The Multiple Myeloma Channel is supported with funding from Sanofi (Gold) and Legend Biotech (Bronze).
VJHemOnc is an independent medical education platform. Supporters, including channel supporters, have no influence over the production of content. The levels of sponsorship listed are reflective of the amount of funding given to support the channel.
ASCO 2026 | Early detection of myeloma and MGUS progression risk using AI and routine laboratory data
Ciro Rinaldi, MD, PhD, United Lincolnshire Teaching Hospital and University of Lincoln, Lincoln, UK, discusses the potential of using artificial intelligence (AI) and routine laboratory data for early detection of multiple myeloma (MM) and for identifying progression risk in patients with monoclonal gammopathy of undetermined significance (MGUS). Prof. Rinaldi shares insights into the development of an AI model that can predict the risk of progression from MGUS to myeloma, even in patients in the ‘low-risk’ MGUS category, and notes that this model could have a significant impact on clinical practice by enabling more personalized monitoring and timely referral. This interview took place during the 2026 American Society of Clinical Oncology (ASCO) Meeting in Chicago, IL.
These works are owned by Magdalen Medical Publishing (MMP) and are protected by copyright laws and treaties around the world. All rights are reserved.
Transcript
So artificial intelligence is clearly coming more and more into our clinical practice and not just for, you know, support and help in reducing the administrative burden in clinics, but it also has the power to, you know, identify early progression, you know, prognostication, etc. So what I’ve done in collaboration with De Montfort University in Dubai was to design a potential application for looking at the MGUS progression possibilities and utilizing a different number of AI models...
So artificial intelligence is clearly coming more and more into our clinical practice and not just for, you know, support and help in reducing the administrative burden in clinics, but it also has the power to, you know, identify early progression, you know, prognostication, etc. So what I’ve done in collaboration with De Montfort University in Dubai was to design a potential application for looking at the MGUS progression possibilities and utilizing a different number of AI models. What we are presenting here is the result of the most aligned, where with a degree of precision that is acceptable from our computer engineer, we were able, from a cohort of MGUS patients, studied over time, looking at which ones were progressing into multiple myeloma, even if they were technically part of a low-risk MGUS category. The reason why there is a need for this is because even now, what we say to patients with MGUS is that there is a chance they can progress into myeloma, which is about 1% a year. That is a very, very wide way of saying, you know, there’s no, you know, clear prognostication system where you can pull clinical data or laboratory data and give a proportion of risk. What this, you know, AI model is able to do is to give that possibility. So what we are trying to understand now is, obviously, the model was trained based on data from a historical cohort of patients. What we want to do is now proactively look at patients and see whether that prognostication actually is correct. And that could have a very important impact in clinical practice because some patients that might progress quickly might need to be seen in clinic more frequently. Patients that actually have a very, very low risk of progression might not need to be seen in a specialist hematology clinic. It might be monitored by general practice and there’s no need to be referred to an acute hospital altogether. And also, it will give a degree of reassurance for patients in the future. So an exciting time.
This transcript is AI-generated. While we strive for accuracy, please verify this copy with the video.
Read more...
