Degree
Master of Science in Computer Science
Department
Department of Computer Science
School
School of Mathematics and Computer Science (SMCS)
Date of Submission
Spring 2024
Supervisor
Dr. Sajjad Haider, Professor, Department of Computer Science, Institute of Business Administration, Karachi
Keywords
Disease Extraction, Time series analysis, Machine learning, Disease trends, ARIMA, RNN, LSTM, Hospital Management
Abstract
This project employs medical NER (named entity recognition) and time series analysis on clinical notes, aiming to enhance public health monitoring services. It performs a comparative analysis of three time series models, namely, Autoregressive Integrated Moving Average (ARIMA), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM), to analyze disease trends extracted from clinical notes using medical NER. For this purpose, the "en_ner_bc5cdr_md" Spacy model trained on the BC5CDR disease dataset was utilized. The Mean Squared Error (MSE) metric was used to evaluate the performance of ARIMA, RNN, and LSTM models. The comparative analysis highlights the strengths and limitations of each model in the context of disease trend analysis within clinical records. The findings are expected to significantly contribute to data-driven healthcare decision-making. The applications of this research are manifold, ranging from early disease detection to informed resource allocation and healthcare policy formulation. Ultimately, the goal is to enhance patient care and improve the overall quality of healthcare delivery, demonstrating the potential of advanced analytical techniques in the medical domain.
Document Type
Restricted Access
Submission Type
Research Project
Recommended Citation
Abid, Muhammad Affan. "Analyzing disease trends in clinical records: A comparitive study of ARIMA, AUTOARIMA, RNN and LSTM time series models on extracted medical entities." Unpublished graduate research project. Institute of Business Administration. 2024. https://ir.iba.edu.pk/research-projects-mscs/51
MSCS End Semester Progress Rreport
25355-ms-project-demo-video.mp4 (42174 kB)
MSCS Project Demo Video
25355_masters_project_poster.pdf (821 kB)
MSCS Project Poster
The full text of this document is only accessible to authorized users.
