Machine Learning and Artificial Intelligence to Improve Interpretation of Urodynamics

Article CAS PubMed Google Scholar

Silver D, Schrittwieser J, Simonyan K, et al. Mastering the game of go without human knowledge. Nature. 2017;550(7676):354–9.

Meta Fundamental AI Research Diplomacy Team (FAIR), Bakhtin A, Brown N, et al. Human-level play in the game of Diplomacy by combining language models with strategic reasoning. Science. 2022;378(6624):1067–74.

Manning C, Schutze H. Foundations of statistical natural language processing. MIT press; 1999.

Deng J, Lin Y. The benefits and challenges of ChatGPT: an overview. Front Comput Intelligent Systems. 2022;2(2):81–3.

Metz C, Laffin B, Duc HDT, Clontz I. What riding in a self-driving Tesla tells us about the future of autonomy. The New York Times. https://www.nytimes.com/interactive/2022/11/14/technology/tesla-self-driving-flaws.html

Halpern S. The rise of A.I. fighter pilots. The New Yorker. New York: Condé Nast; 2022.

J.P Morgan Asset ManagementMachine learning in hedge fund investing. 2023. Accessed 01 Jan 2023. https://am.jpmorgan.com/sg/en/asset-management/institutional/insights/portfolio-insights/machine-learning-in-hedge-fund-investing/

Park B, Bae JK. Using machine learning algorithms for housing price prediction: The case of Fairfax County, Virginia housing data. Expert Syst Appl. 2015;42(6):2928–34.

Müller B, Reinhardt J, Strickland MT. Neural networks: an introduction. Physics of Neural Networks. Springer Science & Business Media; 1995.

Book Google Scholar

Dave T, Athaluri SA, Singh S. ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations. Front Artif Intell. 2023;6:1169595.

U.S. Food and Drug Administration. Artificial intelligence and machine learning (AI/ML)-enabled medical devices. AI/ML-Enabled Medical Devices. 2022. https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices. Accessed 3 Jan 2024.

Lakhani P, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017;284(2):574–82.

Bejnordi BE, Veta M, Van Diest PJ, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 2017;318(22):2199–210.

Moon JW, Yang E, Kim J-H, Kwon OJ, Park M, Yi CA. Predicting non-small-cell lung cancer survival after curative surgery via deep learning of diffusion MRI. Diagnostics. 2023;13(15):2555.

Attia ZI, Noseworthy PA, Lopez-Jimenez F, et al. An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction. The Lancet. 2019;394(10201):861–7. The algorithm in this study accurately predicted underlying atrial fibrillation based on normal EKGs.

Khene Z-E, Bigot P, Doumerc N, et al. Application of machine learning models to predict recurrence after surgical resection of nonmetastatic renal cell carcinoma. Eur Urol Oncol. 2023;6(3):323–30.

Ostrowski DA, Logan JR, Antony M, Broms R, Weiss DA, Van Batavia J, et al. Automated Society of Fetal Urology (SFU) grading of hydronephrosis on ultrasound imaging using a convolutionalneural network. J Pediatr Urol. 2023;19(5):566.E1–566.E8.

Ström P, Kartasalo K, Olsson H, et al. Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study. Lancet Oncol. 2020;21(2):222–32.

Article CAS PubMed Google Scholar

Heller N, Tejpaul R, Isensee F, et al. Computer-generated RENAL nephrometry scores yield comparable predictive results to those of human-expert scores in predicting oncologic and perioperative outcomes. J Urol. 2022;207(5):1105–15.

Pannek J, Kennelly M, Kessler TM, Linsenmeyer T, Wyndaele J-J, Biering-Sørensen F. International spinal cord injury urodynamic basic data set (version 2.0). Spinal Cord Ser Cases. 2018;4(1):98.

Miller BD, Tallman CT, Boone TB, Khavari R. Low interrater reliability of videourodynamic diagnosis of detrusor external sphincter dyssynergia. Urogynecology. 2021;27(5):297–9.

