Team: Stats N Facts
INFO 523 - Spring 2023 - Project 1
Which COVID vaccines have undergone the most revisions while maintaining an approved authorization status with no conditions applied?
Answering question 1 requires the use of the following variables:
Column Name | Description |
---|---|
medicine_name | The brand name of the medicine |
therapeutic_area | The therapeutic area for which the medicine is authorized |
authorisation_status | The authorization status of the medicine |
conditional_approval | Indicator if conditional approval is applied |
revision_number | The number of revisions for the medicine |
1. Filtered the dataset to include only COVID vaccines based on ‘therapeutic_area’ variable.
2. Excluded medicines with conditions applied in the ‘conditional_approval’ variable.
3. Sorted the dataset based on the ‘revision_number’ in descending order to get the vaccines with the most revisions.
4. Extracted and displayed the relevant columns (‘medicine_name’ and ‘revision_number’) for the vaccines.
What are the most recently released medicines (name and company) authorized for human usage for ‘Hepatitis B’?
Answering question 2 requires the use of the following variables:
Column Name | Description |
---|---|
category | The category (human or veterinary) of the medicine |
medicine_name | The brand name of the medicine |
therapeutic_area | The therapeutic area for which the medicine is authorized |
authorisation_status | The authorization status of the medicine |
company_name | The company holding the marketing authorization for the medicine |
revision_date | The date of the latest revision for the medicine |
1. Filtered the dataset to include only medicines related to ‘Hepatitis B’ in the ‘therapeutic_area’ variable.
2. Filtered the dataset to include only medicines for humans in the ‘category’ variable.
3. Sorted the dataset based on the ‘revision_date’ in descending order to get the most recently revised medicines.
4. Extracted and displayed the relevant columns (‘medicine_name’ and ‘marketing_authorisation_holder_company_name’) for the most recently revised medicines.
As our project is focused on current datasets encompassing drugs for COVID and hepatitis B, we can think of utilizing ML models for predicting future changes in drugs.
For COVID-19, we are focusing on medicine which have undergone most revisions but this doesn’t necessarily tell us about their quality or level of advancement.