The Mayo Clinic plans to use a combination of federated learning and deidentified data to generate new insights into patient data at a massive scale. This is a laudable effort - but given that federated learning protects the privacy of patients, is it the right thing to also use deidentified data? I make the case that it isn't and Mayo should use identified data instead.
For your security, we need to re-authenticate you.
Click the link we sent to , or click here to log in.