Is Head CT Overused in the ED?

A new study suggests that head CT could be overused in the emergency department for patients presenting with conditions like headache and dizziness. Writing in a paper in Internal and Emergency Medicine, researchers looking at CT angiography use at a large medical center found a big increase in CTA utilization – even as the rate of positive findings dropped. 

CTA is a powerful tool that can quickly and efficiently give clinicians information to guide treatment of acute neurovascular conditions like aneurysm and stroke. 

  • As such, many emergency departments have been installing their own CT scanners to enable them to scan emergent patients without transporting them to the radiology department. 

But with great power comes great responsibility, and there is always the temptation to scan first and ask questions later. 

  • To better understand changing CTA use in the emergency setting, researchers from the Harvey L. Neiman Health Policy Institute analyzed CTA exams at a level 1 trauma center that sees about 110k emergency patients a year.

Researchers analyzed 25k ED visits from 2017 to 2021 and correlated them to head and neck CTA exams for headache and/or dizziness, finding …

  • The rate of CTA exams rose 64%, from 7.9% of ED visits to 13%
  • Symptomatic patients were 15% more likely to have a CTA in 2021 versus 2017
  • The rate of positive CTA findings fell 38%, from 17% to 10%
  • Patients with private insurance were more likely to have CTA (OR=1.44)
  • Black patients were less likely to be scanned (OR=0.69)

The researchers said the findings indicate the need for better clinical decision support tools, which they believe can help emergency physicians provide an accurate diagnosis without exposing patients to unnecessary radiation and incurring additional cost. 

The Takeaway

This study further confirms widespread accounts that head and neck CTA is overused and on the rise. As the US government backs off on its attempt to force clinical decision support on referring physicians, it may be up to health systems and providers themselves to ensure more appropriate utilization – in a way that doesn’t rely on heavy-handed tools like prior authorization. 

Imaging and US Healthcare Costs

In the debate over rising US healthcare costs, medical imaging is often painted as a bad guy. But a new study in Health Affairs Scholar claims that since 2010, spending on imaging services has not grown at the same rate as other medical services. 

It’s no secret that the US spends far more on healthcare per capita than other developed countries, spending 16.6% of GDP as of 2022 according to OECD data. 

  • For point of reference, Germany spends 12.7%, France spends 12.1%, and most other developed countries spend under 12% of GDP. 

Reasons why the US is such an outlier have been blamed on a variety of factors, such as pharmaceutical prices, physician salaries, administrative costs, and the fragmented nature of the US healthcare system. 

  • But medical imaging is often singled out for criticism, perhaps due to the high cost of scanners and the explosion of imaging volume since the advent of cross-sectional technologies like CT and MRI in the 1970s and 1980s. 

This has led the US government to exert major pressure on imaging reimbursement in the Medicare and Medicaid systems, starting with the Deficit Reduction Act of 2005 and continuing to the present day, while private insurers have employed tools like prior authorization. 

The new study indicates that these efforts may have accomplished their mission. Researchers from the ACR’s Harvey L. Neiman Health Policy Institute analyzed imaging’s contribution to overall growth of medical costs from 2010 to 2021 in employer-sponsored insurance plans, finding …

  • Spending on medical imaging grew 36% 
  • Spending for all other healthcare services grew 64% 
  • Two-thirds of the growth in imaging spending was due to general price inflation
  • Only one-fifth was due to increased utilization
  • Imaging’s share of total US healthcare spending fell from 10.5% to 8.9%

The findings indicate that efforts by the US government and private payors to drive down imaging utilization are working … but at the price of overworked radiology staff.

  • Imaging cuts could also be leading to patient access issues, as the study found that the percentage of patients undergoing imaging fell from 46% in 2010 to 40% in 2021. 

The Takeaway

The new study reinforces what imaging advocates have been saying for years – that medical imaging isn’t a major cause for runaway healthcare spending in the US. The question is whether anyone outside of radiology is listening.

AI Speeds Up MRI Scans

In our last issue, we reported on a new study underscoring the positive return on investment when deploying radiology AI at the hospital level. This week, we’re bringing you additional research that confirms AI’s economic value, this time when used to speed up MRI data reconstruction. 

While AI for medical image analysis has garnered the lion’s share of attention, AI algorithms are also being developed for behind-the-scenes applications like facilitating staff workflow or reconstructing image data. 

  • For example, software developers have created solutions that enable scans to be acquired faster and with less input data (such as radiation dose) and then upscaled to resemble full-resolution images. 

In the new study in European Journal of Radiology, researchers from Finland focused on whether accelerated data reconstruction could help their hospital avoid the need to buy a new MRI scanner. 

