Unsupervised Machine Learning Approaches Reveal Distinct Phenotypes of Perceived Bladder Pain: A Pilot Study

Abstract

Interstitial cystitis/bladder pain syndrome (IC/BPS) is defined as an unpleasant sensation perceived to be related to the bladder with associated urinary symptoms. Due to difficulties discriminating pelvic visceral sensation, IC/BPS likely represents multiple phenotypes with different etiologies that present with overlapping symptomatic manifestations, which complicates clinical management. We hypothesized that unique bladder pain phenotypes or “symptomatic clusters” would be identifiable using machine learning analysis (unsupervised clustering) of validated patient-reported urinary and pain measures. Patients (n = 145) with pelvic pain/discomfort perceived to originate in the bladder and lower urinary tract symptoms answered validated questionnaires [OAB Questionnaire (OAB-q), O'Leary-Sant Indices (ICSI/ICPI), female Genitourinary Pain Index (fGUPI), and Pelvic Floor Disability Index (PFDI)]. In comparison to asymptomatic controls (n = 69), machine learning revealed three bladder pain phenotypes with unique, salient features. The first group chiefly describes urinary frequency and pain with the voiding cycle, in which bladder filling causes pain relieved by bladder emptying. The second group has fluctuating pelvic discomfort and straining to void, urinary frequency and urgency without incontinence, and a sensation of incomplete emptying without urinary retention. Pain in the third group was not associated with voiding, instead being more constant and focused on the urethra and vagina. While not utilized as a feature for clustering, subjects in the second and third groups were significantly younger than subjects in the first group and controls without pain. These phenotypes defined more homogeneous patient subgroups which responded to different therapies on chart review. Current approaches to the management of heterogenous populations of bladder pain patients are often ineffective, discouraging both patients and providers. The granularity of individual phenotypes provided by unsupervised clustering approaches can be exploited to help objectively define more homogeneous patient subgroups. Better differentiation of unique phenotypes within the larger group of pelvic pain patients is needed to move toward improvements in care and a better understanding of the etiologies of these painful symptoms.

Development and Validation of a Machine Learning Algorithm to Classify Lower Urinary Tract Symptoms

“…Several groups have tried to subclassify urinary symptoms or genitourinary pain, but have typically examined only one symptom cluster in isolation (e.g., overactive bladder (40)(41)(42)(43) or genitourinary pain (44)(45)(46)(47)). However, "as often patients present with multiple urinary symptoms that do not perfectly fit the pre-established diagnoses,"(42) the intentional exclusion in these studies of patients with overlapping symptoms or co-existing pelvic organ prolapse may underlie the lack of practical progress in improving current diagnostic schema.…”

“…23 These nine phenotypic diagnoses included the range of common urologic diagnoses (SUI, UUI, MUI, IC/BPS), but also incorporated several less common, emerging pathologies that have only recently been suspected in the etiology of LUTS (MFS, MPP, NUPP). 28,[35][36][37] The classifier also distinguished between subjects with mixed urinary incontinence in whom a correctable, anatomic cause (POP) to their symptoms should be suspected, which may influence treatment choices. Lastly, the classifier was capable of recognizing highly impactful symptoms like FI, which are frequently unaddressed as patients are often too embarrassed to express them.…”

“…Several groups have tried to subclassify urologic phenotypes, but have typically examined only one symptom cluster in isolation (e.g., overactive bladder 12,22-24 or genitourinary pain 25-28 ). Substantial work, however, documents that these divisions are artificial; many patients carrying an OAB diagnosis suffer from significant bladder pain (35%) while more than 30% of IC/BPS patients have urge incontinence.…”

Aspectos psicológicos asociados a la cistitis intersticial

“…Esta condición no cuenta con análisis diagnósticos que permitan emitir un dictamen certero, lo que dificulta su identificación por los especialistas y por tanto su prevalencia puede estar subestimada 12 , pues se basa en los síntomas informados. No obstante, se ha avanzado en la investigación, en entender la heterogeneidad de los pacientes 29 y en el desarrollo de tratamientos eficaces para el manejo de la enfermedad, así como en la identificación de aspectos que pueden incidir en la profundización de los síntomas y el deterioro de la calidad de vida del paciente.…”

Validation of Distinct Bladder Pain Phenotypes Utilizing the MAPP Research Network Cohort

“…Other classification systems for patients without Hunner lesions have been proposed but remain underutilized due to reliance on extensive clinical information, detailed physical exams, or genetic/histopathologic results [ 13 – 15 ]. Our group recently evaluated symptomatic patterns in 145 women with IC/BPS without Hunner lesions [ 16 ]. Using unsupervised machine learning (ML) approaches, patients with bladder pain could be categorized into three distinct phenotypes using patient-reported symptomatic questionnaires alone.…”