An Artificial Intelligence-Based App for Self-Management of Low Back and Neck Pain in Specialist Care: Process Evaluation From a Randomized Clinical Trial.

BACKGROUND: Self-management is endorsed in clinical practice guidelines for the care of musculoskeletal pain. In a randomized clinical trial, we tested the effectiveness of an artificial intelligence-based self-management app (selfBACK) as an adjunct to usual care for patients with low back and neck pain referred to specialist care. OBJECTIVE: This study is a process evaluation aiming to explore patients' engagement and experiences with the selfBACK app and specialist health care practitioners' views on adopting digital self-management tools in their clinical practice. METHODS: App usage analytics in the first 12 weeks were used to explore patients' engagement with the SELFBACK app. Among the 99 patients allocated to the SELFBACK interventions, a purposive sample of 11 patients (aged 27-75 years, 8 female) was selected for semistructured individual interviews based on app usage. Two focus group interviews were conducted with specialist health care practitioners (n=9). Interviews were analyzed using thematic analysis. RESULTS: Nearly one-third of patients never accessed the app, and one-third were low users. Three themes were identified from interviews with patients and health care practitioners: (1) overall impression of the app, where patients discussed the interface and content of the app, reported on usability issues, and described their app usage; (2) perceived value of the app, where patients and health care practitioners described the primary value of the app and its potential to supplement usual care; and (3) suggestions for future use, where patients and health care practitioners addressed aspects they believed would determine acceptance. CONCLUSIONS: Although the app's uptake was relatively low, both patients and health care practitioners had a positive opinion about adopting an app-based self-management intervention for low back and neck pain as an add-on to usual care. Both described that the app could reassure patients by providing trustworthy information, thus empowering them to take actions on their own. Factors influencing app acceptance and engagement, such as content relevance, tailoring, trust, and usability properties, were identified. TRIAL REGISTRATION: ClinicalTrials.gov NCT04463043; https://clinicaltrials.gov/study/NCT04463043.

A Machine Learning Model for Predicting Sleep and Wakefulness Based on Accelerometry, Skin Temperature and Contextual Information.

Purpose: Body-worn accelerometers are commonly used to estimate sleep duration in population-based studies. However, since accelerometry-based sleep/wake-scoring relies on detecting body movements, the prediction of sleep duration remains a challenge. The aim was to develop and evaluate the performance of a machine learning (ML) model to predict accelerometry-based sleep duration and to explore if this prediction can be improved by adding skin temperature data, circadian rhythm based on the estimated midpoint of sleep, and cyclic time features to the model. Patients and Methods: Twenty-nine adults (17 females), mean (SD) age 40.2 (15.0) years (range 17-70) participated in the study. Overnight polysomnography (PSG) was recorded in a sleep laboratory or at home along with body movement by two accelerometers with an embedded skin temperature sensor (AX3, Axivity, UK) positioned at the low back and thigh. The PSG scoring of sleep/wake was used as ground truth for training the ML model. Results: Based on pure accelerometer data input to the ML model, the specificity and sensitivity for predicting sleep/wake was 0.52 (SD 0.24) and 0.95 (SD 0.03), respectively. Adding skin temperature data and contextual information to the ML model improved the specificity to 0.72 (SD 0.20), while sensitivity remained unchanged at 0.95 (SD 0.05). Correspondingly, sleep overestimation was reduced from 54 min (228 min, limits of agreement range [LoAR]) to 19 min (154 min LoAR). Conclusion: An ML model can predict sleep/wake periods with excellent sensitivity and moderate specificity based on a dual-accelerometer set-up when adding skin temperature data and contextual information to the model.

Decision Support for Managing Common Musculoskeletal Pain Disorders: Development of a Case-Based Reasoning Application.

