Skip to main content

A decision support system for self-management of low back pain

Periodic Reporting for period 3 - selfBACK (A decision support system for self-management of low back pain)

Reporting period: 2018-07-01 to 2019-12-31

The recent global burden of disease study showed 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. LBP is the fourth most common diagnosis seen in primary care (after upper respiratory infection, hypertension, and coughing). Self-management in the form of physical activity and exercise programs constitutes the core component in the management of non-specific LBP; however, adherence to a self-management plan is challenging for most individuals due to lack of feedback and reinforcement. In this project, we have developed a decision support system (DSS) - SELFBACK - to be used by the individual him/herself to facilitate, improve and reinforce self-management of LBP. Specifically, SELFBACK is designed to assist the individual in deciding and reinforcing the appropriate actions to manage own LBP after consulting a health care professional. The decision support is conveyed to the individual via a smartphone app in the form of advice for self-management. The advice is tailored 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. The second part of the project is evaluating the effectiveness of SELFBACK in an international multi-centre randomized controlled trial (RCT) using pain-related disability as primary outcome. The RCT targets care-seeking individuals in primary care with non-specific LBP as their main health problem. Process evaluation will be carried out as an integrated part of the trial to document the implementation and map the individuals’ satisfaction with SELFBACK. A business plan with a targeted commercialization strategy is being developed to transfer the SELFBACK technology into the market.
The first milestone of the project – completion of the design phase of the SELFBACK app – was set and achieved in month 6. This milestone included a literature review, collecting relevant data from external resources, and the user interface design. Moreover, the project infrastructure has been set up and the first version of the data management plan is completed. In the reporting period, the beneficiaries started working towards the second milestone that is due in month 18. For this milestone the basic integration infrastructure is in place and the first completed components are available, including a model for physical activity recognition, a feature extraction algorithm, similarity measures as part of the case-based reasoning system, specification for the mobile app, demonstration of the web-based questionnaire. In the period from month 18 to month 30, the focus has been on implementing the decision support system and the accompanying app. This work included documentation on the case structure, a report on scaleable query processing, a definition of the user intervention modelling framework, a demonstrator of the integrated case-based reasoning system, a software component demonstration of the explanation engine, an application programming interface guide for back-end communication, a first version of smartphone SELFBACK application on iOS, a demonstration of the final connected SELFBACK mobile application on iOS and Android, a demonstration of web and mobile software interacting with connected devices such as a wristband that monitors patient activities, and a demonstration of localized software in multiple languages. Furthermore, the planning of the pilot and randomized controlled trials has started, and a complete protocol has been developed. The necessary ethics approvals for the feasibility studies, pilot study and the randomised controlled trial has been obtained. Finally, a business plan for exploitation of selected results has been developed.
During the third reporting period the project first focused on completing the technical development, which was achieved with the third milestone of the project – the final version of SELFBACK – in M33. This milestone included the documentation on the case structure, secure case storage and population, the scalable query processing, the predictive monitoring software components, the integrated CBR system, including a rule engine and explanation engine. Furthermore, all aspects of the user interaction around the SELFBACK intervention for the RCT was completed and adapted to the relevant languages (English, Danish and Norwegian). Finally, the preparations for the RCT were completed and the exploitation strategy was set.
Between M33 – M48, the work continued focusing on further developments of the clinician dashboard. In preparation for the RCT, the pilot study was completed and the recruitment of patients for the RCT was initiated and completed. Furthermore, the process evaluation that is carried out in parallel with the RCT was initiated. All the remaining ethics approvals was obtained before the pilot and RCT were launched. Finally, in WP6, the focus has been on dissemination of results along with further exploitation of different alternatives for commercialisation of the SELFBACK technology.
The SELFBACK project targets the most common musculoskeletal disorder and the most significant contributor to disability in Europe. In a randomised controlled trial, we envisage that patients who use SELFBACK will have about 10% reduction in pain-related disability at 3 months’ follow-up compared to patients receiving treatment as usual. To achieve this, the SELFBACK system will be 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 self-management plan will be tailored to each patient by integrating case-based reasoning and a machine-learning component into the SELFBACK system. Case-based reasoning is a technology 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 will enable us to develop predictive models that can be used to tailor self-management plans for each individual patient. By providing tailored feedback, decision support and improved understanding of own LBP, SELFBACK will empower the patient to improve self-management and thereby reduce the risk of long-term disability. With SELFBACK, the patient will be equipped with a tool that is far beyond the state-of-the-art to facilitate, improve and reinforce self-management of non-specific LBP. Although the effectiveness of SELFBACK remains to be proven, the potential cost-benefit is without doubt substantial. We estimate that the total cost of using SELFBACK will range between 120-150 EUR per patient, including the app, the activity-detecting wristband, and brief education to enable safe use of SELFBACK. SELFBACK does not require direct medical supervision and can easily be made available for a large number of people, thereby resulting in a highly cost-effective use of resources.
selfBACK Logo