Figure 2 (A) The optimal parameter (λ) selection in the LASSO model employed 5-fold cross-validation using a minimum criteria approach. The optimal values of λ are represented by dotted vertical lines. Among these values, λ=0.0063, corresponding to an algorithm of λ equal to −3.2, was selected as the optimal choice. (B) LASSO coefficient profiles of 40 clinical features. The plot was created using a logarithmic scale for the lambda values. A vertical line was added to indicate the lambda value selected through 5-fold cross-validation. This optimal lambda value led to the identification of 7 features with non-zero coefficients. The software used for creation of the figure: Produced by Professor Zheng’s team from Zhejiang Chinese Medical University: R version 4.3.3 (2024-02-29), along with Zstats 1.0 (www.zstats.net).