Capacity Dashboard for Authority/Hospitals
Overall Consumables Statistics Dashboard
Overall Patient Statistics Dashboard
Hospital Capacity Details and Forecasted Data
Transaction Log and Corresponding Blockchain Transaction
Capacity/Consumable Category Creation Screen
Ambulance can reserve a bed for the patient based on symptoms
The availability of medical facilities and equipment has become a challenge due to an exponential increase in the demand during this pandemic (Covid-19). The lack of data visibility results in the under-utilization of resources and wrong routing of patients. There is a need for a solution that could help track critical medical resources and at the same time could forecast and track its supply chain.
What it does
VitalWatch is a Blockchain-powered solution which aims to track critical resources at multiple medical facilities in various regions of a country. The resulting single source of truth keeps all the stakeholders (Hospitals & Administration) in sync. It also leverages ML which helps in capacity forecasting and planning. Information is disseminated in real-time for efficient resource utilization.
It provides a Bird-eye view of critical medical resources for the hospitals in the region, state, or country.
It will help in patient channelization to the appropriate facility based on patient condition and need. Ambulance users can find nearby hospitals based on patient condition, reserve bed/ICU/ventilator as per need, and route the patient.
It will help to forecast the need for critical medical resources using machine learning models.
How we built it
VitalWatch Blockchain platform is a Hyperledger Fabric blockchain network setup using Azure AKS Cluster instance. Azure Machine Learning Studio allows creating datasets, pipelines to execute ML experiments. After multiple experiments with different models, Stack Ensemble was chosen as it had minimum “Normalized root mean squared error” among the results from numerous other algorithms. Azure Container Instances have been used to deploy the selected trained models; alternatively, AKS can also be used to deploy them. The blockchain organization certificates are securely stored using Azure Key Vault. The NodeJS business API’s and compiled Angular based user interface can be hosted with either Azure App Services and/or Virtual Machines. Azure CosmosDB is used as a choice for platform off-chain database to be used to store blockchain transaction id’s and front-end UI’s configuration information. The Azure CosmosDB with MongoDB is also used to store the input data for the machine learning models. Azure Log Analytics workspace is used with Azure Monitor to collect and monitor container logs. Our solution also uses Prometheus and Grafana to collect, monitor, and visualize the Blockchain Platform operation metrics.
Challenges we ran into
This was our first time using Azure(Kubernetes, Machine Learning, CosmoDB, App Services, Blockchain, and many more). It was difficult to figure out everything from scratch and do it.
Accomplishments that we're proud of
Figuring out Azure products and making our project work.
What we learned
We learned a lot of things. We participate in hackathons so that competitiveness makes it more interesting to learn things faster. This hackathon challenged us and we learned so much like how to integrate database, blockchain, and frontend, and many more.
What's next for VITAL WATCH
Making User interface more attractive