BACKGROUND: Common interventions for musculoskeletal pain disorders either lack evidence to support their use or have small to modest or short-term effects. Given the heterogeneity of patients with musculoskeletal pain disorders, treatment guidelines and systematic reviews have limited transferability to clinical practice. A problem-solving method in artificial intelligence, case-based reasoning (CBR), where new problems are solved based on experiences from past similar problems, might offer guidance in such situations. OBJECTIVE: This study aims to use CBR to build a decision support system for patients with musculoskeletal pain disorders seeking physiotherapy care. This study describes the development of the CBR system SupportPrim PT and demonstrates its ability to identify similar patients. METHODS: Data from physiotherapy patients in primary care in Norway were collected to build a case base for SupportPrim PT. We used the local-global principle in CBR to identify similar patients. The global similarity measures are attributes used to identify similar patients and consisted of prognostic attributes. They were weighted in terms of prognostic importance and choice of treatment, where the weighting represents the relevance of the different attributes. For the local similarity measures, the degree of similarity within each attribute was based on minimal clinically important differences and expert knowledge. The SupportPrim PT's ability to identify similar patients was assessed by comparing the similarity scores of all patients in the case base with the scores on an established screening tool (the short form Örebro Musculoskeletal Pain Screening Questionnaire [ÖMSPQ]) and an outcome measure (the Musculoskeletal Health Questionnaire [MSK-HQ]) used in musculoskeletal pain. We also assessed the same in a more extensive case base. RESULTS: The original case base contained 105 patients with musculoskeletal pain (mean age 46, SD 15 years; 77/105, 73.3% women). The SupportPrim PT consisted of 29 weighted attributes with local similarities. When comparing the similarity scores for all patients in the case base, one at a time, with the ÖMSPQ and MSK-HQ, the most similar patients had a mean absolute difference from the query patient of 9.3 (95% CI 8.0-10.6) points on the ÖMSPQ and a mean absolute difference of 5.6 (95% CI 4.6-6.6) points on the MSK-HQ. For both ÖMSPQ and MSK-HQ, the absolute score difference increased as the rank of most similar patients decreased. Patients retrieved from a more extensive case base (N=486) had a higher mean similarity score and were slightly more similar to the query patients in ÖMSPQ and MSK-HQ compared with the original smaller case base. CONCLUSIONS: This study describes the development of a CBR system, SupportPrim PT, for musculoskeletal pain in primary care. The SupportPrim PT identified similar patients according to an established screening tool and an outcome measure for patients with musculoskeletal pain.

Acceptance and use of a clinical decision support system in musculoskeletal pain disorders - the SupportPrim project.

BACKGROUND: We have developed a clinical decision support system (CDSS) based on methods from artificial intelligence to support physiotherapists and patients in the decision-making process of managing musculoskeletal (MSK) pain disorders in primary care. The CDSS finds the most similar successful patients from the past to give treatment recommendations for a new patient. Using previous similar patients with successful outcomes to advise treatment moves management of MSK pain patients from one-size fits all recommendations to more individually tailored treatment. This study aimed to summarise the development and explore the acceptance and use of the CDSS for MSK pain patients. METHODS: This qualitative study was carried out in the Norwegian physiotherapy primary healthcare sector between October and November 2020, ahead of a randomised controlled trial. We included four physiotherapists and three of their patients, in total 12 patients, with musculoskeletal pain in the neck, shoulder, back, hip, knee or complex pain. We conducted semi-structured telephone interviews with all participants. The interviews were analysed using the Framework Method. RESULTS: Overall, both the physiotherapists and patients found the system acceptable and usable. Important findings from the analysis of the interviews were that the CDSS was valued as a preparatory and exploratory tool, facilitating the therapeutic relationship. However, the physiotherapists used the system mainly to support their previous and current practice rather than involving patients to a greater extent in decisions and learning from previous successful patients. CONCLUSIONS: The CDSS was acceptable and usable to both the patients and physiotherapists. However, the system appeared not to considerably influence the physiotherapists' clinical reasoning and choice of treatment based on information from most similar successful patients. This could be due to a smaller than optimal number of previous patients in the CDSS or insufficient clinical implementation. Extensive training of physiotherapists should not be underestimated to build understanding and trust in CDSSs.

Can the bias of self-reported sitting time be corrected? A statistical model validation study based on data from 23 993 adults in the Norwegian HUNT study.

