Bladder compliance, Voiding Dysfunction.
| Article DOI | https://doi.org/10.1016/j.compbiomed.2021.105173 |
| Objective | To classify and predict bladder compliance from a novel method that measures intravesical pressure during the VCUG examination without extra UDS. |
| AI Approach | SVM, RF, Logistic Regression, Perceptron, XGBoost, and Naive Bayes |
| Data Source(s) | Single institutional series (52 patients) |
| Model Input | Time-domain and wavelet features extracted from the bladder pressure measurement, sex, max pressure of bladder before urination, max perfusion |
| Model Outcome | Abnormal bladder compliance |
| Model Metrics | SVM: AUC 0.87, Sensitivity 70.4%, Specificity 84.5%, Accuracy 79.1% |
| Model Usability | NA |
AI = Artificial intelligence, SVM = Support vector machines, RF = Random Forrest, AUC = Area under the receiver operator characteristic
AIPEDURO 
Leave a comment