pith. sign in

arxiv: 2605.21878 · v1 · pith:CQFMFTWNnew · submitted 2026-05-21 · 📡 eess.SP

Automated Detection of Urological Events in Bladder Pressure Signals with a Two-Stage Machine Learning Framework Validated on External Datasets

Hassaan A. Bukhari , Vikram Abbaraju , Jay Patel , Becky Clarkson , Shachi Tyagi , Margot S. Damaser , Steve J. A. Majerus This is my paper

Pith reviewed 2026-05-22 04:40 UTC · model grok-4.3

classification 📡 eess.SP
keywords machine learningurodynamicsbladder pressureevent detectiondetrusor overactivityvoiding contractionsingle-channel monitoringexternal validation
0
0 comments X

The pith

A two-stage machine learning model classifies voiding, abdominal, and detrusor events from single-channel bladder pressure at 84-90 percent accuracy on external data.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops a machine learning framework to automatically detect urological events such as voiding contractions, abdominal pressure artifacts, and detrusor overactivity using only single-channel vesical pressure recordings. Signals are segmented into 0.8-second intervals, features are extracted via discrete wavelet transform, and a two-stage multilayer perceptron is trained to first separate voiding from non-voiding then classify the rest, with median aggregation applied at the event level. The model was trained on two independent datasets and validated on a third, achieving 84 percent accuracy and 0.85 AUC in the first stage and 90 percent accuracy and 0.87 AUC in the second. This matters because it could support simpler wireless monitoring without dual catheters or manual labeling for future home-use bladder tests.

Core claim

The paper claims that a two-stage multilayer perceptron trained on 55 statistical features from the discrete wavelet transform of 0.8-second Pves segments, after grouping consecutive same-class segments and applying median feature aggregation, can distinguish VOID versus non-VOID events and then ABD versus DO events with 84 percent accuracy (balanced 76 percent, F1-macro 0.74, AUC 0.85) and 90 percent accuracy (balanced 80 percent, F1-macro 0.80, AUC 0.87) respectively on an external independent dataset after training on two other independent datasets.

What carries the argument

Two-stage multilayer perceptron that first separates voiding contractions from non-voiding segments and then distinguishes abdominal pressure from detrusor overactivity within non-voiding segments, using median-aggregated statistical features from the discrete wavelet transform of 0.8-second Pves intervals.

If this is right

  • The approach reduces the need for invasive dual catheterization and manual event labeling in conventional urodynamic studies.
  • It demonstrates feasibility for automated classification in single-channel wireless bladder pressure monitoring suitable for ambulatory or home settings.
  • Cross-dataset training and external validation support the generalizability of the wavelet-feature and median-aggregation pipeline across independent patient groups.
  • Permutation feature importance analysis shows that the majority of the 55 extracted features contribute meaningfully to classification decisions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The segmentation and two-stage design could be adapted for real-time processing on wearable single-channel sensors to enable continuous home monitoring of bladder function.
  • Similar staged classification with median aggregation might transfer to event detection tasks in other single-channel physiological signals that suffer from class imbalance.
  • Strong performance on external datasets suggests the framework could serve as a template for medical time-series models where ground truth must be established from richer reference recordings.

Load-bearing premise

Manual annotations on the original dual-channel UDS traces provide reliable ground-truth labels that transfer directly to single-channel Pves segments after 0.8-second segmentation and median aggregation.

What would settle it

Apply the trained model to newly recorded single-channel Pves data whose events are labeled by experts using only that single channel (no dual-channel reference) and observe accuracy falling well below the reported 84 percent and 90 percent levels.

read the original abstract

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.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript presents a two-stage multilayer perceptron framework for automated classification of urological events (VOID, ABD, DO) from single-channel vesical pressure (Pves) signals. UDS traces (118 total) are segmented into 0.8 s Pves intervals; 55 wavelet-derived statistical features are extracted per segment, consecutive same-class segments are grouped into events, and median aggregation yields event-level representations. Stage 1 separates VOID from non-VOID; Stage 2 distinguishes ABD from DO. The model is trained on two independent datasets and externally validated on a third, with additional cross-dataset permutations; performance metrics include accuracy, balanced accuracy, F1-macro, and AUC.