BACKGROUND: Despite apparent shortcomings such as measurement error and low precision, self-reported sedentary time is still widely used in surveillance and research. The aim of this study was threefold; (i) to examine the agreement between self-reported and device-measured sitting time in a general adult population; (ii), to examine to what extent demographics, lifestyle factors, long-term health conditions, physical work demands, and educational level is associated with measurement bias; and (iii), to explore whether correcting for factors associated with bias improves the prediction of device-measured sitting time based on self-reported sitting time. METHODS: A statistical validation model study based on data from 23 993 adults in the Trøndelag Health Study (HUNT4), Norway. Participants reported usual sitting time on weekdays using a single-item questionnaire and wore two AX3 tri-axial accelerometers on the thigh and low back for an average of 3.8 (standard deviation [SD] 0.7, range 1-5) weekdays to determine their sitting time. Statistical validation was performed by iteratively adding all possible combinations of factors associated with bias between self-reported and device-measured sitting time in a multivariate linear regression. We randomly selected 2/3 of the data (n = 15 995) for model development and used the remaining 1/3 (n = 7 998) to evaluate the model. RESULTS: Mean (SD) self-reported and device-measured sitting time were 6.8 (2.9) h/day and 8.6 (2.2) h/day, respectively, corresponding to a mean difference of 1.8 (3.1) h/day. Limits of agreement ranged from - 8.0 h/day to 4.4 h/day. The discrepancy between the measurements was characterized by a proportional bias with participants device-measured to sit less overestimating their sitting time and participants device-measured to sit more underestimating their sitting time. The crude explained variance of device-measured sitting time based on self-reported sitting time was 10%. This improved to 24% when adding age, body mass index and physical work demands to the model. Adding sex, lifestyle factors, educational level, and long-term health conditions to the model did not improve the explained variance. CONCLUSIONS: Self-reported sitting time had low validity and including a range of factors associated with bias in self-reported sitting time only marginally improved the prediction of device-measured sitting time.

Effect of an Artificial Intelligence-Based Self-Management App on Musculoskeletal Health in Patients With Neck and/or Low Back Pain Referred to Specialist Care: A Randomized Clinical Trial.

Importance: Self-management is a key element in the care of persistent neck and low back pain. Individually tailored self-management support delivered via a smartphone app in a specialist care setting has not been tested. Objective: To determine the effect of individually tailored self-management support delivered via an artificial intelligence-based app (SELFBACK) adjunct to usual care vs usual care alone or nontailored web-based self-management support (e-Help) on musculoskeletal health. Design, Setting, and Participants: This randomized clinical trial recruited adults 18 years or older with neck and/or low back pain who had been referred to and accepted on a waiting list for specialist care at a multidisciplinary hospital outpatient clinic for back, neck, and shoulder rehabilitation. Participants were enrolled from July 9, 2020, to April 29, 2021. Of 377 patients assessed for eligibility, 76 did not complete the baseline questionnaire, and 7 did not meet the eligibility criteria (ie, did not own a smartphone, were unable to take part in exercise, or had language barriers); the remaining 294 patients were included in the study and randomized to 3 parallel groups, with follow-up of 6 months. Interventions: Participants were randomly assigned to receive app-based individually tailored self-management support in addition to usual care (app group), web-based nontailored self-management support in addition to usual care (e-Help group), or usual care alone (usual care group). Main Outcomes and Measures: The primary outcome was change in musculoskeletal health measured by the Musculoskeletal Health Questionnaire (MSK-HQ) at 3 months. Secondary outcomes included change in musculoskeletal health measured by the MSK-HQ at 6 weeks and 6 months and pain-related disability, pain intensity, pain-related cognition, and health-related quality of life at 6 weeks, 3 months, and 6 months. Results: Among 294 participants (mean [SD] age, 50.6 [14.9] years; 173 women [58.8%]), 99 were randomized to the app group, 98 to the e-Help group, and 97 to the usual care group. At 3 months, 243 participants (82.7%) had complete data on the primary outcome. In the intention-to-treat analysis at 3 months, the adjusted mean difference in MSK-HQ score between the app and usual care groups was 0.62 points (95% CI, -1.66 to 2.90 points; P = .60). The adjusted mean difference between the app and e-Help groups was 1.08 points (95% CI, -1.24 to 3.41 points; P = .36). Conclusions and Relevance: In this randomized clinical trial, individually tailored self-management support delivered via an artificial intelligence-based app adjunct to usual care was not significantly more effective in improving musculoskeletal health than usual care alone or web-based nontailored self-management support in patients with neck and/or low back pain referred to specialist care. Further research is needed to investigate the utility of implementing digitally supported self-management interventions in the specialist care setting and to identify instruments that capture changes in self-management behavior. Trial Registration: ClinicalTrials.gov Identifier: NCT04463043.

SupportPrim-a computerized clinical decision support system for stratified care for patients with musculoskeletal pain complaints in general practice: study protocol for a randomized controlled trial.

BACKGROUND: Musculoskeletal disorders represented 149 million years lived with disability world-wide in 2019 and are the main cause of years lived with disability worldwide. Current treatment recommendations are based on "one-size fits all" principle, which does not take into account the large degree of biopsychosocial heterogeneity in this group of patients. To compensate for this, we developed a stratified care computerized clinical decision support system for general practice based on patient biopsychosocial phenotypes; furthermore, we added personalized treatment recommendations based on specific patient factors to the system. In this study protocol, we describe the randomized controlled trial for evaluating the effectiveness of computerized clinical decision support system for stratified care for patients with common musculoskeletal pain complaints in general practice. The aim of this study is to test the effect of a computerized clinical decision support system for stratified care in general practice on subjective patient outcome variables compared to current care. METHODS: We will perform a cluster-randomized controlled trial with 44 general practitioners including 748 patients seeking their general practitioner due to pain in the neck, back, shoulder, hip, knee, or multisite. The intervention group will use the computerized clinical decision support system, while the control group will provide current care for their patients. The primary outcomes assessed at 3 months are global perceived effect and clinically important improvement in function measured by the Patient-Specific Function Scale (PSFS), while secondary outcomes include change in pain intensity measured by the Numeric Rating Scale (0-10), health-related quality of life (EQ-5D), general musculoskeletal health (MSK-HQ), number of treatments, use of painkillers, sick-leave grading and duration, referral to secondary care, and use of imaging. DISCUSSION: The use of biopsychosocial profile to stratify patients and implement it in a computerized clinical decision support system for general practitioners is a novel method of providing decision support for this patient group. The study aim to recruit patients from May 2022 to March 2023, and the first results from the study will be available late 2023. TRIAL REGISTRATION: The trial is registered in ISRCTN 11th of May 2022: 14,067,965.

Validation of an Activity Type Recognition Model Classifying Daily Physical Behavior in Older Adults: The HAR70+ Model.

Activity monitoring combined with machine learning (ML) methods can contribute to detailed knowledge about daily physical behavior in older adults. The current study (1) evaluated the performance of an existing activity type recognition ML model (HARTH), based on data from healthy young adults, for classifying daily physical behavior in fit-to-frail older adults, (2) compared the performance with a ML model (HAR70+) that included training data from older adults, and (3) evaluated the ML models on older adults with and without walking aids. Eighteen older adults aged 70-95 years who ranged widely in physical function, including usage of walking aids, were equipped with a chest-mounted camera and two accelerometers during a semi-structured free-living protocol. Labeled accelerometer data from video analysis was used as ground truth for the classification of walking, standing, sitting, and lying identified by the ML models. Overall accuracy was high for both the HARTH model (91%) and the HAR70+ model (94%). The performance was lower for those using walking aids in both models, however, the overall accuracy improved from 87% to 93% in the HAR70+ model. The validated HAR70+ model contributes to more accurate classification of daily physical behavior in older adults that is essential for future research.

External validation of prediction models for patient-reported outcome measurements collected using the selfBACK mobile app.

