Fig. 5: Validation of the AI model applied to EV profiling after MSP-capturing. | Communications Medicine

Fig. 5: Validation of the AI model applied to EV profiling after MSP-capturing.

From: Machine learning-assisted assessment of extracellular vesicles can monitor cellular rejection after heart transplant

Fig. 5

The AI model was tested on a an independent cohort of patients (n = 5) followed up to 357 days (57 samples), and b a separate cohort of subjects with a diagnosis of antibody-mediated rejection (AMR; n = 13). Diagnostic performance (sensitivity, specificity, accuracy, positive and negative predictive value) are reported together with ROC curve analysis (area under the curve, AUC, with 95% confidence interval) and P value for the comparison with referral line. Source data and statistics are reported in Tables S14 and S15.

Back to article page