Adding and managing models
Last updated
Last updated
Adding and managing models on DXAI.app is designed to be intuitive and user-friendly, giving AI researchers full control over their models.
To add a new model, researchers must complete a simple form:
URL: Provide the location where your model is deployed, such as platforms like Hugging Face, Streamlit, AWS, Azure, or others. This allows us to access your model directly for inferences.
Variables: List the variables used by your model to make inferences. This information is crucial for us to understand the input parameters.
Description: Provide a detailed explanation of how the model works and the methodology used in its training. This helps us better understand the model's capabilities and applications.
Speciality: Select the relevant specialty for your model (e.g., cardiology, radiology, etc.), ensuring it’s categorized for healthcare representatives to easily find and use.
Once added, researchers can manage their models efficiently:
Get rated: we will stress-test your models and assign a rating based on model's performance (based on identified variables such as sensitivity, specificity, precision, accuracy, and others) against our proprietary image datasets.
Delete: Remove models that are no longer in use or need updating.
Track Performance: Monitor how your models are performing, including inferences made and feedback received from healthcare representatives.