BACKGROUND: External validation is essential in examining the disparities in the training and validation cohorts during the development of prediction models, especially when the application domain is healthcare-oriented. Currently, the use of prediction models in healthcare research aimed at utilising the under-explored potential of patient-reported outcome measurements (PROMs) is limited, and few are validated using external datasets. OBJECTIVE: To validate the machine learning prediction models developed in our previous work [29] for predicting four pain-related patient-reported outcomes from the selfBACK clinical trial datasets. METHODS: We evaluate the validity of three pre-trained prediction models based on three methods- Case-Based Reasoning, Support Vector Regression, and XGBoost Regression-using an external dataset that contains PROMs collected from patients with non-specific neck and or low back pain using the selfBACK mobile application. RESULTS: Overall, the predictive power was low, except for prediction of one of the outcomes. The results indicate that while the predictions are far from immaculate in either case, the models show ability to generalise and predict outcomes for a new dataset. CONCLUSION: External validation of the prediction models presents modest results and highlights the individual differences and need for external validation of prediction models in clinical settings. There is need for further development in this area of machine learning application and patient-centred care.

Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes.

BACKGROUND: Patient-reported outcome measurements (PROMs) are commonly used in clinical practice to support clinical decision making. However, few studies have investigated machine learning methods for predicting PROMs outcomes and thereby support clinical decision making. OBJECTIVE: This study investigates to what extent different machine learning methods, applied to two different PROMs datasets, can predict outcomes among patients with non-specific neck and/or low back pain. METHODS: Using two datasets consisting of PROMs from (1) care-seeking low back pain patients in primary care who participated in a randomized controlled trial, and (2) patients with neck and/or low back pain referred to multidisciplinary biopsychosocial rehabilitation, we present data science methods for data prepossessing and evaluate selected regression and classification methods for predicting patient outcomes. RESULTS: The results show that there is a potential for machine learning to predict and classify PROMs. The prediction models based on baseline measurements perform well, and the number of predictors can be reduced, which is an advantage for implementation in decision support scenarios. The classification task shows that the dataset does not contain all necessary predictors for the care type classification. Overall, the work presents generalizable machine learning pipelines that can be adapted to other PROMs datasets. CONCLUSION: This study demonstrates the potential of PROMs in predicting short-term patient outcomes. Our results indicate that machine learning methods can be used to exploit the predictive value of PROMs and thereby support clinical decision making, given that the PROMs hold enough predictive power.

Performance of machine learning models in estimation of ground reaction forces during balance exergaming.

BACKGROUND: Balance training exercise games (exergames) are a promising tool for reducing fall risk in elderly. Exergames can be used for in-home guided exercise, which greatly increases availability and facilitates independence. Providing biofeedback on weight-shifting during in-home balance exercise improves exercise efficiency, but suitable equipment for measuring weight-shifting is lacking. Exergames often use kinematic data as input for game control. Being able to useg such data to estimate weight-shifting would be a great advantage. Machine learning (ML) models have been shown to perform well in weight-shifting estimation in other settings. Therefore, the aim of this study was to investigate the performance of ML models in estimation of weight-shifting during exergaming using kinematic data. METHODS: Twelve healthy older adults (mean age 72 (± 4.2), 10 F) played a custom exergame that required repeated weight-shifts. Full-body 3D motion capture (3DMoCap) data and standard 2D digital video (2D-DV) was recorded. Weight shifting was directly measured by 3D ground reaction forces (GRF) from force plates, and estimated using a linear regression model, a long-short term memory (LSTM) model and a decision tree model (XGBoost). Performance was evaluated using coefficient of determination ([Formula: see text]) and root mean square error (RMSE). RESULTS: Results from estimation of GRF components using 3DMoCap data show a mean (± 1SD) RMSE (% total body weight, BW) of the vertical GRF component ([Formula: see text]) of 4.3 (2.5), 11.1 (4.5), and 11.0 (4.7) for LSTM, XGBoost and LinReg, respectively. Using 2D-DV data, LSTM and XGBoost achieve mean RMSE (± 1SD) in [Formula: see text] estimation of 10.7 (9.0) %BW and 19.8 (6.4) %BW, respectively. [Formula: see text] was [Formula: see text] for the LSTM in the [Formula: see text] component using 3DMoCap data, and [Formula: see text] using 2D-DV data. For XGBoost, [Formula: see text] [Formula: see text] was [Formula: see text] using 3DMoCap data, and [Formula: see text] using 2D-DV data. CONCLUSION: This study demonstrates that an LSTM model can estimate 3-dimensional GRF components using 2D kinematic data extracted from standard 2D digital video cameras. The [Formula: see text] component is estimated more accurately than [Formula: see text] and [Formula: see text] components, especially when using 2D-DV data. Weight-shifting performance during exergaming can thus be extracted using kinematic data only, which can enable effective independent in-home balance exergaming.

