“When I first saw the news, I started three companies.”
Stanford CS PhD student, Sharon Zhou, on what CMS reimbursements mean for the business of imaging AI. She was joking, kind of.
Imaging Wire Sponsors
- Bayer Radiology – Providing a portfolio of radiology products, solutions, and services that enable radiologists to get the clear answers they need.
- GE Healthcare – Enabling clinicians to make faster, more informed decisions through intelligent devices, data analytics, applications and services.
- Healthcare Administrative Partners – Empowering radiology groups through expert revenue cycle management, clinical analytics, practice support, and specialized coding.
- Hitachi Healthcare Americas – Delivering best in class medical imaging technologies and value-based reporting.
- Nuance – AI and cloud-powered technology solutions to help radiologists stay focused, move quickly, and work smarter.
- Riverain Technologies – Offering artificial intelligence tools dedicated to the early, efficient detection of lung disease.
The Imaging Wire
NTAPs & DRGs
Viz.ai’s Medicare NTAP was enough to get us yet another excellent Luke Oakden-Rayner blog, with the latest gem sharing insights from Viz.ai’s CEO about how the reimbursements will work and what they mean for the business of imaging AI. Here are the big takeaways:
- Reimbursement Math – The NTAP reimbursement rates are based on a hospital’s annual Viz.ai ContaCT scan volume, divided by their ContaCT subscription cost. So hospitals with fewer stroke patients are more likely to receive reimbursements close to the $1,040 rate that everyone is talking about.
- NTAP Qualifiers – Fewer patient cases qualify for these NTAP reimbursements than some might assume. In order for a patient to qualify, they must be covered by Medicare (obviously), have inpatient status (not emergency), and would have to be a loss-maker for the hospital.
- Defining a Loss Maker – The patient would have to cost the hospital more than the value of the stroke DRG that the hospital would receive from Medicare. For those of us who are just now figuring out what NTAPs and DRGs are, a DRG (diagnosis related group) is a bundled payment that hospitals receive to cover a Medicare patient’s inpatient care.
- Viz.ai Loss Leader – The likelihood that more ContaCT scans might lead to more thrombectomy procedures is good news for hospitals because these additional surgeries would result in higher reimbursements than they would get from the NTAP. As Dr. Luke puts it, the NTAP is the “consolation prize,” while getting more patients to thrombectomy “is the real value-maker.”
- Another AI Value Prop Pivot – When Viz.ai’s NTAP reimbursement came out, everyone was quick to call this a major turning point for imaging AI’s value proposition (efficiency, outcomes, and now…. reimbursements). However, these new details show that if an AI solution leads to better outcomes and more high-reimbursement procedures, its value prop is pretty solid even without reimbursements (although reimbursements surely help).
The Wire
- POCUS’ Primary Benefits: A new study out of Denmark found that primary care doctors use point-of-care ultrasound (POCUS) in a wide variety of patient situations and commonly change treatment plans based on their POCUS exams. The study’s 22 physicians used POCUS in 8.6% of their patient consultations (574 patients, >100 different tentative diagnoses), finding that using POCUS often led to a changed diagnoses (49.4% of patients), increased diagnostic confidence (89.2%), changed management plans (50.9%), changed treatments (26.5%), and reduced referrals (from 49.2% to 25.6% of patients).
- Surprise Billing Back to Congress: One of radiology’s biggest stories in 2019 might find its way back into the 2020 news cycle. President Trump signed an executive order calling on Congress to address surprise medical billing before the end of the year. Although is is technically progress, the White House was reportedly prepared to address surprise billing with a more ambitious executive order, but decided to punt this issue to Congress after pushback from healthcare lobbyists and republican lawmakers.
- COVID CXR Keeps Getting Better: A new study in Radiology: Cardiothoracic Imaging compared CXRs and CTs from 254 COVID-positive patients against scans from 254 negative patients, finding that serial chest X-rays can detect COVID-19 with “accuracy approaching that of chest CT” while standard CXR sensitivity increases later in patients’ symptomatic period. The serial CXR comparison revealed that CXR AUCs increased considerably between the first and second scan (0.79 to 0.87 AUCs), coming close to CT’s 0.92 AUC. The study also found that CXR sensitivity increased from 55% at ≤2 days after symptoms onset to 79% at >11 days.
- GLEAMER’s €7.5m: French imaging AI firm, GLEAMER, raised €7.5m that it will use to fund the FDA approval and launch of its BoneView solution (analyze X-rays for trauma, already has CE Mark). Although imaging AI funding rounds are a near-weekly occurrence, GLEAMER’s round gained more attention because 37 radiologists contributed to it (in addition to a mix of VCs).
- Notification Inconsistency: Adopting statewide breast density notification laws might not guarantee that mammography facilities will start sending risk notification letters or provide the supplemental screenings that these notifications recommend. That’s from a new study out of North Carolina (n = 94 centers) that found that 79.4% of centers communicate risk assessments via reports to referring physicians and 58.8% include risks in results letters, while only 63.8% of the facilities performed supplemental screenings and just 48.3% of the centers made supplemental screening decisions based on density.
