Urinary symptoms and urodynamic findings in women with pelvic organ prolapse: is there a correlation? Results of an artificial neural network analysis.

BACKGROUND International official guidelines recommend urodynamic (UDS) evaluation in patients with pelvic organ prolapse (POP). However, the real benefit of this examination is still the subject of heated and controversial debate. Therefore, we aimed to assess the correlation between urinary symptoms and UDS findings in women with POP through the implementation of a sophisticated computer-based technology in the outpatient workup. DESIGN, SETTING, AND PARTICIPANTS A prospective cohort study was performed in a single, tertiary, urogynaecologic referral department, enrolling consecutive women seeking care for pelvic floor dysfunctions. INTERVENTION Patients underwent clinical and urodynamic evaluation. Data regarding baseline characteristics, symptoms, anatomic, and urodynamic findings were gathered for each patient. Multiple linear regression (MLR) and artificial neural networks (ANNs) were performed to design predicting models. RESULTS AND LIMITATIONS A total of 802 women with POP were included. POP quantification stages and baseline data poorly correlated to final UDS findings. Stress urinary incontinence and overactive bladder were both independently associated to each UDS diagnosis, including detrusor overactivity (DO), urodynamic stress incontinence (USI), and mixed urinary incontinence (USI plus DO). Receiver operating characteristic comparison confirmed that ANNs were more accurate than MLR in identifying predictors of UDS diagnosis, but none of these methods could successfully overcome UDS. Case-control studies are needed to confirm our findings. CONCLUSIONS Despite the current debate based on the actual value of UDS in women with POP, even the implementation of ANN, a sophisticated computer-based technology, does not permit an accurate diagnosis just on the basis of symptoms or avoiding UDS. Therefore, in women with POP, especially if scheduled for surgery, UDS should be considered as mandatory, since misleading counselling could result in unpleasant unexpected events.

[1]  R. J. Taylor,et al.  The cost‐effectiveness of preoperative testing (basic office assessment vs urodynamics) for stress urinary incontinence in women , 2002, BJU international.

[2]  K. J. Dalton,et al.  Artificial neural networks for decision support in clinical medicine. , 1995, Annals of medicine.

[3]  R. Oliver A Cognitive Model of the Antecedents and Consequences of Satisfaction Decisions , 1980 .

[4]  Mohid S. Khan,et al.  The relationship between urinary symptom questionnaires and urodynamic diagnoses: an analysis of two methods of questionnaire administration , 2004, BJOG : an international journal of obstetrics and gynaecology.

[5]  S. Petrou An International Urogynecological Association (IUGA)/International Continence Society (ICS) joint report on the terminology for female pelvic floor dysfunction , 2010 .

[6]  L. Selvaggi,et al.  Validation of an Italian version of the prolapse quality of life questionnaire. , 2003, European journal of obstetrics, gynecology, and reproductive biology.

[7]  P. Abrams,et al.  Good urodynamic practices: Uroflowmetry, filling cystometry, and pressure‐flow studies * * , 2002, Neurourology and urodynamics.

[8]  B. S. Hampton,et al.  The impact of multichannel urodynamics upon treatment recommendations for female urinary incontinence , 2008, International Urogynecology Journal.

[9]  C. Maher,et al.  Surgery for Pelvic Organ Prolapse , 2010, Female pelvic medicine & reconstructive surgery.

[10]  W. Baxt Application of artificial neural networks to clinical medicine , 1995, The Lancet.

[11]  L. Cardozo,et al.  Pelvic organ prolapse and overactive bladder , 2010, Neurourology and urodynamics.

[12]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[13]  S. Salvatore,et al.  Do overactive bladder symptoms improve after repair of anterior vaginal wall prolapse? , 2007, International Urogynecology Journal.

[14]  R. Turner-Warwick,et al.  Synchronous cine-pressure-flow-cysto-urethrography with special reference to stress and urge incontinence. , 1970, British journal of urology.

[15]  T. Dorkin,et al.  Urodynamics in the octogenarian female: is it worthwhile? , 2010, International Urogynecology Journal.

[16]  Brian L. Cohen,et al.  What is the predictive value of urodynamics to reproduce clinical findings of urinary frequency, urge urinary incontinence, and/or stress urinary incontinence? , 2010, International Urogynecology Journal.

[17]  S. Salvatore,et al.  Correlation between anatomical findings and symptoms in women with pelvic organ prolapse using an artificial neural network analysis , 2011, International Urogynecology Journal.

[18]  L. Cardozo,et al.  Ringing the changes in evaluation of urogenital prolapse , 2011, International Urogynecology Journal.

[19]  Jonas S Almeida,et al.  Predictive non-linear modeling of complex data by artificial neural networks. , 2002, Current opinion in biotechnology.

[20]  F. Ghezzi,et al.  Ultrasound measurement of bladder wall thickness in different forms of detrusor overactivity , 2010, International Urogynecology Journal.

[21]  F. Ghezzi,et al.  Efficacy of tolterodine in women with detrusor overactivity and anterior vaginal wall prolapse: is it the same? , 2007, BJOG : an international journal of obstetrics and gynaecology.

[22]  F. Pesce,et al.  Italian validation of the International Consultation on Incontinence Questionnaires , 2006, BJU international.

[23]  M. Takeda,et al.  Incontinence and detrusor dysfunction associated with pelvic organ prolapse: clinical value of preoperative urodynamic evaluation , 2009, International Urogynecology Journal.

[24]  A. Markland,et al.  Symptoms of Combined Prolapse and Urinary Incontinence in Large Surgical Cohorts , 2010, Obstetrics and gynecology.

[25]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.