Application Of Artificial Intelligence As An Adjunct In The Evaluation Of Lower Urinary Tract Symptoms Among Rural Women: A Study In Functional And Female Urology
DOI:
https://doi.org/10.69980/ajpr.v28i5.803Keywords:
Artificial intelligence, Lower urinary tract symptoms, Female urology, Rural healthAbstract
Lower urinary tract symptoms (LUTS) are common among women and often underreported, particularly in rural populations where access to specialist care is limited. Accurate symptom evaluation is essential for appropriate management; however, conventional assessment may be constrained by time, resources, and expertise. Artificial intelligence (AI) has emerged as a potential adjunct to enhance symptom classification and clinical decision-making in functional and female urology.
Objectives: To evaluate the role of artificial intelligence as an adjunct to standard clinical assessment in the evaluation and classification of LUTS among rural women.
Materials and Methods: This prospective observational study included 100 rural women presenting with LUTS. All participants underwent standard clinical evaluation using validated symptom assessment tools, followed by AI-assisted evaluation for symptom classification and triage. Concordance between AI-assisted assessment and clinician diagnosis was analyzed. Secondary outcomes included feasibility, impact on clinical decision-making, and referral accuracy.
Results: Storage symptoms were the predominant presentation (72%), with mixed symptom patterns observed in 44% of participants. AI-assisted evaluation reduced non-specific LUTS classification (10% to 4%) and improved identification of mixed phenotypes (18% to 24%). There was substantial agreement between AI-assisted evaluation and clinician diagnosis (overall agreement 86%, Cohen’s κ = 0.78; p < 0.001). AI recommendations influenced refinement of initial clinical classification in 18% of cases and significantly improved identification of patients requiring referral for advanced evaluation (p < 0.001). Clinician acceptance of AI-assisted recommendations was high (84%).
Conclusion: AI-assisted evaluation, when used as an adjunct, enhances symptom phenotyping and referral triage in rural women with LUTS. This approach offers a feasible and standardized strategy to strengthen functional and female urology care in resource-limited settings, provided appropriate validation and ethical safeguards are maintained.
References
1. Garg P, et al. Utility of opportunistic screening to assess the impact of urinary incontinence on quality of life and barriers to seeking treatment among women attending a tertiary healthcare centre in North India. BMC Urol. 2024;24
2. Youn S, Park BJ. Artificial intelligence for predicting treatment failure in neurourology: from automated urodynamics to precision management. Int Neurourol J. 2025;29
3. Speich JE, Klausner AP. Artificial intelligence in urodynamics (AI-UDS): the next “big thing”. Continence. 2025;13:101754.
4. Liu X, Zhong P, Chen D, Liao L. Real-time typical urodynamic signal recognition system using deep learning. Int Neurourol J. 2025;29(1):40–47.
5. Chen K, Chen Q, Nan N, Sun L, Ma M, Yu S. An optimized deep learning model based on transperineal ultrasound images for precision diagnosis of female stress urinary incontinence. Front Med. 2025;12:1564446.
6. Yang CC, et al. Lower urinary tract symptoms: advances in women’s urologic health. Urol Clin North Am. 2020;47
7. Sutcliffe S, et al. Lower urinary tract symptoms in US women. J Urol. 2024;211
8. Omae K, Sekido N, Haga N, et al. Unsupervised machine learning approach to interpret complex lower urinary tract symptoms and their impact on quality of life in adult women. World J Urol. 2025;43
9. Machine learning in female pelvic medicine and reconstructive surgery: urology and beyond. AUA News. 2023;28
10. Wang Q, et al. Machine learning in female urinary incontinence: a scoping review. Int Urogynecol J. 2024;35
11. Huang HH, et al. Exploring artificial intelligence in functional urology: a comprehensive review. Urol Sci. 2025;36
12. Samenezhad S, Rafighi D. The role of artificial intelligence in advancing urologic care: from diagnostics to therapeutics. Urol Pract. 2025
13. Peng B, et al. A female overactive bladder risk model developed by machine learning. Int Neurourol J. 2025;29
14. Hadi F, et al. A treatment prediction strategy for overactive bladder using machine learning. Neurourol Urodyn. 2023;42
15. Başaranoğlu M, et al. Artificial intelligence-based prediction of treatment failure and outcomes in overactive bladder management. BMC Urol. 2025;25
16. Wang J, et al. Deep learning–assisted two-dimensional transperineal ultrasound for analyzing bladder neck motion in women with stress urinary incontinence. Am J Obstet Gynecol. 2025;232
17. Raina D, et al. Deep-learning model for quality assessment of urinary bladder ultrasound images using multiscale and higher-order processing. IEEE Trans Ultrason Ferroelectr Freq Control. 2024;71
18. Su M, et al. Predicting postoperative stress urinary incontinence after pelvic organ prolapse surgery using machine learning. JMIR Med Inform. 2025;13:e
19. Farashi S, et al. Prediction of urinary tract infection using machine learning approaches. BMC Med Inform Decis Mak. 2025;25
20. Ma SP, et al. Electronic phenotyping of urinary tract infections as a labeling strategy for machine learning. J Biomed Inform. 2024
21. Mahapatra C, et al. Artificial intelligence for diagnosing bladder pathophysiology: an updated review and future prospects. Diagnostics (Basel). 2025;15
22. Neves B, et al. Zero-shot learning for clinical phenotyping with large language models. Artif Intell Med. 2025
Downloads
Published
Issue
Section
License
Copyright (c) 2025 American Journal of Psychiatric Rehabilitation
This work is licensed under a Creative Commons Attribution 4.0 International License.
This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 International License permitting all use, distribution, and reproduction in any medium, provided the work is properly cited.
This work is licensed under a 
