Saurabh Jha, MD, on GTP-4 passing a mock radiology board exam.

Imaging Wire Sponsors

Annalise.ai  •  Arterys  •  Bayer  •  Blackford  •  CARPL.ai  •  Change Healthcare  •  Enlitic  •  GE HealthCare  •  Hyperfine  •  Intelerad  •  Medality  •  Merge by Merative  •  Nuance  •  Riverain Technologies  •  Siemens Healthineers  •  Subtle Medical  •  United Imaging  •  Us2.ai  •  Visage Imaging

Imaging Service

The Perils of Worklist Cherry-Picking

If you’re a radiologist, chances are at some point in your career you’ve cherry-picked the worklist. But picking easy, high-RVU imaging studies to read before your colleagues isn’t just rude – it’s bad for patients and bad for healthcare.

That’s according to a new study in Journal of Operations Management that analyzes radiology cherry-picking in the context of operational workflow and efficiency. 

Based on previous research, researchers hypothesized that radiologists who are free to pick from an open worklist would choose the easier studies with the highest compensation – the classic definition of cherry-picking.

To test their theory, they analyzed a dataset of 2.2M studies acquired at 62 hospitals from 2014 to 2017 that were read by 115 different radiologists. They developed a statistical metric called “bang for the buck,” or BFB, to classify the value of an imaging study in terms of interpretation time relative to RVU level. 

They then assessed the impact of BFB on turnaround time (TAT) for different types of imaging exams based on priority, classified as Stat, Expedited, and Routine. Findings included:

• High-priority Stat studies were reported quickly regardless of BFB, indicating little cherry-picking impact
• For Routine studies, those with higher BFB had much lower reductions in turnaround — a sign of cherry-picking
• Adding one high-BFB Routine study to a radiologist’s worklist resulted in a much longer increase in TAT for Expedited exams compared to low-BFB studies (increase of 17.7 minutes vs. 2 minutes)
• The above delays could result in longer patient lengths of stay that translate to $2.1M-$4.2M in extra costs across the 62 hospitals in the study. 

The findings suggest that radiologists in the study prioritized high-BFB Routine studies over Expedited exams – undermining the exam prioritization system and impacting care for priority cases.

Fortunately, the researchers offer suggestions for countering the cherry-picking effect, such as through intelligent scheduling or even hiding certain studies – like high-BFB Routine exams – from radiologists when there are Expedited studies that need to be read. 

The Takeaway 

The study concludes that radiology’s standard workflow of an open worklist that any radiologist can access can become an “imbalanced compensation scheme” that can lead to poorer service for high-priority tasks. On the positive side, the solutions proposed by the researchers seem tailor-made for IT-based interventions, especially ones that are rooted in AI. 

Calantic’s AI Use Cases

Calantic Digital Solutions is a radiology AI suite developed to help you focus on providing quality care. Learn about the use cases for Calantic in this InformaticsTECH Talk at SIIM 2023 on Thursday June 15 by Pamela Habib, head of commercial development at Bayer Digital Solutions.

A Major Enabler in Theranostics

StarGuide digital SPECT/CT from GE HealthCare is a major enabler in Theranostics. With the ability to identify bio-distribution and perform dosimetry for therapies like 177Lu, pioneering clinicians rely on StarGuide to monitor therapy.

The Wire

• GPT-4 Passes Mock Board Exam: GPT-4, the latest version of the ChatGPT AI algorithm, was able to pass a mock radiology board exam that GPT-3.5 had failed. In a study in Radiology, researchers said GPT-4 beat GPT-3.5 on a panel of 150 multiple-choice questions with no images (81% vs. 69%, passing is 70%). The study shows the “remarkable improvement” of GPT-4 over the previous version. No word yet on how well ChatGPT does in paying off student loan debt.

