For this project, Intel partnered with a healthcare organization and a data science consultancy to develop a proof of concept predictive model that can be used to assign a risk score to patients based on the likelihood that they may require an emergency medical intervention within an hour. The goal of this project is to demonstrate how an analytics cluster, based on servers running Intel® Xeon® processors with Cloudera*, can be leveraged to develop predictive models that are clinically relevant. We plan to open source the predictive model to accelerate development for other healthcare customers by providing a ready made proof of concept that can help analytics teams shorten the time to value for new infrastructure.
To get started, follow the links below:
- Implementation guide: https://github.com/bartleyintel/model-for-predicting-rapid-response-team-events/blob/master/Model-for-predicting-rapid-response-events-implementation-guide-final.pdf
- Model: https://github.com/bartleyintel/model-for-predicting-rapid-response-team-events/blob/master/notebooks/modeling/modeling_diff_algorithms.ipynb
- Data science notebooks: https://github.com/bartleyintel/model-for-predicting-rapid-response-team-events/tree/master/notebooks
- Test data set: