Clinical Validation of DystoniaNet for Dystonia Diagnosis
This study is testing a new computer program called DystoniaNet to see how well it can diagnose dystonia (a movement disorder causing involuntary muscle contractions) and tell it apart from other conditions that have similar symptoms. Currently, it can be hard to get an accurate diagnosis for dystonia, often taking many years. Researchers want to see if DystoniaNet can provide a faster and more accurate diagnosis. The study will look at information from past patients and also follow new patients. You might be able to join if you have any form of dystonia. The main goals are to see how accurate DystoniaNet is at diagnosing dystonia and how quickly it can do so, with these results being measured over four years.
- Study design
- This study aims to enroll 1000 participants and involves using the DystoniaNet program for diagnosis. It includes both looking at past patient data and following new patients.
- What's involved
- Not specified in the trial record.
- Compensation
- Not stated in the trial record.
- Follow-up
- The main study outcomes will be measured at 4 years.
AI-generated from the public study record. Only the study team can confirm whether you're eligible — confirm details with them before making decisions.
Clinical Validation of DystoniaNet Deep Learning Platform for Diagnosis of Isolated Dystonia
At a glance
Conditions
Where it's being run
1 sites across 1 statesStudy leadership
- Kristina Simonyan, MD, PhD · PRINCIPAL_INVESTIGATOR · Massachusetts Eye and Ear
Who to contact
Opens a ready-to-send draft in your own email app — review before sending.
What this trial measures
- Correctness of clinical diagnosis of dystonia using the DystoniaNet algorithm4 years
Correctness of dystonia diagnosis (yes dystonia/no dystonia) will be established using the DystoniaNet machine-learning algorithm
- Time of clinical diagnosis of dystonia using the DystoniaNet algorithm4 years
The length of time (in months) from symptom onset to clinical diagnosis will be established using the DystoniaNet machine-learning algorithm