Health Affairs on the administrative waste’s massive health system impact.

Imaging Wire Sponsors

annalise.ai  •  Arterys  •  Bayer  •  Blackford  •  Canon Medical  •  CARPL.ai  •  Change Healthcare  •  Enlitic  •  GE Healthcare  •  Hyperfine  •  Intelerad  •  Novarad  •  Riverain Technologies  •  Siemens Healthineers  •  United Imaging  •  Us2.ai

Artificial Intelligence

iCAD and Solis CVD Alliance

iCAD and major breast imaging center company Solis Mammography announced plans to develop and commercialize AI that quantifies breast arterial calcifications (BACs) in mammograms to identify women with high cardiovascular disease (CVD) risks.

Through the multi-year alliance, iCAD and Solis will expand upon iCAD’s flagship ProFound AI solution’s ability to detect and quantify BACs, with the goal of helping radiologists identify women with high CVD risks and guide them into care.

iCAD and Solis’ expansion into cardiovascular disease screening wasn’t exactly expected, but recent trends certainly suggest that commercial AI-based BAC detection could be on the way: 

• There’s a growing list of studies showing that women with BACs have far higher risks of future CVD, and radiologists don’t have a consistent approach for reporting incidental BAC findings. 

• There’s also mounting academic and commercial momentum behind using AI to “opportunistically” screen for incidental findings in scans that were performed for other reasons (e.g. analyzing CTs for CAC scores, osteoporosis, or lung nodules).

• Despite being the leading cause of death in the US, it appears that we’re a long way from formal heart disease screening programs, making the already-established mammography screening pathway an unlikely alternative.

• Volpara and Microsoft are also working on a mammography AI product that detects and quantifies BACs. In other words, three of the biggest companies in breast imaging (at least) and one of the biggest tech companies in the world are all currently developing AI-based BAC screening solutions.

The Takeaway

Widespread adoption of mammography AI-based cardiovascular disease screening might seem like a longshot to many readers who often view incidentals as a burden and have grown weary of early-stage AI announcements… and they might be right. That said, there’s plenty of evidence suggesting that a solution like this would help detect more early-stage heart disease using scans that are already being performed.

AI’s Healthcare System Value

AI delivers value to a wide range of healthcare stakeholders, but its primary value to health systems originate from its ability to automate tasks, democratize care, and deliver hard and soft ROI. See how these factors impact health systems’ bottom line in this latest Arterys report.

United Imaging’s Culture-Led Strategy

Check out our interview with United Imaging CEO, Jeffrey Bundy, who explores company culture’s central role in medical imaging and how to build, improve, and maintain culture. If you’re ready to improve your organization’s culture, this interview is a great way to start.

The Wire

• RamSoft’s All-in-One EMR: RamSoft unveiled its OmegaAI platform, calling it the “world’s first imaging EMR,” and backing up that title with a comprehensive list of integrated imaging tools that have traditionally existed separately (VNA, PACS, RIS, viewer, image exchange, radiologist reporting, front desk, patient portal, app marketplace, etc.). Although many in radiology might want to see OmegaAI for themselves, most would agree that a comprehensive and natively-integrated platform would help address a lot of imaging IT’s current problems.

• ASPECT Scores and EVT Outcomes: A new JAMA study revealed that LVO stroke patients with higher CT-based ASPECT Scores (4 or 5, medium severity) are far better candidates for endovascular treatment (EVT) than patients with lower ASPECT Scores (0-3, greatest severity). Analysis of 202 LVO patients showed that EVT was twice as effective among ASPECTS 4-5 patients than ASPECTS 0-3 patients after 90 days (43.2% vs. 21.4% had no-to-low disabilities), and had far lower risk of intracranial hemorrhage within 48 hours (odds ratios: 2.05 vs. 4.14). 

• AI Bill of Rights Blueprint: The Biden Administration released its “Blueprint” for an AI Bill of Rights that calls on technology companies to develop AI solutions with built-in safeguards to “protect the American people in the age of artificial intelligence.” The Blueprint outlines five principles to guide AI design and deployment: (1) systems should be safe and effective… and tested/monitored, (2) algorithms shouldn’t discriminate against certain groups, (3) individuals should have control over their personal data, (4) organizations should disclose how AI is being used, (5) individuals should be provided a human alternative to automated systems.

• MGH’s Peer Review Preference: A new MGH study showed that radiology trainees and faculty prefer daily peer learning meetings versus using traditional peer review systems. MGH replaced its peer review tool with daily one hour peer learning conferences during a three-month pilot (~9 cases daily, 711 overall), finding via a follow-up survey (n=30 out of 40) that respondents unanimously supported permanently replacing their existing peer review tool, and the vast majority found PL conferences to be effective for improving care and identifying errors (100% of faculty and 90% of trainees).

• Missed Pancreatic Cancers: UK researchers found that many pancreatic cancers go undiagnosed in initial medical imaging exams, leading to diagnoses at later and less-treatable stages. Analysis of 600 patients with pancreatic cancer revealed that 46 patients (7.7%) had normal initial CT and MRI exam results, and were diagnosed 3 to 18 months later. The researchers estimate that 36% of post-imaging pancreatic cancer cases are potentially avoidable.

