Get ready, everyone! VIRASAT 2024 is here Now Click To Register New   NPTEL ENROLLMENT DETAILS AND LIST OF COURSES ( JULY- DEC 2024) New   NAAC REACCREDITED WITH A++ CGPA OF 3.51 New    Patna Women’s College gets remarkable ranking in MDRA – India Today Best Colleges 2023 New  Corona Crusaders College Magazine New   Alumni Association Life Membership/Contribution Form Link New   Patna Women's College is ranked at a rank band of 101 - 150 in the NIRF 2024 Ranking under College category
                 

Enter your keyword

Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy

Explore –Journal of Research

                                    Peer Reviewed Journal

     ISSN 2278–0297 (Print)

                                                                                                ISSN 2278–6414 (Online)

                Vol. XIV No. 2, 2022

© Patna Women’s College, Patna, India

                                                         https://patnawomenscollege.in/explore-journal-of-research/

Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy

•    Niraj Kumar Rai         •    Kumari Pragati

Received                                   : April 2022

Accepted                                   : May 2022

Corresponding Author   : Niraj Kumar Rai

Abstract : The term Machine Learning was invented by Arthur Samuel in 1959, an American pioneer within the field of “Computer Gaming” & “AI” and he said that “it gives computers the power to be told without being explicitly programmed.” it’s the most growing technical field, lying at the intersection of computing and statistics, and the core of computer science and data science. The adoption of data-intensive machine-learning methods will be found throughout science, technology, and commerce, resulting in more evidence-based decision-making across many walks of life, including health care, manufacturing, education, financial modeling, policing, and marketing. The power of machine learning algorithms to be told from the current context and generalized into unseen tasks would improve the protection and efficacy of radiotherapy practice, resulting in better outcomes.

Effective prediction of toxicity and testing schemes is essential to limit the side effects associated with radiotherapy (RT). In recent years, a growing interest in mechanical engineering (ML) in the scientific community

has led to the use of new tools in RT. Several researchers have shown the high efficacy of ML-based models in predicting toxicity. However, the use of these methods in clinics is still delayed, in part due to their low interpretation. Therefore, a review of modern research is needed to familiarize physicians with standard methods and techniques. Here, we present a study of ML-based models for predicting and differentiating RT-induced complications from methodological and clinical perspectives, focusing on the type of hypotheses, ML methods used, and the main results obtained. An overview of our work published research in many areas of cancer, including brain, breast, throat, gynecology, head and neck, liver, lung, and prostate cancer. The purpose is to describe the current state of the art and the key achievements within the field for both researchers and physicians.

Keywords : Introduction, machine learning, Human-Machine interaction, Radiotherapy, toxicity.

Niraj Kumar Rai

Assistant professor, Amity Institute of Information Technology,    Amity University, Patna

Email-id: nkrai@ptn.amity.edu

 

Kumari Pragati

Master of Computer Application, Amity Institute of Information Technology, Amity University, Patna

Email-id: tiwaripragati507@gmail.com