Christoph Wald, M.D., Ph.D., M.B.A., F.A.C.R.’s Post

I know so many healthcare organizations are still sitting on the fence when it comes to investing in AI. The lack of reimbursement for these applications is one of the main things preventing widespread deployment, but a panel of experts at #SIIM24 say this shouldn't keep organizations from taking advantage of all the #AI has to offer now.

Excited to share the latest news from the Harrison.ai team: our multimodal foundational model Harrison.rad.1, a major step forward in medical AI. Harrison.rad.1 is a specialised medical model with an open-ended chat interface that can detect and localise radiological findings, generate clinical-grade reports, and provide longitudinal reasoning based on clinical history and patient context. It's the most capable multimodal model in radiology, trained on a high-quality dataset of millions of images, radiology studies, and reports. What sets Harrison.rad.1 apart? It outperforms competitor LLMs by nearly 2x on the FRCR Rapid 2B radiology exams and achieves 82% accuracy on closed questions current industry standards dataset VQA-RAD, beating some of today’s leading models. But beyond the numbers, what truly matters is how as a society we can use technology such as this responsibly. We’re making Harrison.rad.1 accessible to select radiologists, clinicians, healthcare professionals, and regulators to spark essential conversations about the responsible and ethical use of AI in healthcare. This is just the beginning of a much-needed dialogue on how AI can safely and effectively innovate healthcare. Learn more about Harrison.rad.1 and register your interest to collaborate with us: https://lnkd.in/gm_xHFbr.

"...The ACR Recognized Center for Healthcare-AI (ARCH-AI) set the guidelines for AI use in imaging interpretation and ensures radiology facilities are using AI safely and effectively. It is the first national artificial intelligence quality assurance program for radiology facilities designed to recognize adherence to best practices for use of AI in imaging interpretation. The criteria for a site to be considered an ARCH-AI site are: - Establishing an interdisciplinary AI governance group. - Maintaining an inventory of AI algorithms with detailed documentation. - Ensuring adherence to security and compliance measures. - Engaging in diligent review and selection of AI algorithms. - Documenting use cases and training procedures. - Monitoring algorithm performance, including safety and effectiveness. - Participating in the Assess-AI national AI registry for performance benchmarking..." Fredrik Nomme Kristian Kolnes Brita Eline G. Halleraker Harald Nes Hilde Lovett Mikael Boesen https://lnkd.in/dz2HpBp6

They have finally understood the importance of the below mentioned statements 👇🏻👇🏽👇🏿👇in the #US and can collaborate around making the needed infrastructure and provide a certificate for participants for complience to the needed rules for implementing, running and quality ensuring Radiological AI - Lets do the same in #Denmark and the Nordics. We have long been ready to run a similar blueprint and digital governance and AI data infrastructure in all regions of Denmark as Radiology was chosen as the AI usecase started by Danish regions in 2023 where we agreed that all of the below mentioned bullets where needed for running AI in Radiology in the clinical environment at scale. Sundhedsstyrelsen Lægemiddelstyrelsen (Danish Medicines Agency) Indenrigs- og Sundhedsministeriet Digitaliserings- og Ligestillingsministeriet Danske Regioner - Danish Regions Marie Bjerre Anders Kühnau Lars Gaardhøj Erik Jylling Mette Harbo Bodil Ørkild Kirsten Wisborg Randi Brinckmann RAIT Denmark CAI-X - Centre for Clinical AI

It's no secret that radiology is the leading champion for AI thus far. As more radiology departments join the fray and seek out the right vendor for their needs, it's important to have a solid foundation for asking the right questions before formally choosing. The well established guidelines called "Evaluating Commercial AI Solutions in Radiology" (ECLAIR) offer 10 questions to ask when engaging with a potential vendor. Here are the takeaways from each of the 10 to help steer the buying decision. #radiology #healthcareai

🎙️ Exciting Podcast Alert! 🎙️ Part of my mission with NextFutureToday is to go well beyond the surface level of AI (Now with 1000% more hype!), and I found a great exemplar in this interview with Jeff Chang, co-founder of RadAI. We went deep into the impact of AI in radiology and its potential to alleviate burnout and repetition for radiologists. Here are three key takeaways from our discussion: 🔍 Operational AI Solutions: RadAI focuses on operational AI, streamlining processes and reducing the time spent on dictating reports. Their innovative approach seamlessly integrates into radiologists' workflow, making it a zero-click solution - a game-changer for the industry. 🏥 Patient Care Enhancement: The company not only assists radiologists but also addresses the problem of patient leakage (where patients fall into a blackhole on their next steps), ensuring follow-up imaging for specific findings. Their smart work list and follow-up care coordination tools are reshaping patient care and communication in healthcare systems. 🚀 Agile Adaptation and Innovation: RadAI keeps a pulse on industry needs and customer feedback, constantly refining and expanding its product suite. Their upcoming introduction of new generative AI elements promises even further improvements in radiology workflow. Full episode at: https://lnkd.in/ebrNNFCY https://lnkd.in/e_yWUBSA https://lnkd.in/efxZB5Cm #AIinRadiology #OperationalAI #HealthcareInnovation #RadAI

Good comprehensive approach.

A must read for any enterprise evaluating AI solutions

Here is a nice story about the Sectra Amplifier Services and how it helps one of our customers.

Highlights from our March'24 Newsletter! We've got insights on driving 5x ROI in radiology AI, a study by Dr. Charlene Liew, and our new series Unboxing AI, featuring experts talking about Large Language Models and AI's future in radiology. Subscribe for a dose of AI-powered healthcare innovation: https://lnkd.in/dJ7FJrf3 #MakingAIReal #Newsletter #RadiologyAI #UnboxingAI