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

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.

Artificial Intelligence Interventions in Chronic Pain Management: A Scoping Review (Preprint)

“…The reports revealed that most of (65.5-98%) the participants who used the AI-based interventions had at least year 12 education. Although some studies reported that more than half of the subjects had a fulltime job, [55][56][57]75 the accounts by Piette et al 50 and Chiauzzi et al 52 reported that just about one third of their participants were fully employed. targeted the management of one or all the biopsychosocial components of chronic low back pain (specific or non-specific).…”

“…Randomized controlled trials made up 34.4% (n= 11) of the research, [49][50][51][52][53][54][55][56][57][58][59] while others were pilot studies, observational studies, quasi-experimental studies, among others (Figure 7).…”

The SelfSTarT intervention for low back pain patients presenting to first contact physiotherapists: A mixed methods service evaluation

“…Patients using the SelfBACK App were shown to have reduced pain and disability. In a recent study of 461 people with low back pain (Rughani et al, 2023), the SelfBack App was able to improve outcomes for those with high levels of pain and distress. For the purposes of this service evaluation, the combined approach was called SelfSTarT.…”

Digital Therapeutics (DTx) Expand Multimodal Treatment Options for Chronic Low Back Pain: The Nexus of Precision Medicine, Patient Education, and Public Health

“…Digital health technologies for CLBP provide diverse treatment and self-management modalities [35,55,[94][95][96][97][98][99][100][101][102][103][104][105][106][107][108]. Examples of mobile apps for CLBP include "BackRx" delivering yoga and Pilates exercises for patients with discogenic CLPB [97,109], as well as PainNavigator delivering CLBP management, including education, physical exercises, yoga, and mindfulness [110].…”