Fig. 2: Performance comparison of machine learning models across four feature sets. | npj Digital Medicine

Fig. 2: Performance comparison of machine learning models across four feature sets.

From: Streamlined machine learning model for early sepsis risk prediction in burn patients

Fig. 2: Performance comparison of machine learning models across four feature sets.The alternative text for this image may have been generated using AI.

Receiver Operating Characteristic (ROC) curves (top row; a–d) and Precision–Recall (PR) curves (bottom row; e–h) are shown for Random Forest, Logistic Regression, XGBoost, and LightGBM. Each column represents one feature set: EDA (a, e), High Frequency (b, f), Intersection (c, g), and Minimalistic (d, h). Legends indicate the area under the ROC curve (AUC) and the average precision (AP) with 95% confidence intervals. Random Forest and Logistic Regression consistently achieved the highest performance across all feature sets.

Back to article page