My Capstone for the HarvardX Course "Introduction to Data Science with Python" Task: Compare scenarios from different countries' COVID-19 Response to emphasize the problem of relying on a single metric such as accuracy for prediction.
Problem Setting: At the peak of the COVID-19 pandemic, hospital authorities had to make a call about who to admit and who to send home given the limited available resources. Our problem is to have a classifier that suggests whether a patient should be immediately admitted to the hospital or sent home.
The Data: The data consists of the following predictors:
- Age
- Sex
- Cough
- Fever
- Chills
- Sore Throat
- Headache
- Fatigue
The outcome is a classification prediction to indicate the urgency of admission.
- Positive: Indicates that a patient that was admitted within 1 day from the onset of symptoms.
- Negative: Indicates everyone else.