Fig. 4 | Scientific Reports

Fig. 4

From: Machine learning models to predict osteoporosis in patients with chronic kidney disease stage 3–5 and end-stage kidney disease

Fig. 4

Confusion matrices and predictive probabilities histograms for the ANN model on (A) the validation and (B) the test datasets. The confusion matrices on the left indicate the number of correct and incorrect classifications, where 0 represents the control group (no osteoporosis) and 1 represents the osteoporosis group. The middle panels display histograms of the predicted probabilities for the “not osteoporosis” and “osteoporosis” classes separately. The rightmost panels combine the predicted probabilities of both classes and show the overall distribution. The x-axis represents the predicted probability, and the y-axis represents the sample count, reflecting the confidence of the model in its predictions.

Back to article page