Deep learning, Artificial Intelligence and machine learning in cancer: Prognosis, diagnosis and treatment
1 Temitope Oluwatosin Fatunmbi, Hustle, Victoria Island, Lagos, Nigeria.
2 Andrew Ricardo Piastri, Rhoda, Colorado Springs, Colorado, Nigeria.
3 Frederick Adrah, Unilever, London, London, United Kingdom.
Review Article
World Journal of Advanced Research and Reviews, 2022, 15(02), 725–739
Publication history:
Received on 14 July 2022; revised on 21 August 2022; accepted on 24 August 2022
Abstract:
Thus, over the past years, the progress in AI, especially in machine learning and deep learning, has affected the area of oncology. It is in this context that this paper reviews the different changes in technologies for cancer prognosis, diagnosis, and treatment. Some of the ways that AI is helping improve cancer diagnosis and treatment are in the analysis of large clinical and genetic data to provide better forecast accuracy of cancer outcomes, the detailed image analysis to aid early cancer diagnosis, and the use of population, patient, and clinical data to create a custom-made treatment plan. For instance, ML performs well in prognostic evaluations where the algorithm tries to predict diseases’ progress and patients’ survival since it can recognize specific patterns in large databases; on the other hand, DL, particularly CNNs, are precise in interpreting medical images for early diagnosis. Also, AI assists in the application of enhanced therapies for genetic mutations as a form of precision medicine. During treatment strategy development, AI supports oncologists in determining the appropriate radiation doses and the proper combination of drugs; robotic systems increase the accuracy of operations due to AI. However, there is still information privacy and protection, algorithm and model bias, and implementation of AI applications in the context of clinical health care. These issues require special attention for the future development and adoption of AI in oncology. The present uses, advantages, and prospects of AI, ML, and DL in cancer treatment have been described in this paper, along with the focus on the capability of the interventions to transform the course of therapy and actual patient experience.
Keywords:
Artificial Intelligence; Machine Learning; Predictive Analysis; Deep Learning; Generative Adversarial Networks
Full text article in PDF:
Copyright information:
Copyright © 2022 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0