Summary
In this chapter, we got an understanding of what patient risk stratification is and why it is important. We also got insights into why conventional analytical approaches may not be enough to stratify patients for risk. We then looked at various steps and guidelines before embarking on building a patient risk stratification model.
We got introduced to SageMaker Canvas, the no-code service from AWS that allows business analysts to build ML models.
Lastly, we went through an exercise creating an ML model to identify whether a breast mass is malignant or benign based on cell nuclei features and learned how this could help prevent the disease from taking a turn for the worse.
In Chapter 4, Using Machine Learning to Improve Operational Efficiency for Healthcare Providers, we will learn about how ML can help make healthcare providers more efficient in providing patient care by automating certain time-consuming tasks.