  • Six MRI scanners currently serve their hospital, but the radiology department will be losing access to one of them by the end of the year, leaving them with five. 

They calculated that a 20% increase in capacity per remaining scanner could help them achieve the same MRI throughput at a lower cost; to test that hypothesis they evaluated Siemens Healthineers’ Deep Resolve Boost algorithm. 

  • Deep Resolve Boost uses raw-data-to-image deep learning reconstruction to denoise images and enable rapid acceleration of scan times; a total knee MRI exam can be performed in just two minutes. 

Deep Resolve Boost was applied to 3T MRI scans of 78 patients acquired in fall of 2023, with the researchers finding that deep learning reconstruction… 

  • Reduced annual exam costs by 399k euros compared to acquiring a new scanner
  • Enabled an overall increase in scanner capacity of 20-32%
  • Had an acquisition cost 10% of the price of a new MRI scanner, leading to a cost reduction of 19 euros per scan
  • Was a lower-cost option than operating five scanners and adding a Saturday shift

The Takeaway

As with last week’s study, the new research demonstrates that AI’s real value comes from helping radiologists work more efficiently and do more with less, rather than from direct reimbursement for AI use. It’s the same argument that was made to promote the adoption of PACS some 30 years ago – and we all know how that turned out.

Study Shows AI’s Economic Value

One of the biggest criticisms of AI for radiology is that it hasn’t demonstrated its return on investment. Well, a new study in JACR tackles that argument head on, demonstrating AI’s ability to both improve radiologist efficiency and also drive new revenues for imaging facilities. 

AI adoption into radiology workflow on a broad scale will require significant investment, both in financial cost and IT resources. 

  • So far, there have been few studies showing that imaging facilities will get a payback for these investments, especially as Medicare and private insurance reimbursement for AI under CPT codes is limited to fewer than 20 algorithms. 

The new paper analyzes the use of an ROI calculator developed for Bayer’s Calantic platform, a centralized architecture for radiology AI integration and deployment. 

  • The calculator provides an estimate of AI’s value to an enterprise – such as by generating downstream procedures – by comparing workflow without AI to a scenario in which AI is integrated into operations.

The study included inputs for 14 AI algorithms covering thoracic and neurology applications on the Calantic platform, with researchers finding that over five years … 

  • The use of AI generated $3.6M in revenue versus $1.8M in costs, representing payback of $4.51 for every $1 invested
  • Use of the platform generated 1.5k additional diagnoses, resulting in more follow-up scans, hospitalizations, and downstream procedures
  • AI’s ROI jumped to 791% when radiologist time savings were considered
  • These time savings included a reduction of 15 eight-hour working days of waiting time, 78 days in triage time, 10 days in reading time, and 41 days in reporting time  

Although AI led to additional hospitalizations, it’s possible that length of stay was shorter: for example, reprioritization of stroke cases resulted in 264 fewer hospital days for patients with intracerebral hemorrhage. 

  • Executives with Bayer told The Imaging Wire that while the calculator is not publicly available, the company does use it in consultations with health systems about new AI deployments. 

The Takeaway

This study suggests that examining AI through the lens of direct reimbursement for AI-aided imaging services might not be the right way to assess the technology’s real economic value. Although it won’t settle the debate over AI’s economic benefits, the research is a step in the right direction.

MSK Problems Weigh Down Interventional Radiologists

Musculoskeletal problems are common among interventional radiologists, caused by many hours wearing heavy radiation protection gear. That’s according to a new study in European Journal of Radiology which found that almost half of interventionalists suffered from multiple orthopedic problems, issues that forced a significant portion to either reduce or stop their interventional practice. 

Interventional radiology has been responsible for major improvements in patient care through image-guided procedures that are noninvasive and can eliminate the need for open surgery, reducing patient recovery times to hours rather than days.

  • But these advances can come at the cost of higher radiation doses to the personnel who perform and assist with interventional radiology procedures, which has led to issues such as higher breast cancer rates among women who work with image-guided procedures and even DNA damage in cases of long-term exposure.

Radiation protection gear is worn by interventionalists to mitigate that radiation risk, but this gear is heavy and can carry risks of its own, which were investigated by researchers from the University Hospital Marburg in Germany. They conducted a 17-question survey of orthopedic problems among interventional radiologists, receiving 221 responses indicating that …

  • Some 48% of responders experienced more than five orthopedic problems during their interventional career
  • Problems of the lumbar spine were reported by 82% of respondents, followed by cervical spine (33%), shoulder (29%), and knee (25%)
  • Orthopedic problems caused 16% of respondents to reduce their interventional activities, and 2.7% to stop their practice altogether
  • Just 16% of respondents said they had never experienced an orthopedic problem in their career

The new findings track with previous research highlighting the toll that radiation protection gear takes on interventional personnel. The researchers said that one positive finding of their study was that all interventional radiologists reported wearing radiation protection, although fewer respondents reported using radiation glasses (49%) or visors (11%) despite radiation’s known risk of cataracts.