Significance. If the central results hold under single-channel conditions, the work would support automated event detection for future catheter-free ambulatory bladder monitoring, reducing reliance on invasive dual-channel UDS. External validation on a third independent dataset and cross-permutation experiments strengthen the generalizability assessment. Wavelet feature extraction combined with permutation importance analysis provides a concrete, interpretable pipeline. The significance is reduced, however, by the dependence on labels derived from dual-channel annotations.

major comments (2)
  1. [Methods] Methods section: Ground-truth labels for ABD versus DO are assigned on full dual-channel UDS traces by using Pabd to differentiate abdominal pressure rises from detrusor contractions. After 0.8 s segmentation and median aggregation performed exclusively on Pves, Stage 2 is required to recover those same labels from Pves-derived features alone. This creates a risk that the learned decision boundary encodes information unavailable in true single-channel ambulatory recordings, which could inflate the reported external-validation metrics (90 % accuracy, balanced accuracy 80 %, AUC 0.87).
  2. [Results] Results section: Exact per-class event counts and total segment numbers in the external validation set are not reported, nor are details of hyperparameter search, class-imbalance weighting, or potential label noise in the source UDS annotations. Without these quantities it is difficult to judge whether the balanced-accuracy figures (76 % and 80 %) and F1-macro scores reflect robust performance or are driven by dataset composition.
minor comments (2)
  1. [Abstract] Abstract: The phrase 'three classes' is introduced without an explicit statement of the class distribution or total event count, which would help readers contextualize the reported metrics.
  2. The manuscript would benefit from a brief discussion of how the 0.8 s segmentation window and median aggregation were chosen, including any sensitivity analysis to these preprocessing choices.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and detailed comments, which have prompted us to clarify key aspects of our methodology and results. We address each major comment point by point below and outline the corresponding revisions.

read point-by-point responses

  1. Referee: [Methods] Methods section: Ground-truth labels for ABD versus DO are assigned on full dual-channel UDS traces by using Pabd to differentiate abdominal pressure rises from detrusor contractions. After 0.8 s segmentation and median aggregation performed exclusively on Pves, Stage 2 is required to recover those same labels from Pves-derived features alone. This creates a risk that the learned decision boundary encodes information unavailable in true single-channel ambulatory recordings, which could inflate the reported external-validation metrics (90 % accuracy, balanced accuracy 80 %, AUC 0.87).

    Authors: We appreciate the referee's concern regarding the derivation of ground-truth labels. The ABD versus DO distinction is indeed established using dual-channel UDS annotations (Pabd to identify abdominal pressure rises), which represents the clinical gold standard for labeling these events. Our framework then trains exclusively on Pves-derived wavelet features to predict these labels, directly simulating the information available in single-channel catheter-free recordings. The wavelet statistical features are selected to encode temporal-frequency patterns in Pves that differ systematically between detrusor contractions and abdominal events. While we acknowledge that this supervised setup cannot fully eliminate the possibility of the model leveraging subtle Pves signatures that correlate with the dual-channel labels, the external validation across independent datasets and the permutation importance analysis support that the learned boundaries are driven by Pves characteristics. In the revised manuscript we will add an explicit limitations subsection in the Discussion that discusses this annotation dependency and its implications for translating to purely ambulatory single-channel use. revision: partial

  2. Referee: [Results] Results section: Exact per-class event counts and total segment numbers in the external validation set are not reported, nor are details of hyperparameter search, class-imbalance weighting, or potential label noise in the source UDS annotations. Without these quantities it is difficult to judge whether the balanced-accuracy figures (76 % and 80 %) and F1-macro scores reflect robust performance or are driven by dataset composition.

