Bajaj S et al, in a new JACR study on the marketing of AI applications.

Imaging Wire Sponsors

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

Artificial Intelligence

How Vendors Sell AI

Better patient care is the main selling point used by AI vendors when marketing neuroimaging algorithms, followed closely by time savings. Farther down the list of benefits are lower costs and increased revenue for providers. 

So says a new analysis in JACR that takes a close look at how FDA-cleared neuroimaging AI algorithms are marketed by vendors. It also includes several warning signs for both AI developers and clinicians.

AI is the most exciting technology to arrive in healthcare in decades, but questions percolate on whether AI developers are overhyping the technology. In the new analysis, researchers focused on marketing claims made for 59 AI neuroimaging algorithms cleared by the FDA from 2008 to 2022. Researchers analyzed FDA summaries and vendor websites, finding:

• For 69% of algorithms, vendors highlighted an improvement in quality of patient care, while time savings for clinicians were touted for 44%. Only 16% of algorithms were promoted as lowering costs, while just 11% were positioned as increasing revenue
• 50% of cleared neuroimaging algorithms were related to detection or quantification of stroke; of these, 41% were for intracranial hemorrhage, 31% for stroke brain perfusion, and 24% for detection of large vessel occlusion 
• 41% of the algorithms were intended for use with non-contrast CT scans, 36% with MRI, 15% with CT perfusion, 14% with CT angiography, and the rest with MR perfusion and PET
• 90% of the algorithms studied were cleared in the last five years, and 42% since last year

The researchers further noted two caveats in AI marketing: 

• There is a lack of publicly available data to support vendor claims about the value of their algorithms. Better transparency is needed to create trust and clinician engagement.
• The single-use-case nature of many AI algorithms raises questions about their economic viability. Many different algorithms would have to be implemented at a facility to ensure “a reasonable breadth of triage” for critical findings, and the financial burden of such integration is unclear.

The Takeaway

The new study offers intriguing insights into how AI algorithms are marketed by vendors, and how these efforts could be perceived by clinicians. The researchers note that financial pressure on AI developers may cause them to make “unintentional exaggerated claims” to recoup the cost of development; it is incumbent upon vendors to scrutinize their marketing activities to avoid overhyping AI technology.

Automating Echo Strain Analysis

Check out our Cardiac Wire publication’s latest Q&A with Us2.ai president and co-founder, Yoran Hummel, discussing how his career as a sonographer led him to echo AI, and how Us2.ai’s upcoming automated strain analysis feature brings the company even closer to democratizing echo.

A Fast and Reliable Second Opinion

See why radiologist Dr. Eleanna Saloura called Arterys’ Lung AI solution “a fast and reliable second opinion” for chest CT lung nodule analysis and tracking, allowing “more accurate diagnostic and treatment decisions.”

The Wire

• UK AI Milestone: In a milestone on the path to broader use of AI in the UK, the country’s National Institute for Health and Care Excellence (NICE) has recommended the use of nine different AI algorithms to aid with planning external-beam radiation therapy. In a draft guidance, NICE recommended use of AI for contouring, currently a manual and time-consuming process. This is the first NICE guidance on the use of AI – more are sure to come as the NHS ramps up its investment in AI.

• Siemens Cements Partnership with SSM Health: Siemens Healthineers signed a 10-year collaboration with SSM Health of St. Louis, Missouri. Under the relationship, Siemens will provide SSM with access to new diagnostic imaging technology and software, as well as education and other on-site support with an emphasis on oncology and radiologic technologist recruiting and training. The deal covers SSM’s four-state service area including Illinois, Missouri, Oklahoma, and Wisconsin, making it Siemens’ largest deal to date as measured by geographic area.

• Algorithm Assesses Sarcopenia: A deep learning algorithm that analyzed CT scans for signs of sarcopenia in patients with head and neck squamous cell carcinoma worked well in predicting overall survival. In JAMA Network Open, researchers found that in 899 patients scanned from 2003-2013, those identified by a homegrown algorithm as having sarcopenia had worse overall survival (HR=2.05). This study offers a more automated method to detect sarcopenia on CT scans than manual image analysis.

