Aug 27, 2026 · 31 min · 13 segments
**Can growing amounts of real-world MS data help clinicians predict disease progression and make more personalised treatment decisions?** In this episode of the ECTRIMS Podcast, host Brett Drummond…
Carmen TurGuest
Will BrownGuest
Brett DrummondHost
Well, I think the central challenge is that MS does not reflect one disease process, it does not run on one clock, and it does not produce one outcome.
So there's extraordinary biological and clinical heterogeneity, and w- we all see this.
Two people the same age, same duration of MS, and apparently a similar MRI scan can have completely different trajectories.
And that balance between the processes underlying that, the focal inflammation, the compartmentalized inflammation, the neurodegeneration, repair and when it fails, neurological reserve, these all vary both between individuals, but also within an individual over time.
So it's really hard to predict what we don't understand, and those processes that we do understand often lack the biomarkers that have sufficient specificity and sensitivity, but are widely available and practical to repeat.
If I can add to this, I would say that up to now we had very limited data, so we have been, uh, having more data sets, more rich, uh, data sets as well.
And also, as Will was saying, we have, uh, gained, uh, more understanding of the disease, and this has allowed us to build, uh, predictive models, uh, based more on biology than before.
Because now we know that there are these two types of, um, inflammation or kind of processes, more acute process and more a chronic process.
So this has also allowed us to build clinical outcomes that are more in line with these two types of processes, and this has allowed us to, to perform more accurate, uh, solutions to, to the future.
And, and of course, the, the start of AI or the eruption of AI and machine learning, uh, models has, uh, helped us to make more powerful predictive models.
Well, I think the central challenge is that MS does not reflect one disease process, it does not run on one clock, and it does not produce one outcome.
So there's extraordinary biological and clinical heterogeneity, and w- we all see this.
Two people the same age, same duration of MS, and apparently a similar MRI scan can have completely different trajectories.
And that balance between the processes underlying that, the focal inflammation, the compartmentalized inflammation, the neurodegeneration, repair and when it fails, neurological reserve, these all vary both between individuals, but also within an individual over time.
So it's really hard to predict what we don't understand, and those processes that we do understand often lack the biomarkers that have sufficient specificity and sensitivity, but are widely available and practical to repeat.
If I can add to this, I would say that up to now we had very limited data, so we have been, uh, having more data sets, more rich, uh, data sets as well.
And also, as Will was saying, we have, uh, gained, uh, more understanding of the disease, and this has allowed us to build, uh, predictive models, uh, based more on biology than before.
Because now we know that there are these two types of, um, inflammation or kind of processes, more acute process and more a chronic process.
So this has also allowed us to build clinical outcomes that are more in line with these two types of processes, and this has allowed us to, to perform more accurate, uh, solutions to, to the future.
And, and of course, the, the start of AI or the eruption of AI and machine learning, uh, models has, uh, helped us to make more powerful predictive models.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.