    Authors: We agree that these quantitative details are required for proper interpretation of the reported metrics. The revised manuscript will include a new table (or expanded supplementary material) reporting the exact number of segments and aggregated events per class for the external validation dataset as well as for the training sets. The Methods section will be expanded to describe the hyperparameter search procedure (grid search over hidden-layer sizes, learning rates, and regularization strengths with 5-fold cross-validation), the class-imbalance strategy (weighted cross-entropy loss with inverse class-frequency weights), and our assessment of label quality (manual review of a random subset of UDS annotations for consistency). These additions will enable readers to evaluate whether the balanced accuracy and F1-macro values are influenced by dataset composition. revision: yes

Circularity Check

0 steps flagged

No circularity in empirical ML pipeline with external validation

full rationale

The paper reports an empirical two-stage MLP classifier trained on wavelet features from segmented single-channel Pves traces, with performance measured via accuracy, F1, and AUC on a fully independent external dataset after cross-dataset permutations. No mathematical derivations, equations, fitted parameters renamed as predictions, or self-citations appear in the load-bearing chain; the central claims rest on standard supervised learning evaluated against held-out labels rather than any reduction to inputs by construction.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The approach depends on the domain assumption that wavelet-derived statistical features from short segments remain discriminative after median aggregation across clinical events, plus standard ML choices for architecture and training; no new physical entities or ad-hoc constants are introduced.

free parameters (1)
  • MLP hidden-layer sizes and training hyperparameters
    Chosen to optimize performance on the imbalanced training sets; exact values not stated in abstract.
axioms (1)
  • domain assumption Discrete wavelet transform features extracted from 0.8-second Pves segments capture the distinguishing time-frequency characteristics of ABD, DO, and VOID events.
    Invoked when generating the 55 statistical features per segment prior to event grouping.

pith-pipeline@v0.9.0 · 5921 in / 1454 out tokens · 56771 ms · 2026-05-22T04:40:50.936885+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

51 extracted references · 51 canonical work pages

  1. [1]

    Incidence of Lower Urinary Tract Symptoms in a Population-Based Study of Men and Women,

    N. N. Maserejianet al., “Incidence of Lower Urinary Tract Symptoms in a Population-Based Study of Men and Women,”Urology, vol. 82, no. 3, pp. 560–564, Sep. 2013

    work page 2013

  2. [2]

    The standardisation of terminology of lower uri- nary tract function: report from the Standardisation Sub-committee of the International Continence Society,

    P. Abramset al., “The standardisation of terminology of lower uri- nary tract function: report from the Standardisation Sub-committee of the International Continence Society,”Neurourology and Urodynamics, vol. 21, no. 2, pp. 167–178, 2002

    work page 2002

  3. [3]

    Worldwide prevalence estimates of lower urinary tract symptoms, overactive bladder, urinary incontinence and bladder outlet obstruction,

    D. E. Irwinet al., “Worldwide prevalence estimates of lower urinary tract symptoms, overactive bladder, urinary incontinence and bladder outlet obstruction,”BJU international, vol. 108, no. 7, pp. 1132–1138, Oct. 2011

    work page 2011

  4. [4]

    Prevalence, Burden, and Treatment of Lower Urinary Tract Symptoms in Men Aged 50 and Older: A Sys- tematic Review of the Literature,

    A. Y . Zhang and X. Xu, “Prevalence, Burden, and Treatment of Lower Urinary Tract Symptoms in Men Aged 50 and Older: A Sys- tematic Review of the Literature,”SAGE Open Nursing, vol. 4, p. 2377960818811773, Dec. 2018

    work page 2018

  5. [5]

    Fundamentals of urodynamic practice, based on International Continence Society good urodynamic practices recommen- dations,

    M. J. Drakeet al., “Fundamentals of urodynamic practice, based on International Continence Society good urodynamic practices recommen- dations,”Neurourology and Urodynamics, vol. 37, no. S6, pp. S50–S60, 2018

    work page 2018

  6. [6]

    V . W. Nitti,Practical Urodynamics. W.B. Saunders, 1998

    work page 1998

  7. [7]