• Akumin Exploring ‘Strategic Initiatives:’ Radiology outsourcing provider Akumin said its board has formed a special committee to “explore strategic initiatives related to its capital structure.” The announcement came after the company posted a 4% Q2 revenue decline and a net loss of $96M, up sharply compared to a net loss of $26M in Q2 of 2022. Much of the higher net loss was due to a $54M charge for impairment of goodwill related to its radiology division.  

• AI Detects Link to Breast Cancer: An AI algorithm that analyzes breast MRI exams found that higher background parenchymal enhancement (BPE) is an indicator of breast cancer risk in women with extremely dense breast tissue. In a study in Radiology, Dutch researchers assessed breast MRI exams in 4.6k women, finding that higher BPE was associated with breast cancer; women in the highest third of BPE by volume had 2X the risk as those in the lowest third (HR=2.09). 

• Prior Authorization On the Wane? Prior authorization continues to fall out of favor. UnitedHealthcare is continuing the trend by moving ahead with its plan to eliminate prior authorization starting September 1 for medical procedures that add up to 20% of its total volume. Over 60 radiology CPT codes are subject to the move, per a list on the company’s website. UnitedHealthcare telegraphed the move earlier this year as part of an effort to streamline medical services. 

• Coronary Angio for Cardiac Arrest: It may not be necessary to perform coronary angiography immediately in some patients who experience cardiac arrest outside the hospital, says a new study in JAMA Cardiology. In the TOMAHAWK study, researchers from 2016 to 2019 tracked 554 patients with out-of-hospital cardiac arrest who did not have ST-segment elevation. They found that those who got immediate coronary angiography had no statistically significant difference in all-cause mortality after one year than those who got delayed or selective angiography (60.8% vs. 54.3%, P=0.05).

• Blackford Adds Cardiac MRI: AI platform developer Blackford Analysis has added a cardiac MRI quantification application from AI4MedImaging to its Blackford Platform. AI4CMR uses AI to calculate, quantify, and analyze the heart’s left and right ventricle in two minutes, producing a structured report that can be extracted to any reporting system. Triage functionality for wall motion detection has the CE Mark and is pending FDA clearance. Blackford has been adding a growing number of applications to its platform, such as Lunit’s chest X-ray and mammography algorithms. 

• Lung Cancer Linked to Metabolic Syndrome: A new research study found a link between lung cancer and metabolic syndrome, a collection of diseases including hypertension, elevated HDL-C, and hyperglycemia. In a study in Chest of 332k people from the UK BioBank study, researchers found higher lung cancer incidence per 100k people in those with metabolic syndrome (97.7 vs. 61.8), and those with the syndrome had 21% higher lung cancer risk. The findings suggest people with metabolic syndrome should receive lung cancer screening.

• Prenuvo’s Kardashian Controversy: A promotion for Prenuvo’s whole-body MRI screening service featuring Kim Kardashian is generating controversy. In a social media post, the reality star said she underwent a Prenuvo scan to detect “cancers and diseases such as aneurysms,” which sparked a debate over the entire concept of wellness scans. Prenuvo and whole-body scanning are no strangers to controversy, so the promotion was probably money well spent – especially as Kardashian claims her post was not an ad.

• India’s Home-Grown MRI: A startup company in India called Voxelgrids is launching a new 1.5T MRI scanner developed and manufactured entirely within the country. Voxelgrids notes that 70% of the world lacks access to MRI; the new system will address this challenge with a price of about $400k, compared to a price range of $670k-$1.2M for a conventional MRI scanner. In addition to sales in India, the company plans to export the scanner to other countries. 

• AAA Trial Collaboration: Nectero Medical will be using AI-based technologies from Astute Imaging as part of a clinical trial of its Nectero EAST (endovascular aneurysm stabilization treatment) system for treating small to mid-sized abdominal aortic aneurysms (AAA). Astute will provide its Preview surgical planning tool and PEMS image-based registry platform to enable real-time visualization of implanted device performance. Astute’s technologies can track devices and treatments to provide insights into their long-term efficacy. 