The Takeaway

This study indicates that interventional radiologists are caught between a rock (radiation dose) and a hard place (orthopedic problems). Relief could come from companies that are developing radiation protection solutions such as free-hanging radiation protection gear; for interventional personnel, these options can’t come soon enough.

Predicting Patient Follow-Up for Imaging Exams

There’s nothing more frustrating than patients who don’t comply with follow-up imaging recommendations. But a new study in JACR not only identifies the factors that can lead to patient non-compliance, it also points the way toward IT tools that could predict who will fall short – and help direct targeted outreach efforts.

The new study focuses specifically on incidental pulmonary nodules, a particularly thorny problem in radiology, especially as CT lung cancer screening ramps up around the world.

  • Prevalence of these nodules can range from 24-51% based on different populations, and while most are benign, a missed nodule could develop into a late-stage lung cancer with poor patient survival. 

Researchers from the University of Pennsylvania wanted to test a set of 13 clinical and socioeconomic factors that could predict lack of follow-up in a group of 1.6k patients who got CT scans from 2016 to 2019. 

  • Next, they evaluated how well these factors worked when fed into several different types of homegrown machine learning models – precursors of a tool that could be implemented clinically – finding …
  • Clinical setting had the strongest association in predicting non-adherence, with patients seen in the inpatient or emergency setting far more likely skip follow-up compared to outpatients (OR=7.3 and 8.6)
  • Patients on Medicaid were more likely to skip follow-up compared to those on Medicare (OR=2)
  • On the other hand, patients with high-risk nodules were less likely to skip follow-up compared to those at low risk (OR=0.25) 
  • Comorbidity was the only one of the 13 factors that was not predictive of follow-up 

The authors hypothesized that the strong association between clinical setting and follow-up was due to the different socio-demographic characteristics of patients typically seen in each environment. 

  • Patients in the outpatient setting often have access to more resources like health insurance, transportation, and health literacy, while those without such resources often have to resort to the emergency department or hospital wards when they become sick enough to require care.

In the next step of the study, the data were fed into four types of machine learning algorithms; all turned in good performance for predicting follow-up adherence, with AUCs ranging from 0.76-0.80. 

The Takeaway

It’s not hard to see the findings from this study ultimately making their way into clinical use as part of some sort of commercial machine-learning algorithm that helps clinicians manage incidental findings. Stay tuned.

AI Powers Two-for-One Screening

In our last issue, we described how effective coronary artery calcium scoring is in predicting future major adverse cardiovascular events. This week, we’re highlighting new research in AJR showing how – thanks to AI – CAC scoring can be performed on CT lung cancer screening exams, giving radiologists a two-for-one screening test.

Using data from one screening exam to also look for other diseases – known as opportunistic screening – has become a hot topic as a way to make screening even more clinically and economically effective. 

In the new study, South Korean researchers leveraged the country’s CT lung cancer screening program to also screen for CAC, a known marker for future cardiac events

  • They took two commercially available CAC scoring algorithms – Coreline Soft’s Aview CAC and Siemens Healthineers’ syngo Calcium Scoring – to analyze 1k low-dose CT chest images acquired from 2017-2023 as part of the national lung screening program. 

AI results were compared to radiologists’ interpretations of CAC presence and severity, finding … 

  • Substantial agreement between both the AI algorithms and the interpreting radiologists for CAC presence and severity (kappa=0.793 & 0.671)
  • The AI algorithms judged CAC to be more prevalent than radiologists (57-60% vs. 53%)
  • AI was more likely to judge CAC severity as mild (35-40% vs. 28%)
  • But less likely to grade it as severe (6.2%-7.3%  vs. 15%)
  • MACE incidence varied by CAC severity: no CAC (1.1-1.3%), mild (3-5%), moderate (2.9-7.9%), and severe (8.6-11%)

The researchers noted that, as with other studies, MACE incidence increased with CAC severity, underlining the importance of coronary calcium evaluation and supporting the use of CT lung screening for CAC detection. 

The Takeaway

Studies like this highlight the exciting role AI can play in making opportunistic screening a reality. With AI at their side, radiologists will be able to play an even more important role in catching disease early, when it can be treated most effectively.

More Support for Cardiac CT’s Value

A new study in Radiology offers more support for the value of CT-based coronary artery calcium scoring, finding that people with higher CAC scores had worse outcomes, and suggesting that those with scores of 0 could potentially avoid invasive coronary angiography. 