HARTH: A Human Activity Recognition Dataset for Machine Learning.

Existing accelerometer-based human activity recognition (HAR) benchmark datasets that were recorded during free living suffer from non-fixed sensor placement, the usage of only one sensor, and unreliable annotations. We make two contributions in this work. First, we present the publicly available Human Activity Recognition Trondheim dataset (HARTH). Twenty-two participants were recorded for 90 to 120 min during their regular working hours using two three-axial accelerometers, attached to the thigh and lower back, and a chest-mounted camera. Experts annotated the data independently using the camera's video signal and achieved high inter-rater agreement (Fleiss' Kappa =0.96). They labeled twelve activities. The second contribution of this paper is the training of seven different baseline machine learning models for HAR on our dataset. We used a support vector machine, k-nearest neighbor, random forest, extreme gradient boost, convolutional neural network, bidirectional long short-term memory, and convolutional neural network with multi-resolution blocks. The support vector machine achieved the best results with an F1-score of 0.81 (standard deviation: ±0.18), recall of 0.85±0.13, and precision of 0.79±0.22 in a leave-one-subject-out cross-validation. Our highly professional recordings and annotations provide a promising benchmark dataset for researchers to develop innovative machine learning approaches for precise HAR in free living.

Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting.

Data-driven forecasts of air quality have recently achieved more accurate short-term predictions. However, despite their success, most of the current data-driven solutions lack proper quantifications of model uncertainty that communicate how much to trust the forecasts. Recently, several practical tools to estimate uncertainty have been developed in probabilistic deep learning. However, there have not been empirical applications and extensive comparisons of these tools in the domain of air quality forecasts. Therefore, this work applies state-of-the-art techniques of uncertainty quantification in a real-world setting of air quality forecasts. Through extensive experiments, we describe training probabilistic models and evaluate their predictive uncertainties based on empirical performance, reliability of confidence estimate, and practical applicability. We also propose improving these models using "free" adversarial training and exploiting temporal and spatial correlation inherent in air quality data. Our experiments demonstrate that the proposed models perform better than previous works in quantifying uncertainty in data-driven air quality forecasts. Overall, Bayesian neural networks provide a more reliable uncertainty estimate but can be challenging to implement and scale. Other scalable methods, such as deep ensemble, Monte Carlo (MC) dropout, and stochastic weight averaging-Gaussian (SWAG), can perform well if applied correctly but with different tradeoffs and slight variations in performance metrics. Finally, our results show the practical impact of uncertainty estimation and demonstrate that, indeed, probabilistic models are more suitable for making informed decisions.

Individually tailored self-management app-based intervention (selfBACK) versus a self-management web-based intervention (e-Help) or usual care in people with low back and neck pain referred to secondary care: protocol for a multiarm randomised clinical trial.

