The MBD Check algorithm is a validated diagnostic instrument to support referral decisions in patients with suspected mild bleeding disorder before surgery. A proposed clinical algorithm is available here

The MBD Check algorithm is a support vector machine (radial kernel). Missing values can be imputed.

The algorithm was derived and intensively validated in two prospective crossectional studies (n=772). Expert opinion based on extensive laboratory workup served as the reference standard.

The performance of the algorithm was tested in an external validation dataset. The area under the ROC-curve was 0.86 (95% CI: 0.81, 0.90). In the external validation cohort, 87.5% of patients with MBD were correctly identified (sensitivity; 95% confidence interval [CI], 79.9–93.0), while 54.3% of patients without MBD were correctly excluded from further work-up (specificity; 95% CI, 44.3–64.0).

The MBD Check screening algorithm was validated in Swiss patients from a cohort that was referred to a hematology outpatient unit for a suspected mild bleeding disorder. Diagnostic accuracy might change when used in other populations (e.g. unselected patients scheduled for surgery).

The MBD Check algorithm is a non-commercial research tool that has been developed by the PCD research group at Inselspital, University Hospital, and the University of Bern. Scientific societies do not yet support the application of the tool. The algorithm has not been registered as a medical device with the European Medicines Agency (EMA), and it is not CE marked. The application of the algorithm does not replace the standard diagnostic workup in patients with suspected MBD. No patient data is stored with this web-based tool.

RESULTS



This plot shows how the different predictors influenced the model`s prediction of the likelihood of a mild bleeding disorder. The SHapley Additive exPlanations (SHAP) values were used to show the importance of each predictor. SHAP scores quantify how much each feature contributes to a particular prediction, ensuring that the contributions are fairly distributed across the features. Positive SHAP values (red) indicate that a feature increases the predicted likelihood of MBD, and negative SHAP values (blue) indicate that a feature decreases the predicted likelihood of MBD. SHAP values should be interpreted relatively to identify the most influential predictors.