New AI tool doubled efficiency in busy university radiology department
Creative artificial intelligence (AI) solutions are being developed to address critical staffing shortages in radiology that could help with similar shortages in overworked pathology and clinical laboratories as well.
In a recent clinical study at 11-hospital Northwestern Medicine, researchers developed a new generative AI radiology tool to assist radiologists that demonstrates high accuracy and efficiency rates when working with multiple types of imaging scans.
For the study, approximately 24,000 radiology reports were analyzed and then compared for clinical accuracy with and without the AI tool. The tool evaluates an entire scan and generates a report that is 95% complete and personalized to each patient. A template based on that report is then provided to radiologists for review, according to a Northwestern Medicine Feinberg School of Medicine news release.
The study reported an average 15.5% increase in radiograph efficiency without compromising accuracy. Some radiologists even produced gains as high as 40%. The radiology reports were scrutinized during a five-month period last year and enabled radiologists to improve the time it took to return a diagnosis.
“This is, to my knowledge, the first use of AI that demonstrably improves productivity, especially in healthcare. Even in other fields, I haven’t seen anything close to a 40% boost,” said the study’s senior author Mozziyar Etemadi, MD, PhD, assistant professor of anesthesiology and biomedical engineering at Northwestern University McCormick School of Engineering, in the news release. (Photo copyright: Northwestern University.)
Doubled Efficiency for One Radiology Team
“For me and my colleagues, it’s not an exaggeration to say that it doubled our efficiency. It’s such a tremendous advantage and force multiplier,” said study co-author Samir Abboud, MD, emergency radiology in the department of radiology at Northwestern Medicine, in the news release.
“Having a draft report available, even before it is viewed by the radiologist, offers a simple, actionable datapoint that can be quickly and efficiently acted upon” added study senior author Mozziyar Etemadi, MD, PhD, assistant professor of anesthesiology and biomedical engineering at Northwestern University McCormick School of Engineering, in the news release. “This is completely different than traditional triage systems, which need to meticulously be trained one by one on each and every diagnosis.”
The AI tool can also alert radiologists to life-threatening conditions.
“On any given day in the ER, we might have 100 images to review, and we don’t know which one holds a diagnosis that could save a life,” Abboud said. “This technology helps us triage faster—so we catch the most urgent cases sooner and get patients to treatment quicker.”
Relying on In-house Data
Engineers at Northwestern developed the AI model using clinical data within the university’s own network, emphasizing that such tools can be created without assistance from other organizations.
“Our study shows that building custom AI models is well within reach of a typical health system, without reliance on expensive and opaque third-party tools like ChatGPT,” Etemadi noted.
The Journal of the American College of Radiology states the supply of radiologists is expected to increase by approximately 26% over the next 30 years. However, the need for radiologists is expected to grow between 17% and 27% over the same period. Becker’s Hospital Review reports there will be a shortage of up to 42,000 radiologists in the US by 2033.
Some health organizations are using a mixed model of permanent employees and contracted radiologists to meet the increasing demand for services. Others are also looking at options such as internal training programs, better benefits for workers, teleradiology, and remote radiologists to fulfill radiology needs.
“You still need a radiologist as the gold standard,” Abboud said. “Medicine changes constantly—new drugs, new devices, new diagnoses—and we have to make sure the AI keeps up. Our role becomes ensuring every interpretation is right for the patient.”
Can pathology practices and clinical laboratories learn from radiology’s situation? Development of AI solutions for those fields would likely have similar effects on workloads and overworked personnel.
Exploring the benefits of AI may be one way of helping meet clinical laboratory and pathology practice staff shortages.
Managers of pathology groups and clinical laboratories can learn from the challenges confronting the radiology profession
Members of the Intersociety Committee of the American Society of Radiology (ACR) recently met in Coronado, Calif., to discuss the “most pressing” challenges to their profession and investigate possible solutions, according to Radiology Business. Many of these challenges mimic similar challenges faced by anatomic pathology professionals.
The radiology leaders identified seven of the “most important challenges facing radiology today.” They include: declining reimbursement, corporatization and consolidation, inadequate labor force, imaging appropriateness, burnout, turf wars with nonphysicians, and workflow efficiency, according to a report on the meeting published in the Journal of the American College of Radiology (JACR).
“Solving these issues will not be easy,” said Bettina Siewert, MD, diagnostic radiologist at Beth Israel Deaconess Medical Center (BIDMC) in Boston, Mass., professor of radiology at Harvard, and lead author of the JACR report, in the JACR. “This is a collection of ‘wicked’ problems defined as having (1) no stoppable rule, (2) no enumerable set of solutions or well-described set of permissible operations, and (3) stakeholders with very different worldviews and frameworks for understanding the problem,” she added.
“The Intersociety Committee is a freestanding committee of the ACR established to promote collegiality and improve communication among national radiology organizations,” JACR noted.
