Liver Tumour Parameter Prediction Using Feature Extraction and Supervised Function

• Published in: 2023 International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI) Vol. 1; pp. 1 - 5
• Main Authors: Kumar, Ankit, Singh, Kamred Udham, Singh, Teekam, Banu, Nargis, Rathore, Yogesh Kumar, Pandey, Saroj Kumar
• Format: Conference Proceeding
• Language: English
• Published: IEEE 29.12.2023
• Subjects: classification algorithm; Decision trees; Feature extraction; LDA; Libraries; Linear discriminant analysis; Liver tumor; Machine learning; Machine learning algorithms; Prediction algorithms; Supervised function
• DOI: 10.1109/ICAIIHI57871.2023.10489663

The process of extracting features is essential to simplifying and condensing a wide variety of data dimensions while at the same time combining essential factors into a single influential parameter. In the field of medical research, predicting liver tumours represents a daunting task, which calls for the development of a more advanced detection mechanism that is focused towards achieving higher levels of identification precision. Even though experienced medical professionals can make preliminary predictions regarding liver tumours based on their clinical experience and diagnostic tools such as imaging and scans, there is still a compelling need for systematic assistance in making a final decision. This is especially true when evaluating patient symptoms. For the sake of our application, the approach of feature extraction that we have choose to use is called linear discriminant analysis (LDA). LDA displays its usefulness by being able to accommodate classification techniques with more than two classes and by exceeding logistic regression in terms of accuracy of classification. We make use of the power of supervised functions, in particular decision trees and the Naive Bayes algorithm, in order to make an accurate prediction about the existence of liver illness. These algorithms produce predictions regarding the existence of liver disease with a high degree of accuracy by using the factors discovered during LDA analysis. For the purposes of our simulation work, we make use of the flexible scikit-learn library in Python. This library offers a dependable infrastructure for the performance of machine learning activities. The part of this research under "Methodology and Implementation" digs into the specifics of our approach and outlines the actions that are required to evaluate the effectiveness of our prediction model.