Big Data Analytics Using Python Based Machine Learning: A Challenging Opportunity in Hospital Pharmacy

Background:

In this study, we introduce the use of Python 3 as an effective tool to hold and analyse Big Data in Healthcare. The aim of this study is to explore how big data may be utilized to support a better hospital pharmacy service, provide potential benefits, and describe the potential future use. Furthermore, population description and pattern are to be explored.

Methods:

We open Jupyter Notebook and then choose Python 3 to run the code. We used the Hospital Pharmacy Management System (PMS) Query Template System to extract data from 01 April 2019 to 31 March 2020. We used Python 3 to hold and analyse all the .CSV dataset.

Results:

The total number of dispensing records retrieved was 1,765,910. 127,337 patients paid 358,802 visits to our pharmacy with 381,060 prescriptions handled. For the 127,337 individual patients, 57% fall into 60-100 while 21% are from 80-100. 43% of the prescriptions had 1 or 2 items. 48,000 patients visited our medical clinic, 47,000 patients visited the family clinic, and 36,000 patients visited the psychiatric clinic during the data collection period.

Conclusions:

In this study, we demonstrate how data analytics could assist in decision making in healthcare. The analytics helps time-strapped pharmacist to monitor patient data easily in real-time and thus enable them to invest more time in better patient care. The huge volume of raw data we obtain during this research is organised to create insights into the behaviour of our patient populations, prescription type, prescribing pattern, services, and workflows.