Hydronephrosis and Pyeloplasty

Article DOIhttps://doi.org/10.1007/s00345-021-03879-z
ObjectiveTo predict risk of and time-to re-intervention after pyeloplasty
AI ApproachLogistic Lasso
Data Source(s)Institutional series (543 patients)
Model Input43 clinical factors, most importantly: anteroposterior diameter on ultrasound
Model OutcomeRisk of re-intervention, Time to re-intervention
Model MetricsAUROC = 0.86, c-index 0.78
Model UsabilityNA
AI = Artificial Intelligence, AUROC = Area-under-the-receiver-operator-characteristic, C-index = Concordance index

Leave a comment