HEALTHCARE  ANALYTICS

Optimizing Patient Care and Operational Efficiency

In this personal project, I leveraged Python's Pandas library for a comprehensive analysis of a hospital appointment dataset.
 
The initial data preprocessing involved addressing issues such as duplicates, null values, column naming inconsistencies, conversion of date columns to datetime format and qualitative values into binary values. 
Subsequently, I conducted data analysis through complex SQL queries executed in a Jupyter Notebook extension, focusing on a MySQL database.
 
The queries delved into various temporal aspects:

• appointment scheduling

• daily, weekly, and monthly trends

• average lead time.

• busiest week

• busiest month

• gender based analysis

• return rate of patients

• average lead time for missed appointments 

• peak appointment times for different age groups

• average number of appointments per patient

 
This analysis provided actionable insights that can be crucial for optimizing resource allocation and refining patient engagement strategies.