    Artifacts in Urodynamic Studies: A Narrative Review,

    F. Pourghaziet al., “Artifacts in Urodynamic Studies: A Narrative Review,”Neurourology and Urodynamics, vol. 44, no. 8, pp. 1583–1592, Nov. 2025

    work page 2025

  8. [8]

    Anxiety, distress, and pain in pediatric urody- namics,

    J. B. Finkelsteinet al., “Anxiety, distress, and pain in pediatric urody- namics,”Neurourology and Urodynamics, vol. 39, no. 4, pp. 1178–1184, Apr. 2020

    work page 2020

  9. [9]

    Intraurethral lidocaine use during urodynamics in female patients: A systematic review and meta-analysis,

    D. P. Oktavianiet al., “Intraurethral lidocaine use during urodynamics in female patients: A systematic review and meta-analysis,”Turkish Journal of Urology, vol. 47, no. 5, pp. 366–374, Sep. 2021. 12 ENGINEERING APPLICA TIONS OF ARTIFICIAL INTELLIGENCE

    work page 2021

  10. [10]

    Catheter-Free Urodynamics Testing: Current Insights and Clinical Potential,

    B. V ogt, “Catheter-Free Urodynamics Testing: Current Insights and Clinical Potential,”Research and Reports in Urology, vol. 16, pp. 1– 17, 2024

    work page 2024

  11. [11]

    Real-Time Classification of Bladder Events for Effective Diagnosis and Treatment of Urinary Incontinence,

    R. Karamet al., “Real-Time Classification of Bladder Events for Effective Diagnosis and Treatment of Urinary Incontinence,”IEEE transactions on bio-medical engineering, vol. 63, no. 4, pp. 721–729, Apr. 2016

    work page 2016

  12. [12]

    Feasibility of Real-Time Conditional Sacral Neuro- modulation Using Wireless Bladder Pressure Sensor,

    S. J. Majeruset al., “Feasibility of Real-Time Conditional Sacral Neuro- modulation Using Wireless Bladder Pressure Sensor,”IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society, vol. 29, pp. 2067– 2075, 2021

    work page 2067

  13. [13]

    Ambulatory urodynamic monitoring: state of the art and future directions,

    B. Abelsonet al., “Ambulatory urodynamic monitoring: state of the art and future directions,”Nature Reviews. Urology, vol. 16, no. 5, pp. 291–301, May 2019

    work page 2019

  14. [14]

    The AUA/SUFU Guideline on Adult Neurogenic Lower Urinary Tract Dysfunction: Diagnosis and Evaluation,

    D. A. Ginsberget al., “The AUA/SUFU Guideline on Adult Neurogenic Lower Urinary Tract Dysfunction: Diagnosis and Evaluation,”The Journal of Urology, vol. 206, no. 5, pp. 1097–1105, Nov. 2021

    work page 2021

  15. [15]

    First in Human Subjects Testing of the UroMonitor: A Catheter-free Wireless Ambulatory Bladder Pressure Monitor,

    B. T. Fraineyet al., “First in Human Subjects Testing of the UroMonitor: A Catheter-free Wireless Ambulatory Bladder Pressure Monitor,”The Journal of Urology, vol. 210, no. 1, pp. 186–195, Jul. 2023

    work page 2023

  16. [16]

    Validation of a Wireless Catheter-Free Ambulatory Urodynamics Device in Women With Neurogenic Bladder,

    M. D. Grosset al., “Validation of a Wireless Catheter-Free Ambulatory Urodynamics Device in Women With Neurogenic Bladder,”Neurourol- ogy and Urodynamics, vol. 45, no. 1, pp. 96–104, Jan. 2026

    work page 2026

  17. [17]

    The Feasibility and Safety of the Glean Urodynamics System: The Modern Urodynamics System Efficacy Study,

    J. Kimet al., “The Feasibility and Safety of the Glean Urodynamics System: The Modern Urodynamics System Efficacy Study,”Journal of Endourology, vol. 39, no. 6, pp. 625–634, Jun. 2025

    work page 2025

  18. [18]

