Finding Predictive Factors of Stabilization Exercise Adherence in Randomized Controlled Trials on Low Back Pain: An Individual Data Reanalysis Using Machine Learning Techniques

Ann-Christin Pfeifer; Paul Schröder-Pfeifer; Marcus Schiltenwolf; Lutz Vogt; Christian Schneider; Petra Platen; Heidrun Beck; Pia-Maria Wippert; Tilman Engel; Monique Wochatz; Frank Mayer; Daniel Niederer

doi:10.1016/j.apmr.2024.12.015

Finding Predictive Factors of Stabilization Exercise Adherence in Randomized Controlled Trials on Low Back Pain: An Individual Data Reanalysis Using Machine Learning Techniques

Arch Phys Med Rehabil. 2025 Jan 3:S0003-9993(24)01419-9. doi: 10.1016/j.apmr.2024.12.015. Online ahead of print.

Authors

Affiliations

¹ Pain Management, Center of Orthopaedics and Trauma Surgery, Heidelberg University Hospital, Heidelberg, Germany.
² Department of Sports Medicine and Exercise Physiology, Goethe University Frankfurt, Frankfurt am Main, Germany.
³ Orthopädiezentrum Theresie, München, Germany.
⁴ Department of Sports Medicine and Sports Nutrition, Ruhr University Bochum, Bochum, Germany.
⁵ University Hospital Carl Gustav Carus at Technical University Dresden, Dresden, Germany.
⁶ Faculty of Health Sciences Brandenburg, joint Faculty of the University of Potsdam, the Brandenburg Medical School Theodor Fontane and the Brandenburg University of Technology Cottbus, Senftenberg, Germany; Medical Sociology and Psychobiology, University of Potsdam, Potsdam, Germany.
⁷ University Outpatient Clinic, Centre of Sports Medicine, University of Potsdam, Potsdam, Germany.
⁸ University Outpatient Clinic, Centre of Sports Medicine, University of Potsdam, Potsdam, Germany; Department of Therapy Sciences/Physiotherapy, University of Applied Sciences for Sports and Management, Potsdam, Germany.
⁹ Institute of Occupational, Social and Environmental Medicine, Goethe University Frankfurt, Frankfurt, Germany. Electronic address: niederer@sport.uni-frankfurt.de.

PMID: 39756772
DOI: 10.1016/j.apmr.2024.12.015

Abstract

Objective: To identify predictors of adherence in supervised and self-administered exercise interventions for individuals with low back pain.

Design: Cohort study.

Setting: Rehabilitation.

Participants: This preplanned reanalysis within the Medicine in Spine Exercise Network included 1511 participants with low back pain (57% female, mean age 40.9 years, SD ±14 years).

Interventions: Participants underwent an initial 3-week supervised phase of sensorimotor exercises, followed by a 9-week self-administered phase.

Main outcome measures: Biological, psychological, and social factors potentially impacting training adherence were evaluated. During the supervised phase, adherence was tracked through a standardized training log. During the self-administered phase, adherence was monitored via a diary, with adherence calculated as the percentage of scheduled versus completed sessions. Adherence was analyzed both as an absolute percentage and as a dichotomized variable (adherent vs nonadherent, with a 70% adherence cut-off). Predictors for adherence were identified using Gradient Boosting Machines and Random Forests (R package caret). Seventy percent of the observations were used for training, whereas 30% were retained as a hold-out test-set.

Results: The average overall adherence was 64% (±31%), with 81% (±28%) adherence during the supervised phase and 58% (±39%) in the self-administered phase. The root mean square error for the test-set ranged from 36.2 (R²=0.18, self-administered phase) to 19.3 (R²=0.47, supervised phase); prediction accuracy for dichotomized models was between 64% and 83%. Predictors of low to intermediate adherence included poorer baseline postural control, decline in exercise levels, and fluctuations in pain intensity (both increases and decreases).

Conclusion: Identified predictors could aid in recognizing individuals at higher risk for nonadherence in low back pain exercise therapy settings.

Keywords: Compliance; Determinants; Exercise; Individual patient data; LBP; Physical therapy; Rehabilitation; Stabilization big data; Training adherence.