Periodic Reporting for period 4 - selfBACK (A decision support system for self-management of low back pain) Reporting period: 2020-01-01 to 2021-03-31 Summary of the context and overall objectives of the project The global burden of disease study has shown that low back pain (LBP) is the most significant contributor to disability in Europe. Most individuals seen in primary care with LBP have non-specific LBP (≥85%), i.e. pain that cannot reliably be attributed to a specific disease or pathology. Evidence-based self-management support, tailored to the needs and abilities of the individual patient, is recommended as part of first line treatment for non-specific LBP. However, self-management is challenging for most patients without feedback and reinforcement. The overall objective of the project was to utilise smartphone technology along with knowledge-driven artificial intelligence (AI), to develop an innovative decision support system - SELFBACK – that can be used by the patient him/herself to facilitate, improve and reinforce self-management of LBP. The self-management support is conveyed to the patient via a smartphone app and individually tailored to each patient according to symptom state, symptom progression, the individual’s goal-setting, and a range of person characteristics, including information from a physical activity-detecting wristband worn by the individual. Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far The effectiveness of SELFBACK was evaluated in an international multi-centre randomized controlled trial (RCT) using pain-related disability as primary outcome. The RCT targeted care-seeking patients in primary care with non-specific LBP. A process evaluation was carried out as an integrated part of the trial to document the implementation and map the patients experiences with SELFBACK as well as the clinicians’ views of the SELFBACK intervention. A total of 461 patients participated in the trial and were randomised to receive self-management support in addition to usual care (SELFBACK) or usual care alone. The process evaluation indicated that the SELFBACK app was very well received among the patients, and clinicians were in general very positive on the prospect of integrating such tools in their clinical practice. A business plan with a targeted commercialization strategy has been developed, describing different alternatives for transferring the SELFBACK technology into the European market. A company (SelfBack APS) has been established in Denmark, projected to license, and commercialise the SELFBACK technology. With SELFBACK, the patient is equipped with a tool that is far beyond the state-of-the-art to facilitate, improve and reinforce self-management of non-specific LBP. The SELFBACK system was developed and designed to improve the participation of the patient in the care process, thereby enhancing motivation and the perception of ‘usefulness’ by the patient. The weekly self-management plans are tailored to each patient by integrating case-based reasoning and a machine-learning component into the SELFBACK system. Case-based reasoning is an AI methodology that uses information about successful past cases of similar patients to optimize advice for self-management for new patients. The use of case-based reasoning and machine learning enabled the development of predictive models used for the tailoring of self-management plans for each individual patient. By providing tailored feedback, decision support and improved understanding of their own LBP, SELFBACK empowers the patient to improve self-management and thereby reduce the risk of long-term disability. As SELFBACK does not require direct medical supervision and can easily be made available for many people, the potential cost-benefit is substantial. Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far) The effectiveness of SELFBACK was evaluated in an international multi-centre randomized controlled trial (RCT) using pain-related disability as primary outcome. The RCT targeted care-seeking patients in primary care with non-specific LBP. A process evaluation was carried out as an integrated part of the trial to document the implementation and map the patients experiences with SELFBACK as well as the clinicians’ views of the SELFBACK intervention. A total of 461 patients participated in the trial and were randomised to receive self-management support in addition to usual care (SELFBACK) or usual care alone. The results from the RCT showed that self-management support delivered via the SELFBACK app reduces LBP-related disability as compared to usual care alone. These findings indicate that evidence-based and individually tailored self-management support delivered via an AI-based app may be a viable and effective supplement to usual care to reduce pain-related disability. Furthermore, the process evaluation indicated that the SELFBACK app was very well received among the patients, and clinicians were in general very positive on the prospect of integrating such tools in their clinical practice. A business plan with a targeted commercialization strategy has been developed, describing different alternatives for transferring the SELFBACK technology into the European market. A company (SelfBack APS) has been established in Denmark, projected to license, and commercialise the SELFBACK technology. With SELFBACK, the patient is equipped with a tool that is far beyond the state-of-the-art to facilitate, improve and reinforce self-management of non-specific LBP. The SELFBACK system was developed and designed to improve the participation of the patient in the care process, thereby enhancing motivation and the perception of ‘usefulness’ by the patient. The weekly self-management plans are tailored to each patient by integrating case-based reasoning and a machine-learning component into the SELFBACK system. Case-based reasoning is an AI methodology that uses information about successful past cases of similar patients to optimize advice for self-management for new patients. The use of case-based reasoning and machine learning enabled the development of predictive models used for the tailoring of self-management plans for each individual patient. By providing tailored feedback, decision support and improved understanding of their own LBP, SELFBACK empowers the patient to improve self-management and thereby reduce the risk of long-term disability. As SELFBACK does not require direct medical supervision and can easily be made available for many people, the potential cost-benefit is substantial. selfBACK Logo
