Integration of Machine Learning Algorithms in Genomic Data for Accurate Cancer Diagnosis and Prognosis
Year: 2024
Type: article
Abstract: The essential driver of disease-related fatalities around the world, bosom carcinoma, is a huge issue that this study endeavors to address. Each year, nearly 900,000 people die; improved results rely upon early identification and exact finding. The challenges in separating among harmless and threatening cancers feature the need for refined methods. Utilizing AI calculations, this study recommends a PC Helped Conclusion (computer aided design) strategy that partitions patients into three gatherings: non-dangerous, no harm, and threatening. As effective classifiers, the review centers around Irregular Backwoods (RF), Backing Vector Machines (SVM), and Convolutional Brain Organizations (CNN). Intriguingly, the study even goes so far as to preprocess images from mammograms in order to increase classification accuracy. By going past customary paired classification, the exploration propels the field of disease identification by giving a more nuanced strategy to additional exact prognostic assessments and maybe bringing the passing rate related down to bosom malignant growth.
Institution: Marathwada Mitra Mandal's College of Engineering
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7217300047