INTRODUCTION: Low back pain (LBP) and neck pain (NP) are common and costly conditions. Self-management is a key element in the care of persistent LBP and NP. Artificial intelligence can be used to support and tailor self-management interventions, but their effectiveness needs to be ascertained. The aims of this trial are (1) to evaluate the effectiveness of an individually tailored app-based self-management intervention (selfBACK) adjunct to usual care in people with LBP and/or NP in secondary care compared with usual care only, and (2) to compare the effectiveness of selfBACK with a web-based self-management intervention without individual tailoring (e-Help). METHODS AND ANALYSIS: This is a randomised, assessor-blind clinical trial with three parallel arms: (1) selfBACK app adjunct to usual care; (2) e-Help website adjunct to usual care and (3) usual care only. Patients referred to St Olavs Hospital, Trondheim (Norway) with LBP and/or NP and accepted for assessment/treatment at the multidisciplinary outpatient clinic for back or neck rehabilitation are invited to the study. Eligible and consenting participants are randomised to one of the three arms with equal allocation ratio. We aim to include 279 participants (93 in each arm). Outcome variables are assessed at baseline (before randomisation) and at 6-week, 3-month and 6-month follow-up. The primary outcome is musculoskeletal health measured by the Musculoskeletal Health Questionnaire at 3 months. A mixed-methods process evaluation will document patients' and clinicians' experiences with the interventions. A health economic evaluation will estimate the cost-effectiveness of both interventions' adjunct to usual care. ETHICS AND DISSEMINATION: The trial is approved by the Regional Committee for Medical and Health Research Ethics in Central Norway (Ref. 2019/64084). The results of the trial will be published in peer-review journals and presentations at national and international conferences relevant to this topic. TRIAL REGISTRATION NUMBER: NCT04463043.

Effectiveness of App-Delivered, Tailored Self-management Support for Adults With Lower Back Pain-Related Disability: A selfBACK Randomized Clinical Trial.

Importance: Lower back pain (LBP) is a prevalent and challenging condition in primary care. The effectiveness of an individually tailored self-management support tool delivered via a smartphone app has not been rigorously tested. Objective: To investigate the effectiveness of selfBACK, an evidence-based, individually tailored self-management support system delivered through an app as an adjunct to usual care for adults with LBP-related disability. Design, Setting, and Participants: This randomized clinical trial with an intention-to-treat data analysis enrolled eligible individuals who sought care for LBP in a primary care or an outpatient spine clinic in Denmark and Norway from March 8 to December 14, 2019. Participants were 18 years or older, had nonspecific LBP, scored 6 points or higher on the Roland-Morris Disability Questionnaire (RMDQ), and had a smartphone and access to email. Interventions: The selfBACK app provided weekly recommendations for physical activity, strength and flexibility exercises, and daily educational messages. Self-management recommendations were tailored to participant characteristics and symptoms. Usual care included advice or treatment offered to participants by their clinician. Main Outcomes and Measures: Primary outcome was the mean difference in RMDQ scores between the intervention group and control group at 3 months. Secondary outcomes included average and worst LBP intensity levels in the preceding week as measured on the numerical rating scale, ability to cope as assessed with the Pain Self-Efficacy Questionnaire, fear-avoidance belief as assessed by the Fear-Avoidance Beliefs Questionnaire, cognitive and emotional representations of illness as assessed by the Brief Illness Perception Questionnaire, health-related quality of life as assessed by the EuroQol-5 Dimension questionnaire, physical activity level as assessed by the Saltin-Grimby Physical Activity Level Scale, and overall improvement as assessed by the Global Perceived Effect scale. Outcomes were measured at baseline, 6 weeks, 3 months, 6 months, and 9 months. Results: A total of 461 participants were included in the analysis; the population had a mean [SD] age of 47.5 [14.7] years and included 255 women (55%). Of these participants, 232 were randomized to the intervention group and 229 to the control group. By the 3-month follow-up, 399 participants (87%) had completed the trial. The adjusted mean difference in RMDQ score between the 2 groups at 3 months was 0.79 (95% CI, 0.06-1.51; P = .03), favoring the selfBACK intervention. The percentage of participants who reported a score improvement of at least 4 points on the RMDQ was 52% in the intervention group vs 39% in the control group (adjusted odds ratio, 1.76; 95% CI, 1.15-2.70; P = .01). Conclusions and Relevance: Among adults who sought care for LBP in a primary care or an outpatient spine clinic, those who used the selfBACK system as an adjunct to usual care had reduced pain-related disability at 3 months. The improvement in pain-related disability was small and of uncertain clinical significance. Process evaluation may provide insights into refining the selfBACK app to increase its effectiveness. Trial Registration: ClinicalTrials.gov Identifier: NCT03798288.

From a Low-Cost Air Quality Sensor Network to Decision Support Services: Steps towards Data Calibration and Service Development.

