Identifies and Reduces Bias in Models

Today, there is plenty of skepticism around AI/ML due to poor quality of evidence supporting many models that are coming to market. Mayo Clinic Platform_Validate is leading the charge in eliminating bias in models.

How It Works

Mayo Clinic Platform_Validate, enabled by a large volume of de-identified data, can accurately and impartially evaluate the efficacy of a model and its susceptibility to bias.

Validate helps measure model sensitivity, specificity and bias, and enables the breaking of racial, gender, and socio-economic disparities in the delivery of care. Mayo Clinic Platform_Validate lends credibility to models, accelerates adoption into clinical practice and enables meeting regulatory requirements for approval.

The Technology

As our customer, you will receive a series of descriptive statistics of model performance and data that the model was run against for each demographic. 

As more data is collected through Gather and other data sources, Mayo Clinic Platform_Validate will be able to do more than assess quality and evaluate bias for models. Validate will be able to offer multiple validations across a range of datasets and even identify additional populations to which the model can be applied.

Mayo Clinic Platform leads a coalition of like-minded health systems, academic institutions, companies and experts to set standards and guidelines for health care AI efficacy, ethics, fairness, transparency and fit for purpose.

Evaluate and certify quality and accuracy of models.

Detect and minimize
bias in models.

Utilize de-identified data to measure current model sensitivity and specificity.

Ensure regulatory approval requirements are met.

Together, let's change the future of health care.

Mayo Clinic Platform_Validate is ideal for algorithm developers.

Connect with us: