Data sharing

With your consent for every uploaded record, we plan to publicly share anonymized health records, for free, for the common good: help researchers, doctors, companies, students find patterns (example), insights and new treatments.

For example, researchers used more than 1,000 deidentified patient X-rays to train a deep-learning network to detect tuberculosis. The network had close to a 100% accuracy rate, which could be especially promising in areas with shortages of radiologists.

Why isn’t such data & software available for free to every hospital & researcher in the world, for the greater good? Because profits matter more than health.

By sharing your fully anonymized data, with your approval, we’ll also help others develop software which flags potential anomalies in medical scans. For example, we plan to automatically analyze MRI scans and capsule endoscopy videos, and point out areas to be double-checked by doctors.