“Taken together, a ‘perfect storm’ of pressures on radiologists and their institutions is brewing,” said Bettina Siewert, MD (above), diagnostic radiologist at Beth Israel Deaconess Medical Center in Boston, Mass., professor of radiology at Harvard, and lead author of the JACR report. Wise pathology and clinical laboratory leaders will see the similarities between their industry’s challenges and those facing radiology. (Photo copyright: Beth Israel Deaconess Medical Center.)
How Radiology Challenges Correlate to Pathology Practices
Here are the seven biggest challenges facing radiology practices today as identified by the Intersociety Committee of the ACR.
Declining Reimbursement: According to the ACR report, radiologists in 2021 performed 13% more relative value units (RVUs) per Medicare beneficiary compared to 2005. However, the inflation-adjusted conversion factor fell by almost 34%––this led to a 25% decline in reimbursements.
This issue has plagued the pathology industry as well. According to an article published in the American Journal of Clinical Pathology (AJCP), prior to adjusting for inflation, the average physician reimbursement increased by 9.7% from 2004 to 2024 for all included anatomic pathology CPT codes. After adjusting for inflation, the average physician reimbursement decreased by 34.2% for included CPT codes. The greatest decrease in reimbursement observed from 2004 to 2024 was for outside slide consultation at 60.5% ($330.12 to $130.49), followed by pathology consultation during surgery at 59.0% ($83.54 to $34.29). The average CAGR was -2.19%,” the authors wrote.
“Our study demonstrates that Medicare physician reimbursement for common anatomic pathology procedures is declining annually at an unsustainable rate,” the AJCP authors added.
The radiologists who identified this trend in their own field suggest that medical societies could lead the push to minimize the reimbursement cuts. Pathologists could also adopt this ‘strength in numbers’ mentality to advocate for one another.
Corporatization Consolidation: The authors of the ACR report identified this issue as limiting job opportunities for radiologists particularly in private practice. Pathology professionals have seen the same trend in their field as well. Increasingly, small pathology groups have been consolidated into larger regional groups. Some of those larger regional pathology groups will then be acquired by public laboratory corporations.
The authors of the ACR report suggest radiologists should be educated on the pros and cons of consolidation. They also suggest pursuing unionization.
Inadequate Labor Force: In both radiology and pathology there is a supply-and-demand issue when it comes to labor. Staffing shortages have been felt across all of healthcare, but particularly among pathology groups and clinical laboratories. Siewert and her co-authors suggest a three-pronged approach to address this issue:
Creating residency positions in private practice.
Recruiting international medical graduates.
Increasing job flexibility.
Pathology professionals could apply these same ideas to help close the gap between the open positions in the field and the number of professionals to fill them.
Imaging Appropriateness: A gap between service capacity and service demand for radiology imaging has created a frustrating mismatch between radiologists and clinicians. Radiology experts point to overutilization of the service causing the supply-and-demand crisis. Comparatively, pathologists see a similar issue in complex cases requiring more pathologist time to come to an appropriate diagnosis and identify a care plan.
“To facilitate this reduction, better data on imaging outcomes for specific clinical questions are urgently needed,” the authors of the ACR report wrote as a possible solution. “Considering the magnitude of the mismatch crisis, radiologists may also need to consider expanding their consultative role to include that of a gatekeeper, as is done in other more resource-controlled countries.”
Burnout: Perhaps one of the most talked about subjects in the medical field has been burnout. The issue has been thrust to the forefront with the COVID-19 pandemic; however, the burnout crisis began before the pandemic. About 78% of radiologists surveyed for this report claimed to be exceeding their personal work capacity.
The authors of the ACR report suggest a structured approach to air grievances without descending into despair. “Using a team approach based on the concept of listen-sort-empower, burnout can be combatted by fostering free discussion between frontline workers and radiologists,” they said. “Facilitators unaffiliated with the radiology department can help to maintain focus on gratitude for positive attributes of the work and the institution as well as to keep the sessions on task and prevent them from devolving into complaint sessions with a subsequent loss of hope.”
A similar approach could be applied to pathology groups and clinical laboratory to combat worker burnout as well.
Turf Wars with Nonphysicians: Over the last five years the number of imaging exams being interpreted by nonphysician providers has increased by 30%, according to the ACR report. The writers emphasized the need for increased understanding and awareness about the importance of physician-led care. They suggest solidarity among hospital medical staff to provide a united front in addressing this issue in hospital bylaws.
In pathology, the counterpart is how large physician groups are bringing anatomic pathology in-house. This has been an ongoing trend for the past 20 years. It means that the pathologist is now an employee of the physician group (or a partner/shareholder in some cases).
Increase Workflow Efficiency: Image interpretation accounts for only 36% of the work radiologists perform, the ACR report noted. This issue has a direct counterpart in pathology where compliance requirements and various tasks take time away from pathologist diagnosis. These issues could be solved by working AI into tasks, delegating non-interpretive tasks to other workers, and improving the design of reading rooms. All of these possible solutions could also be applied to clinical pathologists.
These issues being faced by radiologists compare directly to similar issues in the clinical pathology world. Pathologists and pathology group managers would be wise to learn from the experience of their imaging colleagues and possibly adopt some of the ACR’s suggested solutions.
