Rohit Ghosh, founding member and chief strategy officer of Qure.ai

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

Our latest Imaging Wire Show, Implementing Radiology AI with the NHS Diagnostic Fund, delves into the safe and effective use of AI in radiology workflows within the UK NHS. With the deadline for the UK Government’s £21m NHS Diagnostic Fund closing in fast, we address the challenges and opportunities for enhancing patient outcomes using AI in hospitals and community diagnostic hubs. 

Our guests include Dr. Sarim Ather from Oxford University Hospitals NHS Foundation Trust, Dr. Rhidian Bramley from The Christie NHS Foundation Trust, and Rohit Ghosh from Qure.ai. They share their stories on the journey to AI activation including the benefits, elements needed for safe and secure activation, and how to achieve a timely deployment. 

Artificial Intelligence

Economic Barriers to AI

A new article in JACR highlights the economic barriers that are limiting wider adoption of AI in healthcare in the US. The study paints a picture of how the complex nature of Medicare reimbursement puts the country at risk of falling behind other nations in the quest to implement healthcare AI on a national scale. 

The success of any new medical technology in the US has always been linked to whether physicians can get reimbursed for using it. But there are a variety of paths to reimbursement in the Medicare system, each one with its own rules and idiosyncrasies. 

The establishment of the NTAP program was thought to be a milestone in paying for AI for inpatients, for example, but the JACR authors note that NTAP payments are time-limited for no more than three years. A variety of other factors are limiting AI reimbursement, including … 

• All of the AI payments approved under the NTAP program have expired, and as such no AI algorithm is being reimbursed under NTAP 
• Budget-neutral requirements in the Medicare Physician Fee Schedule mean that AI reimbursement is often a zero-sum game. Payments made for one service (such as AI) must be offset by reductions for something else 
• Only one imaging AI algorithm has successfully navigated CMS to achieve Category I reimbursement in the Physician Fee Schedule, starting in 2024 for fractional flow reserve (FFR) analysis

Standing in stark contrast to the Medicare system is the NHS in the UK, where regulators see AI as an invaluable tool to address chronic workforce shortages in radiology and are taking aggressive action to promote its adoption. Not only has NHS announced a £21M fund to fuel AI adoption, but it is mulling the implementation of a national platform to enable AI algorithms to be accessed within standard radiology workflow. 

The Takeaway

The JACR article illustrates how Medicare’s Byzantine reimbursement structure puts barriers in the path of wider AI adoption. Although there have been some reimbursement victories such as NTAP, these have been temporary, and the fact that only one radiology AI algorithm has achieved a Category I CPT code must be a sobering thought to AI proponents.

Reducing the Risk of Medical Errors and Misreads

What are the factors that contribute to errors and misreads in radiology – and how can they be prevented? Find out how to improve your practice’s quality and accuracy in this white paper from Medality.

AI Echo Copilot – The Future of Echocardiography

New technology from Us2.ai called Us2.connect allows you to add AI automation to any echo device. Any echo machine can now have 100% automated reporting with disease detection and editable measurements – all generated in realtime as you scan.

The Wire

• RadTwitter’s Top 100: What are the top 100 radiology accounts on X, the social media platform formerly known as Twitter? In an article in JACR, researchers listed the platform’s top 100 radiology accounts, based on factors such as followers and engagement (anonymous accounts were excluded). The most influential accounts were run by radiological societies, journals, radiology department, and imaging vendors. The top 100 accounts were listed, but in alphabetical order, leaving it up to others to determine who is at the top of radiology’s social media heap – such as Imaging Wire’s own list.

• GE Launches New Vscan POCUS: GE HealthCare launched Vscan Air SL, a new handheld ultrasound scanner, at last week’s ESC 2023. The new POCUS scanner sports a dual-headed probe consisting of both sector and linear arrays on a single device, making it ideal for switching between focused cardiac scans and vascular assessments at the point of care. Vscan Air SL is the latest evolution of the Vscan product line, to which GE has made numerous additions since it launched in 2010. 

• Better CT Lung Screening: Adding a smoking cessation program to CT lung cancer screening was effective in getting 24% of smokers to quit at 18 months in the PLUTO trial, a study of 636 smokers in JAMA Network Open. But referring smokers to prescription medication therapy management didn’t improve abstinence rates. PLUTO shows that adding cessation therapy to CT lung screening can save more lives than screening alone; getting 15% of smokers to quit would save as many lives as raising screening uptake from 30% to 100%.

