Pancreatic cancer’s aggressive nature has driven the exploration of advanced machine learning techniques. Nevertheless, the difficulty arises from the fact that pancreatic ductal adenocarcinoma (PDAC) lesions identified through biopsies often occur at advanced stages, which impedes early detection initiatives. In response to this limitation, the integration of innovative and validated urinary biomarkers emerges as a solution, addressing the shortcomings associated with traditional biopsy methods. These urinary biomarkers prove instrumental in overcoming the delay in detection commonly associated with PDAC lesions, presenting a promising avenue for early diagnosis and improved patient outcomes. This study introduces an innovative two-stage machine learning pipeline for pancreatic cancer diagnosis, utilizing urinary biomarkers. The initial binary classification differentiates pancreatic ductal adenocarcinoma (PDAC) from a cohort comprising benign hepatobiliary disease and control cases, incorporating robust data preprocessing, and addressing class imbalance. The subsequent fine-grained classification within the PDAC group categorizes cases into grades I–IV, employing a Support Vector Machine (SVM) classifier optimized through grid search. The approach achieves outstanding accuracy, with the best SVM hyperparameters yielding 99.7% accuracy in validation and testing sets. This method advances early detection and precise classification of pancreatic cancer, with ongoing research comparing other methods for comprehensive assessment.
Machine Learning Pipeline for Multi-grade Classification in Pancreatic Cancer Detection Using Urinary Biomarkers
Smart Innovation, Systems and Technologies
Congress on Control, Robotics, and Mechatronics ; 2024 ; Warangal, India February 03, 2024 - February 04, 2024
Proceedings of the Second Congress on Control, Robotics, and Mechatronics ; Kapitel : 11 ; 143-156
14.11.2024
14 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
A Machine Learning Approach for Running Grade Classification Using IMUs Data
Springer Verlag | 2024
|Blood Cancer Detection using Machine Learning
IEEE | 2021
|