Skip to main content


Fig. 3 | BMC Medical Informatics and Decision Making

Fig. 3

From: Using artificial intelligence to reduce diagnostic workload without compromising detection of urinary tract infections

Fig. 3

ROC curve for supervised machine learning models trained using the list of optimal features, in comparison to a Logistic Regression classifier trained solely using WBC count and bacterial count. Random Forest (class weight 1:20), AUC = 0·909; Neural Network (resample 1:2), AUC = 0·905; XGBoost (class weight 1:20), AUC = 0·910; Logistic Regression, AUC = 0·882. The red point indicates the performance of a heuristic model based on 30 WBC/μl and 100 bacteria/μl

Back to article page