Integrating Lean Healthcare and Machine Learning for Cancer Risk Prediction

The rising global threat of cancer has gained significant attention within the scientific community. The integration of Lean Healthcare principles with cutting-edge Machine Learning (ML) techniques has emerged as a promising approach to transform healthcare systems and enhance patient care. One of the most critical areas where this integration is making significant strides is in predicting the risk of developing cancer. This article explores the synergy between Lean Healthcare and ML in the context of cancer risk prediction, highlighting its potential to revolutionize early detection and personalized preventive care. Utilizing five distinct Machine Learning models, the analysis leveraged the Cancer Patients dataset, a publicly accessible resource containing 1000 patient profiles with diverse information related to the risk of cancer development in the human body. The study assessed various ML algorithms in cancer detection and also underscored the potential of Industry 4.0 technologies in improving patient outcomes. Assessment using performance metrics like accuracy, sensitivity, and F-score demonstrated AI’s potential in improving detection accuracy. The results have shown that Multilayer Perceptron (MLP), Random Forest (RF) with Principal Component Analysis (PCA), and Logistic Regression (LR) with PCA exhibit significant efficacy in cancer detection. Consequently, the integration of supervised machine learning methods is poised to offer substantial assistance in the early diagnosis and prognosis of cancer.