This project involves a machine learning (ML) model to predict hospital admissions using data collected in an Emergency Room (ER).
| Index | Description |
|---|---|
| Motivation and Project Overview | High level overview describing the project motivation and solution |
| High Level Architecture | High level overview illustrating component interactions |
| Training and Experimentation Guide | Guide on comparing different models, viewing results and launching a final training job to generate a model for deployment |
| Deployment | How to deploy the project |
| Dashboard Interface Guide | How to interact with the solution dashboard |
| Directories | General project directory structure |
| API Documentation | Documentation on the API the project uses |
| Changelog | Any changes post publish |
| Credits | Meet the team behind the solution |
| License | License details |
When a patient visits an ER, typically they are triaged by ER nurses to collect preliminary information about the visit, and a few hours later, the patient receives a decision from a doctor regarding hospital admission. A ML model that can predict hospital admissions at the time of triage could potentially save the ER time to coordinate beds and allocate staffing resources.
A random forest classifier was identified as the best classifier for the task. This solution prototype includes a dashboard for ER clinicians to sort ER patients by the model output and thus urgency/likelihood of patient admissions.
The solution utilises AWS resources to host a trained ML model and provide a dashboard with patient information.
The following architecture diagram illustrates the various AWS components utilized to deliver the solution.
This solution enables users with ML knowledge to fine-tune and test out different models using Sagemaker Notebooks. For details, please refer to the Training and Experimentation Guide.
To deploy this solution, please follow the steps laid out in the Deployment Guide
Please refer to the Interface Guide for instructions on navigating the dashboard interface.
├── cdk
│ ├── bin
│ ├── lambda
│ ├── layers
│ ├── lib
├── docs
└── frontend
├── public
└── src
├── assets
├── components
├── functions
└── pages
/cdk: Contains the deployment code for the app's AWS infrastructure/bin: Contains the instantiation of CDK stack course when files are uploaded or deleted./lambda: Contains the lambda functions for the project/layers: Contains the required layers for lambda functions/lib: Contains the deployment code for all infrastructure stacks
/docs: Contains documentation for the application/frontend: Contains the user interface of the application/public: public assets used in the application/src: contains the frontend code of the application/assets: Contains assets used in the application/components: Contains components used in the application/functions: Contains utility functions used in the application/pages: Contains pages used in the application
Here you can learn about the API the project uses: API Documentation.
N/A
This application was architected and developed by Rohit Murali, Khushi Narang, with project assistance and front-end development support by Amy Cao. Thanks to the UBC Cloud Innovation Centre Technical and Project Management teams for their guidance and support.
This project is distributed under the MIT License.