Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 02022 | |
Number of page(s) | 9 | |
Section | Machine Learning in Healthcare and Finance | |
DOI | https://doi.org/10.1051/itmconf/20257002022 | |
Published online | 23 January 2025 |
Enhancing Medical Diagnostics with Machine Learning: A Study on Ensemble Methods and Transfer Learning
Department of Statistic Science, University College London, WC1E 6BT London, UK
Corresponding author: zcakj01@ucl.ac.uk
This paper explores the use of machine learning (ML) in medicine, emphasizing how important it is to enhance patient outcomes and diagnostic precision. As medical data grows in complexity and volume, advanced ML techniques are increasingly necessary. The research focuses on leveraging Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Ensemble Methods, and Transfer Learning to enhance medical diagnostics. Specifically, these techniques are applied to large-scale datasets, to address tasks like disease detection, patient outcome prediction, and managing uncertainty in medical data. According to the study, CNNs performs substantially better when handling uncertainty when using the U-Multiclass technique, as seen by the largest Area Under the Curve (AUC) for Cardiomegaly detection. When it comes to diabetes prediction, Ensemble Methods outperform other approaches, and Transfer Learning works well for modifying trained models for use in novel medical applications. The research holds practical value since it can improve patient care and productivity within the healthcare industry. By integrating these ML techniques, the study contributes valuable insights into improving diagnostic processes and optimizing patient outcomes.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.