helped build an AI system that sends alerts inside the doctors’ regular work systems. Alerts come as Best Practice Advisories (BPAs). They show important info about incidental findings and how to order follow-up tests. This setup helps avoid alert overload and lets doctors respond in time.
The AI uses natural language processing (NLP) to read radiology reports and find notes about incidental findings needing follow-up. Lung and adrenal findings were the first focus.
From December 2020 over the next year, the system checked more than 460,000 imaging studies. About 23,000 reports (5%) had flagged lung findings that required follow-up. This meant about 68 patients each day needed extra care, a large number that older systems could not handle well.
Because alerts appeared right in the doctors’ EHR workflow, follow-ups were easier to track and schedule. Nurses contacted patients who could not use online portals, making sure none missed needed follow-up talks.
Dr. Mozziyar Etemadi, Medical Director of Advanced Technologies at Northwestern Medicine, says delayed follow-up on incidental findings causes harm that can be prevented. He explains that the AI is not made to take the place of doctors. Instead, it helps by pointing out possible problems and making workflows smoother.
Doctors and radiologists still make the final calls on further tests and treatment. The AI gives alerts and tools that help make these decisions faster and safer. This cuts down the chance of missing incidental findings when clinics are busy.
Jane Domingo, the program’s lead author, adds that the AI system sends extra patient notices as a safety net. Patients get informed through safe online portals so they can watch their health and ask for care when needed.
Data labeling is when large numbers of radiology reports are marked up to teach NLP algorithms. Northwestern Medicine chose nurses and frontline staff on light duty to do this work instead of paying outside companies.
These trained workers picked out important text from reports. This helped the AI learn better and kept data quality high. This approach saved money and gave expert-reviewed data to improve the system’s accuracy.
After success with lung and adrenal findings, Northwestern Medicine is adding more incidental findings to the AI program. They will include liver, thyroid, and ovarian imaging studies. This aims to lower missed or late care for more types of findings, helping healthcare become more reliable and safe.
Making workflows smooth is very important when using AI in busy clinics and hospitals. Putting AI alerts into the current EHR system helps doctors accept and act on incidental findings quickly.
For clinic managers and IT teams, using such workflow automation means choosing AI tools that fit well with existing clinical work. This helps improve efficiency and cut risks to patient safety.
For practice owners and managers in the U.S., missed or late follow-up on incidental imaging findings is a big problem. It can cause lawsuits, raise healthcare costs, and hurt patient care. Over $43 million a year is spent on lawsuits from missed lung findings alone.
Healthcare practices that use solid AI alert systems get benefits like:
IT departments are important for adding AI tools into EHR systems, protecting data, teaching users, and keeping systems working well.
Making good AI healthcare tools needs people from many fields. At Northwestern Medicine, teams from clinical, admin, tech, and operations worked together to create helpful tools for doctors and patients.
By combining experts from different areas, the AI system built was useful for clinical care, practical to run, and focused on patient safety. Medical practices in the U.S. that want to lower missed incidental imaging follow-ups and improve care can learn from this by using teamwork and adding AI workflow tools carefully.
The article addresses the problem of delayed and missed follow-up on incidental diagnostic imaging findings, which can lead to patient harm and increased healthcare costs.
The AI system uses natural language processing (NLP) integrated with the electronic health record (EHR) to automatically identify radiology reports with incidental findings requiring follow-up and triggers alerts within the physician’s workflow.
The AI facilitates physician decision-making by identifying reports and triggering alerts but does not make clinical decisions, which remain the responsibility of radiologists and ordering physicians.
Physicians receive a Best Practice Advisory (BPA) alert directly within the EHR, which displays findings and provides workflows to order appropriate follow-up studies.
Patients receive notifications through their online portals with study results; if they do not use the portal or have no primary physician, follow-up nurses manage direct outreach to ensure care continuity.
In one year, over 460,000 imaging studies were screened with 23,000 lung findings flagged requiring follow-up, demonstrating the prevalence of incidental findings and effectiveness of the AI alert system in managing follow-ups.
Northwestern Medicine used trained nurses and front-line staff on light-duty to annotate and label relevant radiology report data in-house, ensuring high-quality, expert-reviewed data effectively and cost-efficiently.
A multidisciplinary team from Radiology, Quality, Patient Safety, Process Improvement, Primary Care, Nursing, Informatics, and others collaborated to design and implement the AI follow-up alert system.
Integration ensures alerts appear in the existing physician workflow without requiring additional software access, improving usability and response time to incidental findings.
Yes, the system is being expanded to cover hepatic, thyroid, and ovarian findings requiring follow-up to further reduce missed or delayed care across more conditions.
Simbo is using AI agents to automate all phone related workflows. Connect now to know more.
Schedule AI Agents Demo Now© Since 2019, Simbo AI.
