NORMA eResearch @NCI Library

A Content Based Recommender System for Medicine using Machine Learning Algorithm

Mathur, Utkarsh (2022) A Content Based Recommender System for Medicine using Machine Learning Algorithm. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Background: With the introduction of covid-19 virus and diseases it spreads in such a minimal period, Doctors around the world has to be more prepared with technology and the ability to take an effective decision in terms of proposing medicines or treatment of illnesses should be empowered. As e-commerce grows in the medical industry, more and more healthcare products are being sold online. Involved stakeholders in the study can include healthcare facilities such as hospitals and clinics, as well as online retailers of OTC (Over-the-Counter) medications and other non-profit organizations with extensive patient records. The above-mentioned stakeholders may benefit from making treatment decisions based on prior patients with comparable symptoms who used a Machine Learning recommender model based on patient history.

Objective: When it comes to creating a recommendation system for prescribing drugs, this research will focus on Machine learning models, as well as examining various metrics to determine whether Content Based Recommender system approaches may be utilized to build an Drug Recommendation Model. The CSV file is obtained from the UCI Machine Learning repository, which provides the reviews and ratings of different users over the same medications. This dataset doesn’t involve any personal information and its available on open source platform so no breach of personal information has happened and consecutively ethics form submission not required. This investigation will thus empower patients / stakeholders to take better informed decision and initiate proper medication themselves without the intervention of physician. It may be determined which recommender system outperforms others using the evaluation scores.

Results: After using various metrices for similarity calculation, the model was build upon cosine similarity with an average score of 0.098. The drug recommendation model deployed on cloud also shows that 4 out 5 recommendations are correct. Hence, 90percent accuracy is achieved for this recommender model.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
R Medicine > RS Pharmacy and materia medica
R Medicine > Healthcare Industry
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 22 Feb 2023 17:59
Last Modified: 02 Mar 2023 09:25

Actions (login required)

View Item View Item