Evidence has been building that by measuring calcium buildup in the heart, CAC scores can predict clinical outcomes, in particular major adverse cardiac events, particularly in patients with stable chest. 

  • Studies ranging from MESA to SCOT-HEART to PROMISE have found that patients with CAC scores of 0 have MACE risk that’s lower than 2% – meaning they could be discharged without further invasive workup. 

The new study is an update to the DISCHARGE trial, which in 2022 published results comparing a CT-first evaluation strategy to one with invasive coronary angiography. The new study investigates the value of CAC scoring by analyzing its prognostic power in patients with stable chest pain who were referred for invasive coronary angiography. 

  • The DISCHARGE study is notable for its diversity – 26 clinical centers in 16 European countries – as well as its use of 13 different models of CT scanners from all four major CT OEMs from 2015 to 2019. 

In all, 1.7k patients were studied, and CAC scores were generated based on CT scans and used to stratify patients into one of three groups; they were then followed for 3.5 years and rates of MACE were correlated to CAC levels, finding … 

  • Patients with CAC scores of 0 had the lowest rates of MACE compared to those with scores of 1-399 and ≥400 (0.5% vs. 1.9% & 6.8%)
  • Rising CAC scores corresponded to higher prevalence of obstructive coronary artery disease (0=4.1% vs. 1-399=29.7% & ≥400=76%)
  • Revascularization rates rose with CAC scores (0=1.7% vs. ≥400=46.2%)

While the authors steered away from commenting on the study’s impact on clinical management, the findings – if confirmed with additional studies – suggest that stable chest pain patients may not need invasive coronary angiography.

  • And in another interesting wrinkle to the study, the researchers pointed out that 57% of the DISCHARGE study’s patient population were women, a fact that addresses sex bias in previous research. 

The Takeaway

The DISCHARGE study’s findings are yet another feather in the cap for cardiac CT, with higher CAC scores indicating the long-term presence of atherosclerosis. Should they be confirmed, individuals with stable chest pain in the future will benefit from less invasive – and less expensive – management.

ECR 2024 Video Highlights

The theme of ECR 2024 was Next Generation Radiology, and those who were in attendance at Austria Center Vienna truly got a glimpse of what the future of medical imaging will look like. 

From the latest in cutting-edge AI research to new developments for classic technologies like radiography, ECR 2024 spotlighted why radiology has a bright future ahead. 

In this special edition of The Imaging Wire newsletter, we offer a recap of our ECR video interviews with thought leaders and imaging vendors from the exhibit floor. 

We hope you enjoy watching our coverage as much as we enjoyed producing it! Check out the links below or visit the Shows page on our website, and keep an eye out for our next Imaging Wire newsletter on Thursday.

MASAI Gets Even Better at ECR 2024

One of the biggest radiology stories of 2023 was the release of impressive interim results from the MASAI study, a large-scale trial of AI for breast screening in Sweden. At ECR 2024, MASAI researchers put an emphatic cap on the conference by presenting final data indicating that AI could have an even bigger impact on mammography screening than we thought. 

If you remember, MASAI’s interim results were published in August in Lancet Oncology and showed that ScreenPoint Medical’s Transpara AI algorithm was able to reduce radiologist workload by 44% when used as part of the kind of double-reading screening program that’s common in Europe.

  • Another MASAI finding was that AI-aided screening had a 20% higher cancer detection rate than conventional double-reading with human radiologists, but the difference was not statistically significant. 

That’s all changed with the final MASAI results, presented at ECR on March 2 by senior author Kristina Lång, MD, of Lund University.

  • Lång presented data from 106k participants who were randomized to either screening with Transpara V. 1.7 or conventional double reading without AI.

Transpara triaged mammograms by giving them a risk score of 1-10, and only those classified as high risk received double reading; lower-risk mammograms got a single human reader. In the final analysis, AI-aided screening … 

  • Had a 28% higher cancer detection rate per 1k women (6.4 vs. 5.0), a difference that was statistically significant (p=0.002)
  • Detected more cancers 10-20 mm (122 vs. 79)
  • Detected more cancers of non-specific histologic type (204 vs. 155)
  • Detected 20 more non-luminal A invasive cancers and 12 more DCIS grade 3 lesions

The Takeaway

When combined with the Lancet Oncology data, the new MASAI results indicate that AI could enable breast radiologists to have their cake and eat it too: a lower workload with higher cancer detection rates. 

Get every issue of The Imaging Wire, delivered right to your inbox.

You might also like..

Select All

You're signed up!

It's great to have you as a reader. Check your inbox for a welcome email.

-- The Imaging Wire team

You're all set!