• Can unsupervised machine learn...

*Result*: Can unsupervised machine learning gain new insights into urodynamic pressure flow pattern analysis?

Title:
Can unsupervised machine learning gain new insights into urodynamic pressure flow pattern analysis?
Authors:
van Dort W; Department of Urology, University Medical Center Utrecht, Utrecht, The Netherlands., Rosier PFWM; Department of Urology, University Medical Center Utrecht, Utrecht, The Netherlands., van Steenbergen TRF; Department of Urology, University Medical Center Utrecht, Utrecht, The Netherlands., Geurts BJ; Mathematics of Multiscale Modeling and Simulation, Department of Applied Mathematics, University of Twente, Enschede, The Netherlands., de Kort LMO; Department of Urology, University Medical Center Utrecht, Utrecht, The Netherlands.
Source:
BJU international [BJU Int] 2026 Jan; Vol. 137 (1), pp. 112-119. Date of Electronic Publication: 2025 Oct 01.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Blackwell Science Country of Publication: England NLM ID: 100886721 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1464-410X (Electronic) Linking ISSN: 14644096 NLM ISO Abbreviation: BJU Int Subsets: MEDLINE
Imprint Name(s):
Original Publication: Oxford, UK : Blackwell Science, c1999-
MeSH Terms:
Urodynamics*/physiology , Lower Urinary Tract Symptoms*/physiopathology , Lower Urinary Tract Symptoms*/diagnosis , Unsupervised Machine Learning* , Machine Learning*, Humans ; Male ; Middle Aged ; Aged ; Adult
References:
Neurourol Urodyn. 2024 Nov;43(8):2178-2184. (PMID: 38847287)
Investig Clin Urol. 2022 May;63(3):301-308. (PMID: 35437961)
N Engl J Med. 2017 Sep 28;377(13):1209-1211. (PMID: 28953443)
World J Urol. 1995;13(1):47-58. (PMID: 7773317)
Neurourol Urodyn. 2024 Aug;43(6):1337-1343. (PMID: 37921238)
Br J Urol. 1973 Oct;45(5):497-507. (PMID: 4270633)
Urol Clin North Am. 1996 Aug;23(3):393-405. (PMID: 8701554)
Neurourol Urodyn. 2023 Nov;42(8):1603-1627. (PMID: 37139677)
Neurourol Urodyn. 2021 Jan;40(1):428-434. (PMID: 33205846)
Neurourol Urodyn. 1995;14(3):217-29. (PMID: 7647804)
J Urol. 1995 Jul;154(1):190-4. (PMID: 7776421)
Neurourol Urodyn. 2001;20(2):175-85. (PMID: 11170192)
Neurourol Urodyn. 2023 Nov;42(8):1628-1638. (PMID: 37614044)
Med Biol Eng Comput. 1989 May;27(3):314-21. (PMID: 2601454)
World J Urol. 1995;13(1):34-9. (PMID: 7539679)
J Urol. 1995 May;153(5):1520-5. (PMID: 7536260)
Neurourol Urodyn. 2017 Jun;36(5):1243-1260. (PMID: 27917521)
Neurourol Urodyn. 2002;21(3):261-74. (PMID: 11948720)
J Urol. 2003 Mar;169(3):1007-10. (PMID: 12576832)
Neurourol Urodyn. 2012 Apr;31(4):549-55. (PMID: 22396315)
J Urol. 1992 Dec;148(6):1856-60. (PMID: 1433620)
Eur Urol Focus. 2023 Jan;9(1):209-215. (PMID: 35835694)
Contributed Indexing:
Keywords: artificial intelligence; bladder outflow obstruction; machine learning; male LUTS; pressure flow study; urodynamics
Entry Date(s):
Date Created: 20251001 Date Completed: 20251210 Latest Revision: 20251212
Update Code:
20260130
PubMed Central ID:
PMC12690339
DOI:
10.1111/bju.70011
PMID:
41031874
Database:
MEDLINE

*Further Information*

*Objectives: To explore the use of unsupervised machine learning (UML) to analyse segments of the pressure flow study (PFS) curve after maximum flow, and subsequently to analyse the urodynamic and patient characteristics of men in the detected clusters.
Subjects and Methods: In this study, we considered 1650 PFSs of men with lower urinary tract symptoms, without relevant interventions in the past. After datapoint reduction and normalisation of the PFS curve segments, the k-Shape clustering algorithm was used to identify different pattern clusters. Differences in patient and urodynamic characteristics among those clusters were explored.
Results: The UML approach identified four prominent clusters, with significantly different patient and urodynamic characteristics. Two pairs of these clusters were visually similar, and included similar urethral resistance values; however, they differed with regard to detrusor voiding contraction (DVC) and prostate size. In two clusters, the PFS curve pattern was significantly different from the commonly assumed 'normal' urethral resistance pattern in elderly men.
Conclusion: In males, PFS patterns are considered to be uniform in shape. However, this study shows that UML can help to identify clusters of pressure-flow urethral resistance subtype patterns in men. We found that these subtype patterns were associated with DVC strength and prostate size. This feasibility study has shown that UML clustering of urodynamic PFSs in men holds promise for improving the diagnosis of urethral resistance and DVC properties and dynamics.
(© 2025 The Author(s). BJU International published by John Wiley & Sons Ltd on behalf of BJU International.)*