• COVID’s Impact on Stroke: COVID-19’s impact on cerebrovascular events is chronicled in a new paper in American Journal of Roentgenology. In a study of 382 unvaccinated stroke patients presenting from March 2020 to April 2021, researchers found that COVID patients with stroke were more likely to have larger infarct sizes, even after reperfusion therapy (77.8mL vs. 18.2mL), and COVID was a predictor for continued infarct growth (OR=5.1). The findings highlight the “severe neurologic sequelae” of COVID-19.

• Internet Abuzz over MRI Accident: The Internet is abuzz over what appears to be the latest MRI accident, this one involving a patient and a metallic sex toy. Various Web forums have included details of the incident, and the story even spurred a Snopes investigation. Their conclusion? The tale has “traits often indicative of misinformation.” However, a borderline NSFW incident report that matches the story was filed to the FDA’s MAUDE database in early April. 

• CCTA for Triple-Rule Out: What’s holding back wider use of CCTA for triple rule-out of people presenting to the ER with acute chest pain? In JACR, Washington researchers proposed that 3D workstations that create MPRs aren’t needed for CCTA of ER patients. In a study of 74 patients they showed transaxial CCTA alone was noninferior to transaxial CCTA and MPRs for detecting coronary stenosis (difference in accuracy = -1.4%). The findings suggest ER guidelines may need updating to support transaxial-only CCTA.

• Ex-Elsevier Editors Find Home: A group of over 40 editors who quit Elsevier over high publishing fees at a pair of its neuroimaging journals have found a new home, starting a new open-access journal called Imaging Neuroscience. The journal is published by MIT Press and will keep publishing fees low, even waiving them for low- and middle-income countries. In a statement, they say the new journal should be fully operational by mid-July. Is it too soon to ask about an impact factor?

• Visage Lands $20M Win: Visage Imaging has landed another large multimillion-dollar enterprise imaging contract, this one with Gundersen Health System, an IDN that runs seven hospitals and 65 clinics across Wisconsin, Minnesota, and Iowa. In a deal worth $20M, Visage will install its cloud-based Visage 7 Enterprise Imaging Platform across the Gundersen network, with first go-lives in the second half of 2023. Visage has been successful in landing large IDNs and health networks, such as deals in Washington and Oregon and the upper Midwest.

• Optimizing AI for Thyroid US: Customizing AI use for certain clinical scenarios could benefit radiologists without slowing them down. In a paper in JAMA Network Open, Chinese radiologists developed an “optimized strategy” that reserved AI as a decision aid for more complex thyroid nodule cases. In a test of 1,754 images, the optimized strategy cut interpretation times for senior radiologists, saving 2.5-2.6 seconds per case, while the traditional strategy of AI as a double-reader was best for junior radiologists. 

• Envision Files for Bankruptcy: As expected, national medical group Envision Healthcare filed for Chapter 11 bankruptcy this week after reaching agreements with lenders to restructure over 60% of its approximately $7.7B in debt. As part of the deal, Envision will spin off its AMSURG ambulatory surgery business. Envision’s rise and fall mirrors the dark side of 21st century American medicine and its relationship with private equity, according to a takedown of the company in liberal website The American Prospect. 

• Philips Launches CT Scanner: The hot midrange CT segment is about to get hotter. Philips has launched CT 3500, a high-throughput scanner targeted for routine radiology and high-volume screening programs. The system includes the company’s CT Smart Workflow AI-powered software for automating tasks such as patient setup. Philips is highlighting CT 3500 at two global shows this month, CMEF 2023 in Shanghai and ROKO 2023 in Germany.

• TeraRecon’s CV Visualization Update: ConcertAI’s TeraRecon announced the launch of Intuition 4.7, featuring a range of structural heart-targeted additions to the company’s flagship advanced visualization product. The new Intuition 4.7 release adds a new LAA workflow, an updated TMVR workflow, and various enhancements intended to streamline coronary imaging and pre-op planning. 

