“We will never solve the burnout problem in healthcare until we solve the business model problem in healthcare. Talking about, writing about, tweeting about burnout might make us feel better (momentarily), but we need to scale models that truly reward health, not volume. Not FFS.”
A tweet from physician and healthcare executive, Sachin H. Jain, MD.
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
Big AHRA Takeaways
AHRA 2019 was a blast. It was so good to learn more about this crucial part of radiology and it as great to meet more readers face-to-face. Here’s The Imaging Wire’s big takeaways from AHRA 2019:
- All About Education and Certification – Don’t let the keynote’s opening dance routine to Poison’s ‘Nothin’ But A Good Time’ fool you. AHRA 2019 was serious about education and boosting the role of its CRA (Certified Radiology Administrator) designation. The AHRA team consistently encouraged its members to attain the designation and reiterated its goal to make CRA a job requirement for radiology department leadership positions.
- Awesome, Awesome Attendees – This might be old news to AHRA vets, but the people of AHRA actually call this the “Family Reunion.” That says a lot and it’s supported by the fact that attendees were genuinely happy to be there with each other. The event was full of The Imaging Wire’s favorite type of people: humble and hardworking folks who’ve hustled their way up, take their profession seriously, and still have a lot of fun. If radiology conferences were “families,” AHRA would be RSNA’s hardworking but fun-loving cousin who would never schedule its “reunion” during a major holiday weekend.
- This is No AI Show – AI may get the headlines, but it’s not super top of mind among most AHRA attendees. The imaging department leaders in attendance were far more focused on improving how they work with their teams, machines, and patients than pondering the changes that AI might bring (even when discussing tools that are totally based on AI). This may change over time, but it’s an important reminder for the folks making these headlines (both press and vendors) that the AHRA crowd is a lot more focused on how a solution helps their department than how it was made.
- Marathon Sessions, Exhibit Sprints – I get it. This is an educational conference, so there’s going to be a lot of educational sessions. Based on attendance and engagement during these sessions, it’s easy to say AHRA succeeded in this aspect. However, making it to even a portion of the 150 exhibitors during the three-hour exhibit hall periods can’t be done. As one exhibitor shared, “the human part of me appreciates the short exhibit hall times, but the businessperson in me needs more time with our customers.” AHRA is one of the rare industry shows where customers actually outnumber sellers (and maybe this is why), but the “business person in me” definitely agrees that more exhibit hall time would help.
This was a solid show, AHRA team and attendees. See you next year.
A team of Japanese researchers developed a new imaging method that can simultaneously detect and image PET and SPECT radiotracers, reducing scanning times and patient radiation dosage. Here’s how:
- The Tech – The team developed a new version of a Compton camera that uses silicon/cadmium telluride (Si/CdTe) to allow gamma ray detection in both low (for SPECT) and high (for PET) energy ranges.
- The Test – Patients were given both 99mTc-DMSA (for SPECT) and 18F-FDG (for PET) radiotracers. Using the Compton camera and a new image reconstruction algorithm, the researchers simultaneously created two-dimensional images of each radiotracer in the patients’ organs.
- The Next Steps – More trials are needed, but the researchers are optimistic that this new approach will lead to new types of imaging and help create new tracers.
BCBS’ Global Payment Experiment
A new NEJM article detailed encouraging results from Blue Cross Blue Shield (BCBS) of Massachusetts’ 8-year global payment experiment, finding that providers who enrolled in BCBS’ Alternative Quality Contract (AQC – incentivizes providers to stay within a care budget) had lower medical spending and equal-to-better quality of care compared providers using traditional plans (incentivizes performing services). Here’s how:
- Shared Risk – The ACQ’s two-sided risk model refunded providers who stayed below their budgets with a portion of the savings, while providers who exceeded their budget had to cover a portion of their excess costs. Providers also received bonuses for achieving quality goals.
- Actions – Initial savings relied on shifting services to lower-cost settings (e.g. shifting from hospital-based care to office-based care). However, longer-term reductions came from a drop in wasteful services (e.g. unnecessary lab/imaging tests and ED visits) and an increased focus on preventive care and chronic illness management.
- Results – Average annual spending per-patient during ACQ’s 2009 to 2016 post-intervention period was 11.7% ($461/yr less) lower than per-patient spending in control states. Patient populations who were enrolled for longer periods achieved the greatest spending reductions (e.g. costs for enrollees active from 2010-2016 were 11.9% lower, while those enrolled from 2012-2016 were just 2.3% lower).
There will surely be a few who point out how ACQ undermines the hospital and physician business models that everyone is used to. However, there’s plenty of evidence to suggest that the healthcare business model deserves to be undermined (or perhaps overhauled) and until payors start rewarding for health outcomes over volumes, today’s healthcare issues (high costs, low profits, burnout, etc.) will persist.
- Signify Research shared insights on medical imaging machine learning regulatory approvals (106 approvals, 2014 to H1 2019), highlighted by a spike in approvals in 2018 (~58 approved) and revealing much greater ML progress in the U.S. and Europe (47 & 45 ML solutions approved in last 5.5yrs) than Japan and South Korea (just 5 combined ML solutions approved). Machine learning solutions for brain imaging had the highest share of regulatory approvals in both the U.S. (26%) and Europe (33%), while breast imaging solutions were a close second in the U.S. (21%) and lung imaging solutions were the second most-approved in Europe (20%).