Dudley AG, Adams MC, Brock JW, et al. Interrater reliability in interpretation of neuropathic pediatric urodynamic tracings: an expanded multicenter study. J Urol. 2018;199(5):1337–43.

Zhou Q, Chen Z, Wu B, Lin D, Hu Y, Zhang X, Liu J. A pilot study: detrusor overactivity diagnosis method based on deep learning. Urology. 2023;179:188–95. The study reported models based on deep learning that accurately detected detrusor overactivity from urodynamics studies.

Niederhauser T, Gafner ES, Cantieni T, et al. Detection and quantification of overactive bladder activity in patients: can we make it better and automatic? NeurourolUrodyn. 2018;37(2):823–31. Here, an algorithm based on time-frequency analysis was developed to generate a bladder overactivity index to estimate non-voiding activity and classify detrusor overactivity.

Wang HHS, Cahill D, Panagides J, Nelson CP, Wu HT, Estrada C. Pattern recognition algorithm to identify detrusor overactivity on urodynamics. NeurourolUrodyn. 2021;40(1):428–34. In this study, manifold learning and dynamic time warping algorithms were developed to automatically identify detrusor overactivity on urodynamics.

Hobbs KT, Choe N, Aksenov LI, et al. Machine learning for urodynamic detection of detrusor overactivity. Urology. 2022;159:247–54. Here, the investigators developed algorithms that were constructed using data windowing, dimensionality reduction, and support vector machines, to detect detrusor overactivity from urodynamic tracings from children with spina bifida.

Abbaraju V, Lewis K, Majerus SJ. Machine learning for automated bladder event classification from single-channel vesical pressure recordings. 2022 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), Philadelphia, PA, USA; 2022. p. 1–6. https://doi.org/10.1109/SPMB55497.2022.10014792. The investigators developed a framework for the automatic classification of bladder events including voiding contraction, detrusor overactivity, abdominal event, or no event based on single-channel urodynamics studies.

Abrams P, Cardozo L, Fall M, et al. The standardisation of terminology in lower urinary tract function: report from the standardisation sub-committee of the International Continence Society. Urology. 2003;61(1):37–49.

Osman NI, Chapple CR, Abrams P, et al. Detrusor underactivity and the underactive bladder: a new clinical entity? A review of current terminology, definitions, epidemiology, aetiology, and diagnosis. Eur Urol. 2014;65(2):389–98.

Szmydki D, Burzyński B, Sołtysiak-Gibała Z, et al. Prediction of detrusor underactivity based on non-invasive functional tests and clinical data in patients with symptoms of bladder outlet obstruction. Eur Rev Med Pharmacol Sci. 2020;24(21). In this study, a decision-making algorithm was generated to predict impaired detrusor contractility based on uroflowmetry.

Bang S, Tukhtaev S, Ko KJ, et al. Feasibility of a deep learning-based diagnostic platform to evaluate lower urinary tract disorders in men using simple uroflowmetry. Investig Clin Urol. 2022;63(3):301. The investigators constructed a convolutional neural network prediction model to distinguish bladder outlet obstruction versus detrusor underactivity using simple uroflowmetry.

Matsukawa Y, Kameya Y, Takahashi T, et al. Characteristics of uroflowmetry patterns in men with detrusor underactivity revealed by artificial intelligence. Int J Urol. 2023; The team developed machine learning algorithms to identify and distinguish between detrusor underactivity versus bladder outlet obstruction and identified the ratio of the first peak flow rate to Qmaxas an important predictive factor for detrusor underactivity.

Drake MJ, Doumouchtsis SK, Hashim H, Gammie A. Fundamentals of urodynamic practice, based on International Continence Society good urodynamic practices recommendations. NeurourolUrodyn. 2018;37(S6):S50–60.

Schäfer W, Abrams P, Liao L, et al. Good urodynamic practices: uroflowmetry, filling cystometry, and pressure-flow studies. NeurourolUrodyn. 2002;21(3):261–74.

