Telehealth and remote vital signs monitoring
Developing a project whose core objective is to consume health tracking apps (eg; Android Health Connect) data or custom devices in order to allow monitoring of vital signs
- by the customer
- by their authorised members of their social network of friends and family. Communication is tailored to the preferred communication channel of each user.
- by telehealth providers performing mass monitoring of signed-up customers, ready to arrange response or callback
A loosely coupled architecture will encourage and allow affinity services to be integrated into the service.
Possible examples include:
- personal DNA related health information
- local emergency incidents impacting customer risk
Personalised AI assisted anomaly detection at scale
Harnesses the power of hyper-personalised AI, social networks, and mobile devices, wearables to remotely monitor at-home user's vital signs. With optional connectivity to user's selected social network, providing them reassurance or escalating for action.
Leveraging an individualised AI model (the 'AI shadow of user's health profile') that continuously learns about the user and what is 'normal' for them, all the time getting better at detecting anomalies.
Over half of fatalities due to respiratory or cardiac issues according to US statistics*, could have been avoided if abnormal readings had been acted upon within an hour!
Telehealth and remote monitoring services are already providing a lower cost at-home alternative to round the clock home care or hospital stays. This service aims to drive down the barriers to entry further, so that it is open to wider base of user's.
Future proofed
Component based architecture built round microservices will allow other complementary services to be built or bought 'off the shelf' and integrated into the application, to further refine the AI model's capabilities.
Technical overview
Please check out the readme in link below for more technical detail.
It will work by building a individual AI model for that user and then monitor user's ongoing health metrics by evaluating data consumed from say, Android Health Metrics data, with the model. Any anomalies are alerted on a UI available to user, along with notifications through other channels.
Stack is currently AWS ECS,
Sagemaker, Kafka, Flutter maybe for UI and AWS Quick sight initially.
Getting involved
If anyone wishes to collaborate, add feedback, the Github project is at
https://github.com/jackpa99/iot_health_to_ai_aws
Top comments (0)