• Bertagnolli Tapped to Lead NIH: The Biden Administration has tapped current NCI director Monica Bertagnolli, MD, to lead the NIH. Bertagnolli’s nomination is drawing support from medical groups, such as a positive statement issued by ASTRO. Bertagnolli is a surgical oncologist who was with Dana Farber Cancer Institute from 2000 until she took over as NCI director in October 2022. The last permanent NIH director was Francis Collins, MD, PhD, who stepped down from the post in December 2021.

Leveraging Data for Better Performance

When RWJBarnabas Health wanted to boost its percentage of radial-access interventional cardiology procedures being performed, they leveraged data from HealthView Analytics, a business intelligence platform by Intelerad subsidiary Lumedx. 

Precision Imaging’s Accelerated Enhancement

When one of Precision Imaging Centers’ 3T MRIs wasn’t meeting their requirements, they implemented Subtle Medical’s SubtleMR solution, rather than purchasing a new scanner or an expensive upgrade. See how SubtleMR enhanced Precision’s patient throughput and comfort, without compromising image quality in this case study.

Annalise.ai’s AI Confidence Bar

Curious how certain your AI is about its own finding? Annalise.ai’s confidence bar displays the likelihood of each finding and the AI model’s level of certainty, helping clinicians perform their interpretations with greater confidence.

The Resource Wire

• The technology behind PACS has been around for decades, but experts still disagree about the benefits and functionality that PACS should provide. Learn what you should be considering when choosing a PACS in this Enlitic white paper. 

• When Sao Paolo’s Diagnosticos da America SA (DASA, the world’s fourth largest diagnostics company) set out to evaluate Qure.ai’s QXR solution for their pediatric chest X-ray workflows, they leveraged CARPL.ai’s platform to streamline their evaluation. See how it worked here.

• Check out this Imaging Wire Show interview with Riverain Technology’s Chief Science Officer, Jason Knapp, where we discuss the evolution of imaging AI, how to get generalizability right, AI’s path forward, and much more.

• Merative’s Merge Imaging Solutions had a big Best in KLAS 2023, winning the Cardiology and Hemodynamics categories, while scoring second-place honors in the Large PACS, Universal Viewer, and VNA categories. Merge Cardio previously scored Best in KLAS for six consecutive years, while Merge Hemo has been ranked #1 for 10 years.

• Trying to decide between public and private cloud? Watch this brief Change Healthcare animation detailing the operational benefits of public cloud hosting for imaging.

• See how United Imaging’s uCT ATLAS combines advancements in image quality, patient comfort, and operator efficiency to bring you one step closer to your masterpiece.

• Now available on-demand: Learn how to optimize your CT workflow from scan to reconstruction in this webinar recording. Find out how NYU Langone Health leverages technologies from Siemens Healthineers to streamline their workflow and improve patient care. 

• How patients interact with a medical device can have as much impact as the device itself. Check out this Q&A with Hyperfine Lead Product Designer Corinne Hay to learn how human factors influence the design of everything from prescription containers to portable MRI systems.

• With burnout and staffing shortages on the rise, and the increasing volume of imaging, radiology teams are searching for solutions. This interactive guide from Nuance can help you create an environment where radiologists thrive by building a powerful imaging strategy with AI-driven, real-time intelligence.

• Why should your health system/imaging organization be considering cloud-based PACS? Find out from real-world, live customers in this video why Visage Imaging’s Visage 7 CloudPACS offers major benefits over the limitations of legacy PACS..

• Today’s employment environment in radiology has never been more challenging. But there are tools you can use to keep your radiologists happy and engaged, according to this white paper from Medality. 

• How can AI be mobilized to automate the fight against heart disease? Us2.ai President Yoran Hummel, PhD, discusses how AI echo can be optimized in an interview on The Medical AI Podcast. 

• Arterys’ Cardio AI solution recently added a new Atrial Volumes feature that allows cardiologists and radiologists to easily quantify volumes for both left and right atria in cardiac MRI images.

• Check out this Blackford Analysis white paper detailing how children’s hospital imaging teams can leverage AI to improve modality throughput and imaging device availability.