Analysis of Utility Kernal Based SVM for survival Estimation of Breast Cancer

  • Unique Paper ID: 167837
  • Volume: 11
  • Issue: 4
  • PageNo: 477-482
  • Abstract:
  • The advancement of medical research in cancer prognosis and diagnosis, particularly in breast cancer, has placed significant stress on oncologists due to the complexity and heterogeneity of the disease. To address this challenge, research focusing on breast cancer survival estimation has been proposed. This research aims to merge histological and genomic data to enhance prognosis accuracy, minimizing unnecessary treatment interventions and ensuring tailored patient care. By utilizing a spectrum of machine learning approaches, including SVM, Random Forest, and neural networks, a robust tool is developed for personalized breast cancer survival predictions. The tool empowers clinicians to make informed treatment decisions and optimize healthcare resource allocation efficiently. Moreover, the application of ensemble methods further enhances prediction accuracy, particularly through techniques like Voting Classifier. Additionally, extending the project to include a user-friendly frontend using the Flask framework allows for user testing and authentication, facilitating seamless interaction and practical application in clinical settings.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 4
  • PageNo: 477-482

Analysis of Utility Kernal Based SVM for survival Estimation of Breast Cancer

Related Articles