An explainable machine learning model predicts pediatric varicella encephalitis.

Although the AUC showed only a modest increase from 0.977 to 0.987 (absolute increment 0.010), and the NRI of 0.0288 (95% CI: -0.0652 - 0.1229, P = 0.5478) did not reach statistical significance ( Figure 4B ), the introduction of laboratory indicators substantially improved the model’s goodness-of-fit and provided statistically significant incremental information.

also in 111,027 other papers

Machine learning models development and performance evaluation In the training set, the AUC of each model exhibited an increasing trend with the expansion of the sample size, among which SVM, XGBoost, and Random Forest demonstrated stable performance, consistently maintaining high levels ( Supplementary Figure 1 ).

also in 63,971 other papers