    Pattern recognition algorithm to identify detrusor overactivity on urodynamics,

    H.-H. S. Wanget al., “Pattern recognition algorithm to identify detrusor overactivity on urodynamics,”Neurourology and Urodynamics, vol. 40, no. 1, pp. 428–434, Jan. 2021

    work page 2021

  19. [19]

    Machine Learning for Urodynamic Detection of Detrusor Overactivity,

    K. T. Hobbset al., “Machine Learning for Urodynamic Detection of Detrusor Overactivity,”Urology, vol. 159, pp. 247–254, Jan. 2022

    work page 2022

  20. [20]

    Deep Learning and Numerical Analysis for Bladder Outflow Obstruction and Detrusor Underactivity Diagnosis in Men: A Novel Urodynamic Evaluation Scheme,

    H. Meiet al., “Deep Learning and Numerical Analysis for Bladder Outflow Obstruction and Detrusor Underactivity Diagnosis in Men: A Novel Urodynamic Evaluation Scheme,”Neurourology and Urodynam- ics, vol. 44, no. 2, pp. 512–519, Feb. 2025

    work page 2025

  21. [21]

    Real-Time Typical Urodynamic Signal Recognition System Using Deep Learning,

    X. Liuet al., “Real-Time Typical Urodynamic Signal Recognition System Using Deep Learning,”International Neurourology Journal, vol. 29, no. 1, pp. 40–47, Mar. 2025

    work page 2025

  22. [22]

    Applications of machine learning in urodynamics: A narrative review,

    Liu, Xinet al., “Applications of machine learning in urodynamics: A narrative review,”Neurourology and Urodynamics, vol. 43, no. 7, pp. 1617–1625, Sep. 2024

    work page 2024

  23. [23]

    Can we use machine learning to improve the interpretation and application of urodynamic data?: ICI-RS 2023,

    A. Gammieet al., “Can we use machine learning to improve the interpretation and application of urodynamic data?: ICI-RS 2023,” Neurourology and Urodynamics, vol. 43, no. 6, pp. 1337–1343, Aug. 2024

    work page 2023

  24. [24]

    The Future of Urodynamics: Innovations, Challenges, and Possibilities,

    L. E. Chewet al., “The Future of Urodynamics: Innovations, Challenges, and Possibilities,”Neurourology and urodynamics, p. 10.1002/nau.70074, May 2025

    work page doi:10.1002/nau.70074 2025

  25. [25]

    Real-Time, Single-Sensor Urological Event Detection Using Machine Learning on Low-Power Hardware,

    V . Abbaraju, “Real-Time, Single-Sensor Urological Event Detection Using Machine Learning on Low-Power Hardware,” 2023. [Online]. Available: https://etd.ohiolink.edu/acprod/odb etd/etd/r/1501/10?clear= 10&p10 accession num=case1680559944467708

    work page 2023

  26. [26]

    Real-Time Wavelet Processing and Classifier Algorithms Enabling Single-Channel Diagnosis of Lower Urinary Tract Dysfunction,

    S. J. A. Majeruset al., “Real-Time Wavelet Processing and Classifier Algorithms Enabling Single-Channel Diagnosis of Lower Urinary Tract Dysfunction,” inMachine Learning Applications in Medicine and Biol- ogy, A. Ahmed and J. Picone, Eds. Cham: Springer Nature Switzerland, 2024, pp. 87–114

    work page 2024

  27. [27]

    Estimation of wavelet and short-time Fourier trans- form sonograms of normal and diabetic subjects’ electrogastrogram,

    F. Dirgenaliet al., “Estimation of wavelet and short-time Fourier trans- form sonograms of normal and diabetic subjects’ electrogastrogram,” Computers in Biology and Medicine, vol. 36, no. 12, pp. 1289–1302, Dec. 2006

    work page 2006

  28. [28]

    A comparison of the wavelet and short-time fourier transforms for Doppler spectral analysis,

