Challenge
Neck and lower back pain are among the leading causes of disability worldwide and affect around 70% of adults at some point in their lives. They also contribute substantially to sickness absence, reduced productivity and healthcare costs. However, clinicians often lack sufficient evidence and patient-specific information to predict how a condition will develop, select the most appropriate treatment or support a timely return to work. Existing approaches frequently consider clinical symptoms in isolation, despite the influence of psychological, behavioural, biological, workplace and lifestyle factors.
Solutions
Back-Up developed digital tools and patient-specific prognostic models to support more personalised and efficient management of neck and lower back pain. The models combined clinical history and patient-reported outcomes with physical tests, biomarkers, musculoskeletal characteristics and psychological, behavioural, socioeconomic, workplace and lifestyle factors.
They were designed to predict pain, disability, physical function and time away from work in months following a clinical consultation. The project also developed platforms tailored to healthcare professionals, researchers, patients and occupational stakeholders. These tools supported risk stratification, treatment selection, rehabilitation, self-management and return-to-work planning. The models assessed more than 20 first-line treatments and generated personalised recommendations based on expected outcomes.
Results
Back-Up deliveded professional and research platforms alongside models for ealy risk stratification and for predicting pain, disability, phisical funtion and time off work at two and six months. The project also produced a methodological framework for managing neck and lower back pain in workers, evidence-based treatment recommendations and validation studies assessing the tools through retrospective, prospective and usability research.
By helping identify which patients require more intensive support, the Back-Up approach can improve treatment allocation while reducing unnecessary care and potential harm among people at lower risk. Its personalised recommendations can support better recovery, rehabilitation and return-to-work decisions, with the longer-term potential to improve patient well-being, reduce healthcare expenditure and limit productivity losses.