• Riverain Lands Another VA Center: On the topic of lung screening, Riverain Technologies has added another hospital in the VA healthcare system to its list of customers. Dayton VA Medical Center has implemented the company’s ClearRead CT with Clear Visual Intelligence to detect lung cancer in CT scans. The deal builds on Riverain’s relationship to provide ClearRead CT to 22 VA hub and 87 spoke sites as part of the Lung Precision Oncology Program. ClearRead CT has also been installed at VA hospitals in Pittsburgh and Fresno. 

• Cardiac Images Scare Patients Straight: Showing patients medical images of their own heart structure spurred some to lead healthier lifestyles. In JACC: Cardiovascular Imaging, researchers analyzed six trials encompassing 7.1k patients who were shown either their own CT coronary artery calcium or carotid ultrasound of subclinical atherosclerosis. Follow-up at 10 years showed a 0.91% improvement in Framingham risk scores (P=0.01) as well as statistically significant reductions in LDL, total cholesterol, and systolic blood pressure (P<0.05). 

• More Prior Authorization Setbacks: A bill in the California state legislature would ban prior authorization for healthcare services in certain cases. SB 598 would prohibit health plans and payers from requiring prior authorization if the payer approved less than 90% of prior auth requests by the provider for that type of service in the previous one-year period. In another prior auth setback, Cigna Healthcare announced that it is removing prior auth requirements for nearly 25% of medical services, or 600 medical codes.

• UK AI Alliance: German AI platform developer deepc has entered the UK market through an alliance with BT (formerly known as British Telecom) to provide its deepcOS radiology AI platform to NHS hospitals. BT runs a digital health program within the NHS, and the deepc partnership will enable it to leverage AI as the health system works to reduce patient wait times in the UK. Deepc offers access to over 50 third-party AI algorithms through its platform; the company recently raised €12M in a Series A funding.

• Chatbot Ignores Clinical Guidelines: And you thought you had a hard time following clinical guidelines. In a new study in JAMA Oncology, 34% of the cancer treatment recommendations made by a large language model (LLM) chatbot (ChatGPT 3.5) did not comply with established NCCN guidelines. What’s more, the chatbot demonstrated the “hallucination effect” for 13% of its recommendations. The study shows that passing the medical boards is one thing; actually directing treatment is another. LLMs definitely need more work before they can be used clinically.

• Blackford Adds Echo AI to Platform: Blackford Analysis has added the Ligence Heart echo AI algorithm from Ligence Medical AI Solutions to its Blackford Platform. Ligence Heart is an echo analysis suite that mimics the steps taken by cardiologists and sonographers, enabling clinicians to analyze echo images moments after they are acquired. Ligence Heart has a CE Mark and is pending FDA clearance. Other recent additions to Blackford Platform include Brainreader, AI4MedImaging, and Lunit. 

• CurveBeam AI Goes Public: Point-of-care CT developer CurveBeam AI went public last week on the ASX Australian stock market with an IPO that raised AUS$25M ($16M). CurveBeam AI’s flagship product is HiRise, a cone-beam CT scanner for weight-bearing extremity studies, and the company is developing SkyRise for weight-bearing spine and shoulder exams. CurveBeam AI also offers AI algorithms for orthopedic and bone health that the company accessed through its 2022 merger with StraxCorp.

• Detecting AS with 2D Echo AI: A Yale-led team developed a novel ultrasound AI model that can identify severe aortic stenosis using a single 2D echo view, rather than specialized Doppler echo images typically used for AS diagnosis, and could allow aortic stenosis screening using handheld ultrasound in community settings. After training with 5.3k studies from Yale (17.5k videos), the model detected severe AS in three datasets from Yale, Cedars-Sinai, and four New England hospitals with consistently high AUCs (0.978, 0.952, 0.966).

• Missing the Mark on Stroke Guidelines: When someone having a stroke arrives at the ER but needs procedures at another hospital, current guidelines say that no more than 120 minutes should elapse between arrival and departure. New research in JAMA found that nearly 2k US hospitals miss that mark by almost an hour, with the median door-in-door-out time clocking in at 174 minutes. Black, Hispanic, female, and over-80 patients all experienced longer times, with COVID also tacking on an extra 16 minutes between 2019 and 2021.