- Beth Israel Deaconess Medical Center researchers developed a quantitative cardiac MR approach that could identify coronary disease in just 15-minutes without requiring gadolinium. Here’s how it works: patients undergo a series of baseline imaging scans, then pedal an exercise bike for 30 seconds while lying in the opening of the MRI, then undergo an MRI scan that quantifies myocardium blood flow changes, and then undergo a similar imaging protocol. The different images show how the myocardium’s magnetic properties change in areas impacted by coronary atherosclerosis, supporting CAD diagnosis.
- Intelligent Ultrasound Group (previously known as MedaPhor) partnered with the National Imaging Academy Wales (NIAW) to develop AI-based ultrasound simulation training solutions. The partnership will combine NIAW’s clinical expertise and training focus with Intelligent Ultrasound’s capabilities in AI development, ultrasound simulation software, and ultrasound solution commercialization.
- As the UK NHS pension dispute continues, reports from the country reveal that cancer scans are remaining unread for as long as six weeks, compared to a standard 1-week turnaround time. The pension issue involves an overtime tax that effectively forces physicians (not just radiologists) to “pay the NHS to work extra shifts,” prompting a growing number of specialists to quit, refuse overtime, or even move to other countries.
- A new article published in JAMA outlined the three primary requirements to maintain trust between patients and clinicians as AI takes on a greater role in healthcare. The paper suggested that in order to maintain trust, the parties involved in healthcare AI must exhibit 1) Competency – the physician, patient, and AI tool must all be competent in their roles; 2) Motive – patients must trust that physicians are acting in their interest; and 3) Transparency – physicians/patients should understand how an AI solution works… and eventually know the reasons for its recommendations (aka interpretable).
- The Australian Nuclear Science and Technology Organization (ANSTO) is raising its medical isotope rates by between 3% and 9% in response to the government organization’s own rising costs, creating concern across the Australian nuclear medicine supply chain.
- The Indian Institute of Technology Kharagpur and Tata Medical Center are collaborating to create the descriptively-named Comprehensive Digital Archive of Cancer Imaging (CHAVI). The imaging archive will serve as a national bank of annotated images, representing an early step to evolve the field of image banking and an increased effort to support India’s image-related cancer research and AI development efforts.
- VIDA Diagnostics landed a $1 million strategic investment from UnityPoint Health Ventures (the VC arm of the large Iowa health system) with the goal of developing and commercializing VIDA’s LungPrint AI-powered lung CT analysis solution (flags lung density abnormalities). VIDA will have access to UnityPoint Health’s multi-state hospital network and clinicians, who will contribute insights to support VIDA’s solution roadmap and commercialization processes.
- A team of Mass General radiologists and urologists developed a cascading CNN model that is able to detect urinary tract stones on unenhanced abdominopelvic CT scans with impressive accuracy. Using labeled CT images from 535 patients suspected to have urolithiasis (279 with stones) that were imaged with two scanners, the team developed a pair of CNNs made to identify the urinary tract and detect kidney stones that achieved AUCs as high as 0.954.
- Ikonopedia officially launched its Automated Combined Reporting Package which automatically combines results from a range of breast health tests (mammography, US, MRI, biopsy) into a single clinical report for the referring physician. The Combined Reporting Package is used in conjunction with Ikonopedia’s Closed-Loop Resolution Manager and are intended to improve communication, follow-up, and efficiency.
- Oncology medicine and imaging company, Progenics Pharmaceuticals, announced a medical imaging AI research partnership with the VA Greater Los Angeles Healthcare System (VAGLAHS) that is intended to develop and apply machine learning solutions to improve prostate cancer treatment. Progenics will give the VAGLAHS network access to its machine learning platforms to explore and validate predictive algorithms for prostate cancer based on medical images and associated clinical outcomes.
- Israeli ultrasound startup, iNNOGING, has been busy, launching its new Ultrasound Simulator (a hardware + software platform to help users practice US applications), adding ultrasound leader Professor Larry Needleman to its board, and preparing to start clinical trials for its Ultrasound Analyzer solution (a remote/offline platform that allows physicians to manipulate captured ultrasound video and perform exams without the patient present).
The Resource Wire
– This is sponsored content.
- Four Qure.ai abstracts have been selected for RSNA19 covering: a new metric to evaluate radiology AI models, chest X-ray TB screening, segmenting and measuring ventricular and cranial vault volumes with AI, and how clinical context improves AI performance for cranial fracture detection.
- A study in JACR revealed that the rise of high-deductible health plans has led to greater patient concerns over imaging costs than ever before, while patient cost comparisons often leads to “confusion, misinformation, and opaqueness.” These are the exact patients who can be helped by the Medmo platform, which connects high-deductible patients with radiology centers, ensuring the best value for patients and a profitable revenue stream for imaging centers.
- In this blog post, Nuance Healthcare’s Diagnostic Division GM and VP, Karen Holzberger, shared some real-world examples of how PowerShare is helping providers #DitchTheDisk and improve patient experiences.
- The Focused Ultrasound Foundation’s Asia program is gaining momentum, highlighted by the upcoming 2020 formation of a Hong Kong subsidiary that will work with Asia-based philanthropists and distribute funds research institutions across Asia, in addition to the Foundation’s existing relationships and clinical trials on the continent.
- The POCUS Systems founding team has over 80 years of combined experience in the ultrasound industry.
- In this Carestream video, orthopaedic surgeon Dr. Bryan Den Hartog presents clinical images illustrating traditional CT vs. extremity CT imaging and discusses how the image resolution in the OnSight 3D Extremity System helps in his practice.