    Y . Zhanget al., “A comparison of the wavelet and short-time fourier transforms for Doppler spectral analysis,”Medical Engineering & Physics, vol. 25, no. 7, pp. 547–557, Sep. 2003

    work page 2003

  29. [29]

    Wavelet-based segmentation and feature extraction of heart sounds for intelligent PDA-based phonocardiography,

    H. Nazeran, “Wavelet-based segmentation and feature extraction of heart sounds for intelligent PDA-based phonocardiography,”Methods of Information in Medicine, vol. 46, no. 2, pp. 135–141, 2007

    work page 2007

  30. [30]

    Artificial intelligence reading of cystometric traces provides good correlation with human diagnosis,

    J. E. Batista-Mirandaet al., “Artificial intelligence reading of cystometric traces provides good correlation with human diagnosis,”World Journal of Urology, vol. 44, no. 1, 2025

    work page 2025

  31. [31]

    An Efficient and Automatic ECG Arrhythmia Diagnosis System using DWT and HOS Features and Entropy- Based Feature Selection Procedure,

    A. J. Chashmi and M. C. Amirani, “An Efficient and Automatic ECG Arrhythmia Diagnosis System using DWT and HOS Features and Entropy- Based Feature Selection Procedure,”Journal of Electrical Bioimpedance, vol. 10, no. 1, pp. 47–54, Aug. 2019

    work page 2019

  32. [32]

    Wavelet transform feature extraction from human PPG, ECG, and EEG signal responses to ELF PEMF exposures: A pilot study,

    D. Cvetkovicet al., “Wavelet transform feature extraction from human PPG, ECG, and EEG signal responses to ELF PEMF exposures: A pilot study,”Digital Signal Processing, vol. 18, no. 5, pp. 861–874, Sep. 2008

    work page 2008

  33. [33]

    Functional multi-layer perceptron: a non- linear tool for functional data analysis,

    F. Rossi and B. Conan-Guez, “Functional multi-layer perceptron: a non- linear tool for functional data analysis,”Neural Networks, vol. 18, no. 1, pp. 45–60, Jan. 2005

    work page 2005

  34. [34]

    A novel hybrid classification model of artificial neural networks and multiple linear regression models,

    M. Khasheiet al., “A novel hybrid classification model of artificial neural networks and multiple linear regression models,”Expert Systems with Applications, vol. 39, no. 3, pp. 2606–2620, Feb. 2012

    work page 2012

  35. [35]

    A multi-layer perceptron neural network for varied conditional attributes in tabular dispersed data,

    M. Przybya-Kasperek and K. F. Marfo, “A multi-layer perceptron neural network for varied conditional attributes in tabular dispersed data,”PloS One, vol. 19, no. 12, p. e0311041, 2024

    work page 2024

  36. [36]

    Relief-based feature selection: Introduction and review,

    R. J. Urbanowiczet al., “Relief-based feature selection: Introduction and review,”Journal of Biomedical Informatics, vol. 85, pp. 189–203, Sep. 2018

    work page 2018

  37. [37]

    Estimating attributes: Analysis and extensions of RELIEF,

    I. Kononenko, “Estimating attributes: Analysis and extensions of RELIEF,” inProceedings of the 7th European Conference on Machine Learning, ser. ECML’94. Berlin, Heidelberg: Springer- Verlag, Apr. 1994, pp. 171–182. [Online]. Available: https://doi.org/10. 1007/3-540-57868-4 57

    work page 1994

  38. [38]

    C. M. Bishop,Pattern recognition and machine learning, ser. Informa- tion science and statistics. New York: Springer, 2006

    work page 2006

  39. [39]

    Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation,

    D. M. W. Powers, “Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation,” Oct. 2020. [Online]. Available: http://arxiv.org/abs/2010.16061

    work page arXiv 2020

  40. [40]

    An introduction to ROC analysis,

    T. Fawcett, “An introduction to ROC analysis,”Pattern Recognition Letters, vol. 27, no. 8, pp. 861–874, Jun. 2006

    work page 2006

  41. [41]