- Nautilus’ New Recorder: Nautilus Medical launched its new TeleRay Record all-in-one DICOM surgical recorder, intended for use with a wide range of modalities (endoscope, headset, c-arm, vascular, ultrasound, c-arms, more) and video systems (Panasonic, Olympus, Storz, Zeiss, Leica). Nautilus positioned the new TeleRay Record as a lower-cost solution with high-end features (editing, large screen, Bluetooth foot pedals, and various video connection options).
- DBT Trial on Chopping Block: The National Cancer Institute is reportedly planning to kill the $100m Tomosynthesis Mammography Imaging Screening Trial (TMIST), which launched in 2017 with the goal of comparing DBT and 2D mammography screening outcomes. The TMIST is under review because of its struggles to get enough participation (patients, sites, physicians) and because DBT is already so widely adopted.
- Wellbeing Adds Qure.ai: Wellbeing software announced that Qure.ai joined the UK RIS company’s AI Connect Marketplace. The partnership increases the Wellbeing AI Marketplace to eight AI players, while expanding Qure.ai’s notable marketplace presence (Nuance, Terarecon, Ambra, Blackford, and Incepto).
- OA Risk Map: An international team of researchers developed a technique that might help detect osteoarthritis three years before symptoms or bone damage occur (so, while it’s still reversible) using a technique combining mass transport theory with cartilage phenotype mapping. To study it, the researchers scanned 86 healthy people at baseline and during a 3yr follow up, using the baseline MRI cartilage texture maps to differentiate OA progressors and nonprogressors with 78% accuracy.
- Handheld US’ COVID Potential: A new study out of Italy revealed that handheld ultrasounds perform similarly to cart-based POCUS systems for evaluating patients with COVID-19 pneumonia, while noting the pocket-size systems’ unique advantages (size, cost, portability, accessibility). The researchers performed lung ultrasound evaluations on 18 hospitalized COVID-19 patients using both the handheld Butterfly iQ and the cart-based GE Healthcare Venue GO, finding that the two systems produced statistically similar LUS scores.
- Preventing Breast Imaging Burnout: A new paper in Current Problems in Diagnostic Radiology detailed the steps that practices and departments can take to prevent breast radiologist burnout. Here they are: 1) Delegate patient counseling to a coordinator / navigator; 2) Assign procedures to NPs or PAs; 3) Leverage AI; 4) Create a supportive and positive culture; 5) Support flexible work schedules and work settings; 6) Clearly communicate reading productivity expectations.
- Deep Gray Matter AI: A well-received new UPenn-led paper detailed how the team built a hybrid deep learning system that can diagnose neurologic diseases that involve deep gray matter. The team developed an image processing pipeline, combining 3D CNN and atlas-based image processing with brain MRIs from 212 patients, that detected 11 key neurologic features with 89% accuracy (sensitivity, 81%; specificity, 95%). They also created an expert-derived Bayesian network that incorporated the 11 features with four clinical features to support diagnosis of 35 different neuroradiologic diagnoses, achieving 85% accuracy for a top-three differential diagnoses and 64% for the correct top diagnosis (matching neurorads’ 84% & 65%).
- Varex Obligations: Standard & Poor’s reduced Varex Imaging’s outlook to “negative” last week, after the imaging component company announced a $300n private offering that it will use to pay existing liabilities and fund ongoing operations. The ratings agency foresees plenty of risks (pandemic uncertainty, inflexible cost structure), but still expects Varex’s performance to improve over the next 12-18 months.
- NOUS’ FDA Nod: NOUS Imaging announced the FDA approval of its FIRMM software (Framewise Integrated Real-Time MRI Monitoring), which uses MR image data to calculate and display patient motion during a head scan, helping operators and patients reduce movement.
The Resource Wire
– This is sponsored content.
- Did you know that one in three Americans is obese and obesity is even more prevalent in rural communities? This Hitachi blog shows how its wide aperture CT and MRI systems are the best fit for rural hospitals, helping them care for patients of all sizes and get more ROI from their imaging systems.
- It says a lot when a solution works so well for a radiology department that they decide to perform a study to quantify its benefits. In this Imaging Wire Q&A, University Hospital of Zurich’s Thomas Frauenfelder discusses his experience and study on Riverain Technologies ClearRead CT.
- This GE Healthcare article details how Big Sur’s Mee Memorial hospital leveraged AI-powered POCUS and X-ray technologies as wildfires and the COVID-19 pandemic brought in a new wave of patients.
- Patients have become savvy healthcare shoppers who increasingly rely on price information to make decisions about their care. Join Healthcare Administrative Partners’ CRO, Rebecca Farrington, as she discusses price transparency & consumerism in radiology in this upcoming RBMA webinar.
- This Bayer Radiology white paper details how the right people, plan, and systems can help imaging teams achieve their dose management goals.
- Learn how medical imaging & RADLogics AI can help imaging providers address the COVID-19 crisis and future surges in this Nuance on-demand webinar.