• Argus Cognitive’s RV Clearance: Argus Cognitive landed FDA 510(k) clearance for its ReVISION software, which analyzes 3D echo exams to help cardiologists discover and risk-stratify hidden right ventricular dysfunction. ReVISION is one of the few solutions supporting RV echo analysis, and reportedly the only solution that allows clinicians to fully characterize RV function using 3D echocardiography, while joining a range of LV-targeted echo solutions.

Improving Radiology Accuracy and Scale with Cloud AI

See how AI and the cloud combine to alleviate IT challenges and amplify radiologist performance in this Arterys white paper.

Next-Generation Radiology Reporting

Listen to the conversation in this webinar recording and hear from PACS administrator Griff R. Van Dusen of Memorial Health System how Nuance PowerScribe One’s next-generation reporting experience helps streamline workflow and improve report quality so radiologists can get more done in less time.

A Perfect Balance of Utility and Nirvana

The One Viewer philosophy from Visage offers end users from across the enterprise the chance to get access to Visage 7’s powerful tools based on their clinical need, with the same #1 rated viewer for multiple workflows. Find out today how it works.

The Resource Wire

• Healthcare providers can’t feel confident in the impact they make for their patients without feeling their IT environments are resilient and reliable. This eBook from Merge by Merative breaks down 3 essential ingredients of a resilient imaging IT environment: hybrid cloud, reliable uptime, and zero-trust security. 

• Cutting-edge software solutions are transforming radiology by enabling the generation of synthetic medical images. Learn more about the potential of Subtle Medical’s SubtleMR and SubtleSYNTH applications in this September 21 webinar. 

• When it comes to the cloud for healthcare providers, one size does not fit all. Healthcare organizations are adopting a mix of hybrid and multicloud operating models. Learn more about this emerging trend in this article by Intelerad Chief Product Officer AJ Watson.

• Cleaning up radiology data takes more time than you might think. Learn how Enlitic’s Curie|ENDEX solution transforms medical image data descriptions to a consistent, clinically relevant standard nomenclature.

• Interest is growing in collecting patient-reported outcome measures (PROMs) in healthcare, but how can your hospital implement a PROM collection system? Learn how to get started in this white paper from PocketHealth. 

• Check out this Blackford Analysis white paper detailing how children’s hospital imaging teams can leverage AI to improve modality throughput and imaging device availability.

• What is theranostics, and how is it changing oncology patient care? Learn more about theranostics and how Siemens Healthineers can support your theranostics journey by offering precision oncology tools that cater to every step of the care pathway.

• When the VA adopts your technology nationwide, you know you’ve been making an impact. That’s exactly what’s happening with Riverain Technologies’ ClearRead CT, which will be implemented across the VA Lung Precision Oncology Program (22 hub and 87 spoke locations).

• How is Clearpath improving the healthcare experience for patients? Learn more about the company and its solutions for ditching the disc when sharing images and records with patients. 

• Check out this Change Healthcare video explaining the difference between single-tenant and multitenant cloud architecture, and how multitenant solutions can improve your efficiency and flexibility.

• See how United Imaging’s uCT ATLAS combines advancements in image quality, patient comfort, and operator efficiency to bring you one step closer to your masterpiece.

• Imaging AI is evolving fast, but radiology leaders’ expectations for their AI technologies might be evolving even faster. In this Imaging Wire Show with Dr. Charlene Liew of SingHealth and Dr. Nina Kottler of Radiology Partners, we explore radiology leaders’ current and future expectations for AI, and the central role platforms play in their AI roadmaps.

• Health boards in Scotland are working with AI on a trial basis for tasks such as cancer screening. Find out how NHS Grampian’s radiology department turned to Annalise to identify abnormalities on chest radiographs. 

• What is theranostics, and how is it changing cancer diagnosis and treatment? We talked to Shari Manuel, Chris Heble, and Elfareato Remekie of GE HealthCare in this Imaging Wire Show about the exciting new developments happening in theranostics that are enabling a new era of precision healthcare.

• AI in healthcare has grown quickly, as have discussions about AI regulation. Listen to this on-demand webinar from Bayer and Calantic Digital Solutions to hear expert perspectives on the current and future state of AI governance in healthcare and radiology.