Classification of pigmented lesion using novel logistic regression comparing with support vector machine algorithm for better accuracy.

Technological advances have enabled skin cancer detection studies utilising machine learning algorithms. Machine learning is best for early, curable head and neck non-melanoma skin cancer (NMSC) detection and diagnosis. Techniques and Substances: This study examined real-world machine learning disease diagnosis algorithms. This research uses Novel Logistic Regression (LR) and Support Vector Machine classification algorithms, which use training and validation sets, respectively (SVM). SVM and LR algorithms were assigned to Groups 1 and 2 based on their g-power values of 80% and current study findings using images of squamous cell carcinoma from online sources (threshold: 0.05 percent, Confidence Interval: 95 percent mean and standard deviation). This study's findings will help machine learning systems predict such illnesses. The two-tailed significance value of 0.035 (p0.05) with a 95% confidence range shows that the SVM algorithm is 81.58 percent accurate and the LR algorithm is 85.47 percent accurate. This study recommends POC skin cancer prevention and early diagnosis based on a Machine Learning analysis of the data. [ABSTRACT FROM AUTHOR]