.jpg?format=webp&width=780)
The study conducted on 18,803 prostate cancer patients found that machine learning (ML) models exhibited higher predictive accuracy for lymph node metastasis (LNM) compared to currently recommended nomograms. ML models achieved a C-index of 0.862 in the validation set, outperforming the Briganti and MSKCC nomograms with C-indices of 0.745 and 0.714, respectively. The ML models, mostly based on Logistic Regression, demonstrated a sensitivity of 0.81 and a specificity of 0.82 in the validation set.
Like
Save
Share