Abstract
Welcome to your first in-depth look at machine learning and the code behind it. In this chapter, we will be working with a dataset from the National Electron Injury Surveillance System (NEISS). This dataset, encompassing emergency room visits from 2011 to 2019 on basketball-related injuries, will be used in a task to predict whether an individual is admitted or not given their age, race, sex, location where the injury occurred, body part affected, preliminary diagnoses (from triage), and size of the care center. In the process of attempting to predict admission status, we will encounter a number of issues in machine learning including how to deal with imbalanced data, how to tune hyperparameters, and how to do feature engineering.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2022 Abhinav Suri
About this chapter
Cite this chapter
Suri, A. (2022). Project #1 Machine Learning for Predicting Hospital Admission. In: Practical AI for Healthcare Professionals. Apress, Berkeley, CA. https://doi.org/10.1007/978-1-4842-7780-5_5
Download citation
DOI: https://doi.org/10.1007/978-1-4842-7780-5_5
Published:
Publisher Name: Apress, Berkeley, CA
Print ISBN: 978-1-4842-7779-9
Online ISBN: 978-1-4842-7780-5
eBook Packages: Professional and Applied ComputingProfessional and Applied Computing (R0)Apress Access Books