Building an AI Powered Health Ecosystem

P2P networks have several advantages over client-server architectures. First, they are self-scalable and can grow up to hundred of thousands of peers. Additionally, instead of being concentrated on a single server, compute and storage costs are shared by each of the peers in the network.

As the world moves towards a more digitized and connected healthcare system, there is a huge opportunity to leverage emerging and digital technologies in low-resource settings to help clinicians with decision making and administrative tasks, connect data across facilities, and improve overall health outcomes.

A lot can go wrong when using machine learning in healthcare. This article talks about some of those things from our experience and some considerations to keep in mind.

Even though the care providers have frequent encounters with the community, they do not have the training necessary to deal with any non-trivial situations they may encounter. Given the reach of community health workers, empowering them with digital tools and decision support algorithms can have an immense impact on health delivery and outcomes.

Healthcare is our collective responsibility, and in the digital present and the algorithmic future, the open model is our best shot at health equity

The potential improvements in healthcare delivery and monitoring for hypertensive patients can be multiplied when we leverage the data collected by EMR records to build intelligent, adaptive and personalized care algorithms.

Introducing a casual series of posts to discuss randomness and probabilities geared to healthcare providers who want to work with AI and Elsa algorithms.

Using Federated/Collaborative Learning approaches, in a connected and privacy preserving network, we can leverage each others expertise and prevalence information to treat patients even better.