A digital twin keeps a living, virtual model of a patient's immune activity in sync with joint imaging, inflammatory labs, and daily symptom data — then runs the simulations a quarterly rheumatology visit never has time for, so treatment decisions happen before a flare causes joint damage, not after. Walked through below using rheumatoid arthritis as the working example.
One of the daily symptom-diary entries, plus periodic CRP labs and joint imaging feeding the same model on a slower cadence.
The twin isn't a textbook patient — it's calibrated to how this one person's joints actually respond.
Every treatment option is tried on the model first. The full forecast is below.
One alert, two audiences: the rheumatology team sees the risk, the patient sees the action.
The gauges above show why the twin's forecasts are personal. Here's the actual simulation it ran from a single day-4 CRP draw, testing three treatment courses against this patient's model before anyone committed to one.
The rheumatology team never sees the raw branching — only the ranked outcome, so their time goes to the decision, not the data.