Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bukhari, Hassaan A., Abbaraju, Vikram, Patel, Jay, Clarkson, Becky, Tyagi, Shachi, Damaser, Margot S., Majerus, Steve J. A.
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.21878
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911703602561024
author Bukhari, Hassaan A.
Abbaraju, Vikram
Patel, Jay
Clarkson, Becky
Tyagi, Shachi
Damaser, Margot S.
Majerus, Steve J. A.
author_facet Bukhari, Hassaan A.
Abbaraju, Vikram
Patel, Jay
Clarkson, Becky
Tyagi, Shachi
Damaser, Margot S.
Majerus, Steve J. A.
contents Objective: Conventional urodynamics (UDS) provide critical diagnostic information, but requires invasive dual catheterization and manual labeling of clinically important events. Wireless, catheter-free bladder function tests are becoming available for home use, but only provide vesical pressure (Pves). We developed a machine learning framework that was trained and externally validated on UDS data for automated urological event classification from single-channel (Pves) recordings. Methods: We analyzed 118 annotated UDS traces segmented into 0.8-second Pves intervals. Using the discrete wavelet transform, we extracted 55 statistical features per segment. Consecutive segments (233,338 segments; three classes) sharing the same class, abdominal (ABD), detrusor overactivity (DO), or voiding contraction (VOID), were grouped into events, and median feature aggregation was applied to derive event-level representations. Using an imbalanced dataset, we trained a two-stage multilayer perceptron (MLP): Stage 1 distinguished VOID vs non-VOID, and Stage 2 classified non-VOID into ABD and DO. The model was trained on two independent datasets and externally validated on a third independent dataset. Additional cross-dataset training-validation permutations were performed to assess generalizability. Performance was evaluated using accuracy, F1-macro, sensitivity, specificity, and area under the curve (AUC). Results: Stage 1 (VOID vs. non-VOID) achieved 84% accuracy (balanced accuracy 76%), F1-macro 0.74, and AUC 0.85, while Stage 2 (ABD vs. DO) reached 90% accuracy (balanced accuracy 80%), F1-macro 0.80, and AUC 0.87. Permutation feature importance indicated that most features contributed meaningfully. Conclusion: Our machine learning approach enables accurate automated detection of urological events from Pves, demonstrating feasibility for single-channel monitoring and future ambulatory applications.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21878
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Automated Detection of Urological Events in Bladder Pressure Signals with a Two-Stage Machine Learning Framework Validated on External Datasets
Bukhari, Hassaan A.
Abbaraju, Vikram
Patel, Jay
Clarkson, Becky
Tyagi, Shachi
Damaser, Margot S.
Majerus, Steve J. A.
Signal Processing
Objective: Conventional urodynamics (UDS) provide critical diagnostic information, but requires invasive dual catheterization and manual labeling of clinically important events. Wireless, catheter-free bladder function tests are becoming available for home use, but only provide vesical pressure (Pves). We developed a machine learning framework that was trained and externally validated on UDS data for automated urological event classification from single-channel (Pves) recordings. Methods: We analyzed 118 annotated UDS traces segmented into 0.8-second Pves intervals. Using the discrete wavelet transform, we extracted 55 statistical features per segment. Consecutive segments (233,338 segments; three classes) sharing the same class, abdominal (ABD), detrusor overactivity (DO), or voiding contraction (VOID), were grouped into events, and median feature aggregation was applied to derive event-level representations. Using an imbalanced dataset, we trained a two-stage multilayer perceptron (MLP): Stage 1 distinguished VOID vs non-VOID, and Stage 2 classified non-VOID into ABD and DO. The model was trained on two independent datasets and externally validated on a third independent dataset. Additional cross-dataset training-validation permutations were performed to assess generalizability. Performance was evaluated using accuracy, F1-macro, sensitivity, specificity, and area under the curve (AUC). Results: Stage 1 (VOID vs. non-VOID) achieved 84% accuracy (balanced accuracy 76%), F1-macro 0.74, and AUC 0.85, while Stage 2 (ABD vs. DO) reached 90% accuracy (balanced accuracy 80%), F1-macro 0.80, and AUC 0.87. Permutation feature importance indicated that most features contributed meaningfully. Conclusion: Our machine learning approach enables accurate automated detection of urological events from Pves, demonstrating feasibility for single-channel monitoring and future ambulatory applications.
title Automated Detection of Urological Events in Bladder Pressure Signals with a Two-Stage Machine Learning Framework Validated on External Datasets
topic Signal Processing
url https://arxiv.org/abs/2605.21878