• FDA Clears Dedicated Chest CT: The FDA has cleared a family of dedicated cardiovascular CT scanners from Arineta Cardio Imaging of Israel. Arineta promotes its SpotLight and SpotLight Duo scanners as the only commercially available dedicated cardiovascular CT scanners; Duo also can perform high-resolution thoracic imaging for pulmonary diseases like COVID-19 and lung cancer. Arineta said it will sell and service the scanners directly.

What’s the ROI of AI?

Radiology thought leaders discussed AI’s return on investment in a session at SIIM 2023. We covered some of the high points in this interview with Matt Lungren, MD, and Sander Kloet of Nuance Communications.

Healthcare’s Shift to CloudPACS

What’s behind healthcare’s shift from legacy PACS to cloud-based enterprise imaging? We talked to Brad Levin of Visage Imaging at HIMSS 2023, and he explains the change and the benefits of Visage’s Visage 7 | CloudPACS solution.

Building a Successful Radiology Team in a Hyper-Competitive Market

In today’s hyper-competitive job market, radiologist recruiting and retention is more important than ever. Learn from industry experts and practice leaders in this on-demand Medality webinar as they reveal how to overcome hiring challenges and keep your team engaged.

The Resource Wire

• Over 9 out of 10 people who should be screened for lung cancer aren’t, and nearly 50% of lung cancer cases are caught in the advanced stages. But lung cancer screening has been challenging. Riverain has assembled this resource page for anyone interested in starting or improving their lung screening program.

• Check out this helpful Blackford Analysis report on how to calculate AI’s clinical, IT, administrative, and financial value to your organization.

• Patient-centric care was one of the major highlights at HIMSS 2023. What role does medical imaging play in this patient care pathway? We talked to Morris Panner and A.J. Watson of Intelerad at the meeting.

• There are about 40 million imaging-related diagnostic errors occurring every year. Find out how Annalise.ai’s comprehensive AI solutions can reduce errors and improve diagnostic performance in this demo. 

• EHRs are becoming a source of frustration for physicians, and the COVID-19 pandemic accelerated this trend. Learn how PocketHealth can give patients control and ownership of their records, reducing the burden on clinicians. 

• Medical imaging data plays a pivotal role in healthcare research, especially when integrated into clinical trials. But effective data management is vital for successful medical research. Find out how to get started in this article from Enlitic. 

• What tools are available to help radiologists work remotely? In this case study, teleradiology provider 4ways Healthcare of the UK describes how they used Merative’s Merge PACS 8.0 platform to improve their service to clients while supporting remote radiologists.

• How is Siemens Healthineers helping imaging providers meet their clinical and operational needs while maintaining high-quality care? Find out in this panel discussion with representatives from AdventHealth and WakeMed. 

• Change Healthcare’s cloud-native, zero-footprint Stratus Imaging PACS is live in clinical use. See how Stratus Imaging PACS is helping radiology practices improve productivity and patient care, while eliminating the cost and resource constraints of on-premise systems.

• United Imaging is developing modern medical imaging technology for better patient outcomes. CEO Jeffrey Bundy, PhD, explains the company’s unique philosophy in this interview with Healthcare Tech Outlook. 

• When it began implementing its AimSG nationwide AI program, Singapore’s Synapxe health technology agency relied on the CARPL.ai platform to make everything work. Learn more in this article. 

• Increasing demand for healthcare has led to a boom in imaging exam volume, with studies such as CT requiring complex scanning protocols. Learn how GE HealthCare is evolving CT workflows with its efficient scanning solutions.

• Subtle Medical has been named one of the 50 most promising private generative AI companies by CB Insights, one of just four healthcare companies on the list. Learn more about the Subtle solutions that led to this honor. 

• 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.

• Medical providers and health systems are looking to ditch the disc and modernize their patients’ journey. Learn how Clearpath helps them reduce the cost of retrieving and fulfilling patient requests for imaging and medical records.