• Rising Imaging Costs: A new JACR study showed that U.S. patients’ average annual out-of-pocket (OOP) imaging costs increased by 89.8% from 2000 to 2019 ($97.97 vs. $185.91). Among 102k patients (w/ 229k imaging exams), average OOP costs for mammograms decreased by 32.9%, while costs increased for ultrasound, X-ray, and CT/MR exams (123%, 81%, & 61%). Patients generally had higher OPP costs if they didn’t have health coverage, were younger, had comorbidities, or a history of cancer.  

• AI Computing Breakthrough: One of the most exciting AI studies of the year was just published by Google’s DeepMind lab after its AlphaTensor reinforcement learning AI discovered a new matrix multiplication algorithm with the potential to speed up many common computing routines. Although the findings could impact everything from drug discovery to genomics, the authors were most enthusiastic about the fact that the algorithm itself reaches “beyond human intuition” and opens the door to improving other human-designed algorithms.

• Wasteful Administrative Costs: New research in Health Affairs estimates that roughly 15% of US medical spending is administrative waste ($570B!), with the authors finding that at least half of all admin cost “does not contribute to health outcomes in any discernible way.” The report makes the case that the government should standardize administrative processes such as prior authorization across public and private sectors to cut back on wasteful spending.

• Questioning Colonoscopy: An NEJM study brought new scrutiny on colonoscopy screening — and on the media’s oversimplification of clinical trial results. The NORDICC trial randomly invited or didn’t invite 84k patients to undergo colonoscopy, finding that the ‘invited’ patients had a modest 18% reduction in 10-year colorectal cancer rates (1.2% vs. 0.98%), but just 10% lower mortality rates (0.28% vs. 0.31%). These results drove headlines about colonoscopy screening’s ineffectiveness, even though the 42% of ‘invited’ group members who actually attended their screening had a 50% lower mortality rate.

• RadNet’s NJ Expansion: RadNet expanded its northern New Jersey presence with its acquisition of Montclair Radiology’s imaging operations (6 imaging centers, 200k exams/yr, $40M/yr revenue contribution). The Montclair locations will join RadNet’s joint venture with Barnabas Health, New Jersey Imaging Network. RadNet recently announced a shift in its expansion strategy towards building net new imaging centers, suggesting that its Montclair Radiology acquisition might be due to a unique situation.

• Bot Image’s Prostate Cancer Performance: New research in Academic Radiology showed that Bot Image’s MRI AI solution can improve radiologists’ diagnostic performance during prostate cancer detection. The study had nine radiologists interpret 150 prostate MRIs with and without AI support, finding that the solution improved the radiologists’ inter-reader agreement (IRA: 0.65 vs. 0.47) and average detection performance (AUCs: 0.72 vs. 0.67).

Us2.ai Automates the Fight Against Heart Disease

See how Us2.ai cuts echocardiography’s manual work, subjectivity, and turnaround times to automate the fight against heart disease.

An Image Sharing Starting Point

Imaging providers who want to finally #ditchthedisk can now start off with Novarad’s CryptoChart Lite solution, a no-cost version of CryptoChart built for providers transitioning to imaging sharing.

The Resource Wire

• “It completely changes the way we think about MRI imaging.” Take a look at this video interview with Mass General’s Chief of Neurocritical Care to see how clinicians can use Hyperfine’s Swoop Portable MRI to eliminate care disruptions in the ICU by keeping critically ill patients in the unit throughout the neuroimaging process.

• Check out this talk from Eliot Siegel, MD on the “Hype, Myth, Reality and Next Steps” of imaging AI, including a profile on Canon’s AiCE Deep Learning Reconstruction solution at around the 4-minute mark.

• 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.

• New healthcare technologies have traditionally been hard to implement, and that’s certainly been true for imaging AI, but some of AI’s challenges might have been avoided with the right standards and guidelines. Check out this Enlitic report outlining its 5-stage approach to less-challenging AI adoption.

• Heart disease remains the leading cause of death worldwide, but this editorial by Intelerad’s Morris Panner reveals that medical imaging breakthroughs are making this prognosis more promising. See how advances in cardiac imaging are paving the way for earlier detection, more precise assessments, and more effective interventions.

• See how adopting ClearRead CT allowed Michigan’s Regional Medical Imaging’s radiologists to complete their chest CT reads faster and more accurately in this Riverain Technologies case study.

• Bayer’s cloud-based Calantic Digital Solutions AI platform features a suite of disease-specific AI apps that integrate into radiologist workflows, helping radiology teams scale AI deployment and improve efficiency and quality of care.

• What if your X-ray system could help you do more by doing less? See how GE’s AI-based X-ray workflow automations can reduce your repeat and rejected exams, while improving image quality, consistency, and productivity. 

• See how Thomas Jefferson University relied on CARPL.ai to accelerate its AI validation and clinical adoption in this presentation by informatics and AI leader, Dr. Paras Lakhani.

• Imaging’s cloud evolution didn’t happen all at once. This Change Healthcare animation details the history of digital imaging architectures, and how cloud-native imaging improves stability and scalability, ease of management, patient data security, and operating costs.

• We hear a lot about AI being the next big thing or being immature and overhyped. This set of Blackford Analysis editorials reviews the challenges that are still holding back imaging AI, and the areas that AI is delivering genuine clinical benefits.

• Ready to make MRI more accessible to your patients? See how Siemens Healthineers’ MAGNETOM Free.Max expands MR imaging to more patients, sites, and providers.