    Predictive modeling with linear machine learning can estimate glioblastoma survival in months based solely on MGMT- methylation status, age and sex,

    E. Maragnoet al., “Predictive modeling with linear machine learning can estimate glioblastoma survival in months based solely on MGMT- methylation status, age and sex,”Acta Neurochirurgica, vol. 167, no. 1, p. 52, Feb. 2025

    work page 2025

  42. [42]

    Machine learning used to determine features of importance linked to overnight stay after patellar tendon repair,

    L. Thomaset al., “Machine learning used to determine features of importance linked to overnight stay after patellar tendon repair,”Journal of Orthopaedics, vol. 57, pp. 55–59, Nov. 2024

    work page 2024

  43. [43]

    Investigating the mental health of university students during the COVID-19 pandemic in a UK university: a machine learning approach using feature permutation importance,

    T. Chen, “Investigating the mental health of university students during the COVID-19 pandemic in a UK university: a machine learning approach using feature permutation importance,”Brain Informatics, vol. 10, no. 1, p. 27, Oct. 2023

    work page 2023

  44. [44]

    Permutation-based identification of important biomarkers for complex diseases via machine learning models,

    X. Miet al., “Permutation-based identification of important biomarkers for complex diseases via machine learning models,”Nature Communi- cations, vol. 12, no. 1, p. 3008, May 2021

    work page 2021

  45. [45]

    Interrater Reliability in Pediatric Urodynamic Tracings: A Pilot Study,

    A. G. Dudleyet al., “Interrater Reliability in Pediatric Urodynamic Tracings: A Pilot Study,”The Journal of Urology, vol. 197, no. 3 Pt 2, pp. 865–870, Mar. 2017

    work page 2017

  46. [46]

    Interrater Reliability in Interpretation of Neuro- pathic Pediatric Urodynamic Tracings: An Expanded Multicenter Study,

    A. G. Dudleyet al., “Interrater Reliability in Interpretation of Neuro- pathic Pediatric Urodynamic Tracings: An Expanded Multicenter Study,” The Journal of Urology, vol. 199, no. 5, pp. 1337–1343, May 2018

    work page 2018

  47. [47]

    Automated quantification of low amplitude rhythmic contractions (LARC) during real-world urodynamics identifies a potential detrusor overactivity subgroup,

    Z. E. Cullingsworthet al., “Automated quantification of low amplitude rhythmic contractions (LARC) during real-world urodynamics identifies a potential detrusor overactivity subgroup,”PloS One, vol. 13, no. 8, p. e0201594, 2018

    work page 2018

  48. [48]

    A Pilot Study: Detrusor Overactivity Diagnosis Method Based on Deep Learning,

    Q. Zhouet al., “A Pilot Study: Detrusor Overactivity Diagnosis Method Based on Deep Learning,”Urology, vol. 179, pp. 188–195, Sep. 2023

    work page 2023

  49. [49]

    The AUA/SUFU guideline on the diagnosis and treatment of idiopathic overactive bladder,

    A. P. Cameronet al., “The AUA/SUFU guideline on the diagnosis and treatment of idiopathic overactive bladder,”Journal of Urology, Apr. 2024

    work page 2024

  50. [50]

    Artefact detection and quality assessment of ambu- latory ECG signals,

    J. Moeyersonset al., “Artefact detection and quality assessment of ambu- latory ECG signals,”Computer Methods and Programs in Biomedicine, vol. 182, p. 105050, Dec. 2019

    work page 2019

  51. [51]

    Optimization of activity-driven event detection for long-term ambulatory urodynamics,

    F. Zareenet al., “Optimization of activity-driven event detection for long-term ambulatory urodynamics,”Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine, vol. 238, no. 6, pp. 608–618, Jun. 2024. [Online]. Available: https://pmc.ncbi.nlm.nih.gov/articles/PMC11610109/ ENGINEERING APPLICA TIONS OF ARTIFICIAL ...

    work page 2024