The selfBACK artificial intelligence-based smartphone app can improve low back pain outcome even in patients with high levels of depression or stress

Rughani, G., Nilsen, T.I.L., Mair, F.S. , Hartvigsen, J., Mork, P.J. and Nicholl, B.I. (2023) The selfBACK artificial intelligence-based smartphone app can improve low back pain outcome even in patients with high levels of depression or stress. European Journal of Pain, (doi: 10.1002/ejp.2080) (PMID:36680381) (Early Online Publication)

Abstract

Background: selfBACK provides individually tailored self-management support for low back pain (LBP) via an artificial intelligence-based smartphone app. We explore whether those with depressive/stress symptoms can benefit from this technology. Methods: Secondary analysis of the selfBACK randomized controlled trial (n = 461). Participants with LBP were randomized to usual care (n = 229), or usual care plus selfBACK (n = 232). Primary outcome: LBP-related disability (Roland–Morris Disability Questionnaire, RMDQ) over 9 months. Secondary outcomes: global perceived effect (GPE)/pain self-efficacy (PSEQ)/satisfaction/app engagement. Baseline depressive symptoms were measured using the patient health questionnaire (PHQ-8) and stress with the perceived stress scale (PSS). Outcomes stratified by baseline PHQ-8/PSS scores to assess associations across the whole cohort, and intervention versus control groups. Results: Participants with higher levels of depressive/stress symptoms reported more baseline LBP-related disability (RMDQ 3.1; 1.6 points higher in most vs least depressed/stressed groups respectively); lower self-efficacy (PSEQ 8.1; 4.6 points lower in most vs least depressive/stressed groups respectively). LBP-related disability improved over time; relative risk of improvement in those with greatest depressive/stress symptoms versus nil symptom comparators at 9 months: 0.8 (95% CI: 0.6 to 1.0) and 0.8 (95% CI: 0.7 to 1.0) respectively. No evidence that different baseline levels of depressive/perceived stress symptoms are associated with different RMDQ/GPE/PSEQ outcomes. Whilst participants with higher PHQ-8/PSS were less likely to be satisfied or engage with the app, there was no consistent association among PHQ-8/PSS level, the intervention and outcomes. Conclusions: The selfBACK app can improve outcomes even in those with high levels of depressive/stress symptoms and could be recommended for patients with LBP. Significance: We have demonstrated that an app supporting the self-management of LBP is helpful, even in those with higher levels of baseline depression and stress symptoms. selfBACK offers an opportunity to support people with LBP and provides clinicians with an additional tool for their patients, even those with depression or high levels of stress. This highlights the potential for digital health interventions for chronic pain.

• Item Type: Articles
• Status: Early Online Publication
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Rughani, Dr Guy and Nicholl, Dr Barbara and Mair, Professor Frances
• Authors: Rughani, G., Nilsen, T.I.L., Mair, F.S., Hartvigsen, J., Mork, P.J., and Nicholl, B.I.
• College/School: College of Medical Veterinary and Life Sciences > School of Health & Wellbeing > General Practice and Primary Care
• Journal Name: European Journal of Pain
• Publisher: Wiley
• ISSN: 1090-3801
• ISSN (Online): 1532-2149
• Published Online: 20 January 2023
• Copyright Holders: Copyright © 2023 The Authors
• First Published: First published in European Journal of Pain 2023
• Publisher Policy: Reproduced under a Creative Commons license

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
172430		SELFBACK	Barbara Nicholl	European Commission (EC)	689043	HW - General Practice and Primary Care