Machine Learning Methods in Medical Diagnosis
- DOI
- 10.2991/978-94-6463-598-0_53How to use a DOI?
- Keywords
- “machine learning”; “Medical Diagnosis”; “Artificial Neural Networks (ANNs)”; “Decision Tree and Bayesian Classifier (BC)”
- Abstract
Incorrect diagnosis can significantly affect outcome of treatment of a patients, which is often caused by cognitive bias of clinicians. This paper summarises development of three common machine learning methods in medical diagnosis -- Artificial Neural Networks (ANNs), Decision Tree and Bayesian Classifier (BC). Development of novel molecular approach can improve the ability of ANN models to accurately classify cancer subtypes such as Small Round Blue Cell Tumors (SRBCTs). Moreover, new medical equipment such as mass spectrometry can assist ANNs model in analysis of ovarian cancer. In order to achieve higher accuracy of Decision Tree in medical diagnosis, Shouman et al. examined different combination of discretization methods and Decision Tree and found that disequal frequency discretization Gain Ratio Decision Tree achieved highest accuracy. In addition, BC is more interpretable than other two classifier models because it can produce probabilistic outputs of the likelihood of a certain diagnosis or outcome.
- Copyright
- © 2024 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Nianci You PY - 2024 DA - 2024/12/19 TI - Machine Learning Methods in Medical Diagnosis BT - Proceedings of the 2024 3rd International Conference on Public Service, Economic Management and Sustainable Development (PESD 2024) PB - Atlantis Press SP - 513 EP - 519 SN - 2352-5428 UR - https://doi.org/10.2991/978-94-6463-598-0_53 DO - 10.2991/978-94-6463-598-0_53 ID - You2024 ER -