The lived experience of functional bowel disorders: a machine learning approach

Abstract

AbstractObjectiveFunctional bowel disorders (FBDs) are multi-dimensional diseases varying in demographics, symptomology, lifestyle, mental health, and susceptibility to treatment. The patient lived experience is an integration of these factors, best understood with appropriately multivariate models.MethodsIn a large patient cohort (n=1175), we developed a machine learning framework to better understand the lived experience of FBDs. Iterating through 59 factors available from routine clinical care, spanning patient demography, diagnosis, symptomatology, life-impact, mental health indices, healthcare access requirements, COVID-19 impact, and treatment effectiveness, machine models were used to quantify the predictive fidelity of one feature from the remainder. Bayesian stochastic block models were used to delineate the network community structure underpinning the lived experience of FBDs.ResultsMachine models quantified patient personal health rating (R20.35), anxiety and depression severity (R20.54), employment status (balanced accuracy 96%), frequency of healthcare attendance (R20.71), and patient-reported treatment effectiveness variably (R2range 0.08-0.41). Contrary to the view of many healthcare professionals, the greatest determinants of patient-reported health and quality-of-life were life-impact, mental wellbeing, employment status, and age, rather than diagnostic group and symptom severity. Patients responsive to one treatment were more likely to respond to another, leaving many others refractory to all.ConclusionsThe assessment of patients with FBDs should be less concerned with diagnostic classification than with the wider life impact of illness, including mental health and employment. The stratification of treatment response (and resistance) has implications for clinical practice and trial design, in need of further research.What is known?- The diagnosis of functional bowel disorders (FBDs) is based on combinations of gastrointestinal symptoms.- Beyond diagnosis, the patient lived experience is much broader, with far-reaching impact on their life ranging from effect upon daily activities, mental well-being, access and satisfaction of healthcare, and treatment efficacy.What is new here?- FBD diagnosis was not a determinant of any machine model predicting patient-reported disease impact factors.- Instead, lived experience factors inclusive of life impact, mental wellbeing, employment status, and age were the greatest determinants of patient-reported health quality.- Efforts to prioritize improvements in patient-reported health quality for FBDs should shift focus to the broader lived experience.- Patients reporting response to one treatment were more likely to report response to another, leaving others refractory to all.- Predicting a response to one treatment by response to another highlights the importance of non-placebo trial designs.