Uncategorized

The Case for POCUS | X-Ray Shakeup | Radiology Corporatization

“Become a self-proclaimed ‘tech evangelist,’ advisor and keynote speaker, but don’t actually do any development.”

A Twitter response from radiologist and Kheiron Medical clinical director, Dr. Hugh Harvey, to a question about how to “make money with AI.” This was more criticism/observation than advice, we think.


Imaging Wire Sponsors

  • Carestream – Focused on delivering innovation that is life changing – for patients, customers, employees, communities and other stakeholders
  • Focused Ultrasound Foundation – Accelerating the development and adoption of focused ultrasound
  • Medmo – Helping underinsured Americans save on medical scans by connecting them to imaging providers with unfilled schedule time
  • Nuance – AI and cloud-powered technology solutions to help radiologists stay focused, move quickly, and work smarter
  • Pocus Systems – A new Point of Care Ultrasound startup, combining a team of POCUS veterans with next-generation genuine AI technology to disrupt the industry
  • Qure.ai – Making healthcare more accessible by applying deep learning to radiology imaging

The Imaging Wire



The Case for POCUS

Every once in a while, the results of a clinical study could double as a marketing case study. This is one of them. Harvard Medical researchers revealed some pretty compelling evidence on the savings that community emergency departments can achieve by using point‐of‐care ultrasound. Here’s what they discovered:

  • The Study – During 15 shifts over three months, the researchers interviewed ED physicians whenever they used POCUS, asking questions about POCUS’ clinical role and the tests it was able to replace. They then calculated the savings achieved by avoiding these tests based on CMS and FairHealth data.
  • The Results – POCUS helped clinicians change patient management plans in 33% of encounters (16 out of 49), eliminating an average of $1,134 in testing costs among patients with private coverage, $2,826 for out‐of‐network patients or patients without coverage, and $181 for CMS patients.
  • Conclusion – Unsurprisingly, the team found that POCUS drives significant ED cost savings, especially when it’s incorporated earlier in a patient’s journey and when it’s integrated into clinical management. This was even true for cases where POCUS didn’t change how a patient is managed.



X-Ray Tech’s 21 Year Shakeup

South Korean scientist Dr. Lee Cheol-jin developed a carbon nano X-ray tube that he believes will “shake up the 123-year-old X-ray technology from its foundation,” but it wasn’t easy.

  • Dr. Cheol-jin Perseveres – South Korean news publisher donga.com reveals that Dr. Lee Cheol-jin “made the accomplishment after over 20 years of hard work although fellow researchers left him one after another because the research did not seem to have any ray of hope at the end of the tunnel. Even though Lee had [a] hard time securing funding for his unpopular research and made many trials and errors, he did not give up.” That’s two years longer than Andy Dufresne spent at Shawshank.
  • Carbon Nano Differentiator – The carbon nano X-ray tube is reportedly 100-times more efficient than current X-ray tech and can immediately be applied to existing medical equipment. Just as importantly for donga.com’s South Korean audience, the new tech has a chance of breaking up Japanese and U.S.-based companies’ X-ray tech dominance, noting that South Korea has a competitive advantage with carbon nano technology but limited access to traditional X-ray semiconductor materials. Dr. Lee Cheol-jin has already filed for 13 patents and is in talks with foreign and domestic corporations to commercialize the tube.

It’s hard to predict whether this new technology will actually shake up the industry’s foundation, but we love stories like this and Dr. Lee Cheol-jin’s perseverance.



Radiology Corporatization

Although the folks on certain industry message boards clearly have their minds made up about the corporatization of radiology (they hate it), a new white paper published in JACR shares a more objective view on the causes and implications of this trend. Here are some big takeaways:

  • Reasons – Much like other specialties, the radiology practice consolidation trend has a wide range of largely-financial drivers (falling reimbursements and rising expenses, legislation changes, the value-based shift, growing private equity interest). This trend is also driven by the fact that radiology practices remain largely fragmented, with only 6% of radiologists in the U.S. employed by a corporate firm.
  • Opportunities – Although some may argue that this trend provides the greatest opportunities for partners looking to exit (they wouldn’t be wrong), the report highlights other benefits of corporatization including improved scale, financial flexibility and capital access, and operational efficiency.
  • Concerns – As expected, there are a range of radiologist-based (high productivity demands, specialty commoditization, work culture, altered partner paths) and care-based concerns (geographic consolidation, reduced quality due to pressured radiologists) surrounding the corporatization trend.

This is a useful paper given the high level of emotions involved in the corporatization trend and the fact that it doesn’t seem to be slowing down.


The Wire

  • University of Alberta spinoff, Medo.ai, shared an update on its still in-development app that allows minimally-trained clinicians (just 1hr of training) to create 3D images from point-of-care ultrasound scans that are then uploaded for AI-based analysis. Medo.ai’s app will initially focus on diagnosing hip dysplasia in infants (easy to treat, but easy to miss) and the firm is already testing applications for other injuries and conditions.
  • Imago Systems announced a “know-how license” collaboration with Mayo Clinic, with Mayo providing clinical trial support for Imago’s ICE Reveal breast imaging “visual intelligence” software as well as an unspecified level of funding. Imago ICE Reveal uses algorithms that “re-visualize” grayscale images to create new images with more diagnostic information, initially targeting mammography but potentially supporting all modalities.
  • Research from the University of Texas Southwestern Medical Center detailed how declining interest in pediatric radiology between 2013 and 2018 (and only a 4-fellow increase in 2019) is impacting care, while predicting that interest in the sub-specialization will continue to wane. The most direct victims of this trend are current pediatric radiologists, who are reporting burnout “at alarming rates,” but the paper warned that this shortage may also lead to lower clinical quality (due to more diagnosis from non-radiologists), lower salaries (due to increases in “percentile benchmarks for productivity”), and greater turnover and unhappiness.
  • New research published in JVIR reveals that radiologists significantly increased their share of paracentesis (70% to 80%) and thoracentesis procedures (47% to 66%) performed between 2004 and 2016 (compared to non-radiologists). Radiologists’ dominance with these procedures was particularly evident on weekdays (vs. weekends), while there were no major differences in terms of procedure complexity between rads and non-rads.
  • A Brigham and Women’s team found that natural language processing (NLP) may be a valuable way to identify patients with implantable devices before MRI scans, which is a big deal considering that only up to 45% of patients properly fill out their MRI safety questionnaires. The team trained two different NLP approaches (expert-derived and ontology-derived) on 25k radiology reports, 175k ED notes, and 41k “other” clinical reports and tested them against 465 reports. The two methods achieved similar accuracy (0.83 vs. 0.91), sensitivity (0.88 vs. 0.96), and specificity (0.82 vs. 0.92), spotting implantable devices in 1.47% to 1.88% of reports.
  • Research published in the American Academy of Pediatrics found that screening children for cervical spine injury (CSI) risk factors could cut unnecessary CT scans in half, noting that CSI models exist for adults but not children. The study looked at 4,091 children who suffered from blunt trauma (1.8% had CSIs), using 14 factors associated with CSI (e.g. car crashes, pain, mobility) to develop a pair of models that identified CSIs with 90.5% & 92% sensitivity and 45.6% and 50.3% specificity.

The Resource Wire

– This is sponsored content.

  • This Nuance case study details why the Hospital for Special Surgery chose to #ditchthedisk and how they benefited from moving to the Nuance PowerShare Network.
  • Did you know that imaging patients are most likely to no-show for their procedures on Mondays and Saturdays? By partnering with Medmo, imaging centers can keep their schedules full, despite the inevitable Monday no-shows.

You're signed up!

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

-- The Imaging Wire team