LumineticsCore™ (formerly known as IDx-DR) the first FDA-approved AI system, is growing rapidly. Docwire; 2023, Accessed 10/09/2023. https://www.docwirenews.com/post/idx-dr-the-first-fda-approved-ai-system-is-growing-rapidly

Ginsberg DA, Boone TB, Cameron AP, et al. The AUA/SUFU guideline on adult neurogenic lower urinary tract dysfunction: diagnosis and evaluation. J Urol. 2021;206(5):1097–105.

Ginsberg DA, Boone TB, Cameron AP, et al. The AUA/SUFU guideline on adult neurogenic lower urinary tract dysfunction: treatment and follow-up. J Urol. 2021;206(5):1106–13.

Article CAS PubMed Google Scholar

Weaver J, Weiss D, Aghababian A, et al. Why are pediatric urologists unable to predict renal deterioration using urodynamics? A focused narrative review of the shortcomings of the literature. J Pediatr Urol. 2022;18(4):493–8. A summary of the literature in the field of prediction of renal deterioration using urodynamics, and a call to action for the implementation of machine learning to address the shortcomings.

D'Ancona C, Haylen B, Oelke M, et al. The International Continence Society (ICS) report on the terminology for adult male lower urinary tract and pelvic floor symptoms and dysfunction. NeurourolUrodyn. 2019;38(2):433–77.

Dudley AG, Casella DP, Lauderdale CJ, et al. Interrater reliability in pediatric urodynamic tracings: a pilot study. J Urol. 2017;197(3):865–70.

Article CAS PubMed PubMed Central Google Scholar

Amundsen CL, Richter HE, Menefee SA, et al. OnabotulinumtoxinA vs sacral neuromodulation on refractory urgency urinary incontinence in women: a randomized clinical trial. JAMA. 2016;316(13):1366–74.

Werneburg GT, Werneburg EA, Goldman HB, Mullhaupt AP, Vasavada SP. Machine learning provides an accurate prognostication model for refractory overactive bladder treatment response and is noninferior to human experts. NeurourolUrodyn. 2022;41(3):813–9. Using reproducing kernel techniques, the team developed algorithms based on urodynamics and clinical factors to accurately predict response and reduction in urge incontinence episodes following intravesical botulinum toxin and sacral neuromodulation overactive bladder therapies.

Werneburg GT, Werneburg EA, Goldman HB, Mullhaupt AP, Vasavada SP. Neural networks outperform expert humans in predicting patient impressions of symptomatic improvement following overactive bladder treatment. Int Urogynecol J. 2023;34(5):1009–16. Machine learning algorithms based on urodynamics and other clinical factors were developed to accurately predict patient-reported symptomatic improvement following botulinum toxin and sacral neuromodulation for overactive bladder.

Lightner DJ, Gomelsky A, Souter L, Vasavada SP. Diagnosis and treatment of overactive bladder (non-neurogenic) in adults: AUA/SUFU guideline amendment 2019. J Urol. 2019;202(3):558–63.

Hendrickson WK, Xie G, Rahn DD, Amundsen CL, Hokanson JA, Bradley M, et al. Predicting outcomes after intradetrusor onabotulinumtoxina for non-neurogenic urgency incontinence in women. Neurourol Urodyn. 2022;41(1):432–47. Investigators developed machine learning algorithms trained on clinical variables and urodynamics factors to predict time to recurrence following botulinum toxin intravesical injection.

Sheyn D, Ju M, Zhang S, et al. Development and validation of a machine learning algorithm for predicting response to anticholinergic medications for overactive bladder syndrome. Obstet Gynecol. 2019;134(5):946–57. Here, machine learning algorithms were trained on clinical and urodynamics factors to predict response to anticholinergic therapy in individuals with overactive bladder and validated on an external set of patients.

Siontis KC, Noseworthy PA, Attia ZI, Friedman PA. Artificial intelligence-enhanced electrocardiography in cardiovascular disease management. Nat Rev Cardiol. 2021;18(7):465–78.