A new study offers a breakthrough in detecting risk for #psychosis and #bipolar disorders.
🔗Find out how this work could help clinicians provide more tailored support for people living with these conditions: tinyurl.com/33s73ss9
🧵 In Summary
Prediction models are not “set and forget.” They must be constantly checked, updated, and re-evaluated—before and after clinical use.
With thoughtful updating, we can keep models useful and safe over time.
📄 Read our commentary: kwnsfk27.r.eu-west-1.awstrack.me/L0/https:%2F...
A new study backed by our BRC Data Science Theme found that CBD may worsen memory and psychotic symptoms when taken before THC in people with #schizophrenia who use cannabis.
🔗Read more on our website: tinyurl.com/4sjnrh2s
@oxfordpsychiatry.bsky.social
🚨 What About After Implementation?
Once a model is used in practice, it changes patient outcomes (e.g., high-risk patients get treated and avoid the outcome).
This shifts the relationship between risk factors and outcomes. Updating without accounting for this is risky.
In our commentary, we have expanded on the findings of the study, the impacts of temporal drift and the importance of addressing it.
💻 The Catch? Complexity
Dynamic updates need:
Continuous data
More computing power
Digital infrastructure in place
Also, no method kept the original performance in later years. So, updating helps—but doesn’t fix everything.
A recent study looked at which methods could be effective at addressing this drift doi.org/10.1016/j.bp...
They found that without updating, model performance deteriorated and dynamic updating might be able to address this.
⚖️ Fairness Under Threat
Temporal drift can impact some groups more than others.
Even worse, updating models doesn’t guarantee fairness. It can reduce—or worsen—performance in minority groups.
We need to monitor algorithmic fairness, not just accuracy.