Air pollution is a widespread problem due to its impact on both humans and the environment. Providing decision makers with artificial intelligence based solutions requires to monitor the ambient air quality accurately and in a timely manner, as AI models highly depend on the underlying data used to justify the predictions. Unfortunately, in urban contexts, the hyper-locality of air quality, varying from street to street, makes it difficult to monitor using high-end sensors, as the cost of the amount of sensors needed for such local measurements is too high. In addition, development of pollution dispersion models is challenging. The deployment of a low-cost sensor network allows a more dense cover of a region but at the cost of noisier sensing. This paper describes the development and deployment of a low-cost sensor network, discussing its challenges and applications, and is highly motivated by talks with the local municipality and the exploration of new technologies to improve air quality related services. However, before using data from these sources, calibration procedures are needed to ensure that the quality of the data is at a good level. We describe our steps towards developing calibration models and how they benefit the applications identified as important in the talks with the municipality.

Comparison of a Deep Learning-Based Pose Estimation System to Marker-Based and Kinect Systems in Exergaming for Balance Training.

Using standard digital cameras in combination with deep learning (DL) for pose estimation is promising for the in-home and independent use of exercise games (exergames). We need to investigate to what extent such DL-based systems can provide satisfying accuracy on exergame relevant measures. Our study assesses temporal variation (i.e., variability) in body segment lengths, while using a Deep Learning image processing tool (DeepLabCut, DLC) on two-dimensional (2D) video. This variability is then compared with a gold-standard, marker-based three-dimensional Motion Capturing system (3DMoCap, Qualisys AB), and a 3D RGB-depth camera system (Kinect V2, Microsoft Inc). Simultaneous data were collected from all three systems, while participants (N = 12) played a custom balance training exergame. The pose estimation DLC-model is pre-trained on a large-scale dataset (ImageNet) and optimized with context-specific pose annotated images. Wilcoxon's signed-rank test was performed in order to assess the statistical significance of the differences in variability between systems. The results showed that the DLC method performs comparably to the Kinect and, in some segments, even to the 3DMoCap gold standard system with regard to variability. These results are promising for making exergames more accessible and easier to use, thereby increasing their availability for in-home exercise.

App-Delivered Self-Management Intervention Trial selfBACK for People With Low Back Pain: Protocol for Implementation and Process Evaluation.

BACKGROUND: Implementation and process evaluation is vital for understanding how interventions function in different settings, including if and why interventions have different effects or do not work at all. OBJECTIVE: This paper presents the protocol for an implementation and process evaluation embedded in a multicenter randomized controlled trial conducted in Denmark and Norway (the selfBACK project). selfBACK is a data-driven decision support system that provides participants with weekly self-management plans for low back pain. These plans are delivered through a smartphone app and tailored to individual participants by using case-based reasoning methodology. In the trial, we compare selfBACK in addition to usual care with usual care alone. METHODS: The aim of this study is to conduct a convergent mixed-methods implementation and process evaluation of the selfBACK app by following the reach, effectiveness, adoption, implementation, and maintenance framework. We will evaluate the process of implementing selfBACK and investigate how participants use the intervention in daily life. The evaluation will also cover the reach of the intervention, health care provider willingness to adopt it, and participant satisfaction with the intervention. We will gather quantitative measures by questionnaires and measures of data analytics on app use and perform a qualitative exploration of the implementation using semistructured interviews theoretically informed by normalization process theory. Data collection will be conducted between March 2019 and October 2020. RESULTS: The trial opened for recruitment in February 2019. This mixed-methods implementation and evaluation study is embedded in the randomized controlled trial and will be collecting data from March 2019 to October 2020; dissemination of trial results is planned thereafter. The results from the process evaluation are expected 2021-2022. CONCLUSIONS: This study will provide a detailed understanding of how self-management of low back pain can be improved and how a digital health intervention can be used as an add-on to usual care to support patients to self-manage their low back pain. We will provide knowledge that can be used to explore the possibilities of extending the generic components of the selfBACK system and key drivers that could be of use in other conditions and diseases where self-management is an essential prevention or treatment strategy. TRIAL REGISTRATION: ClinicalTrials.gov NCT03798288; https://www.clinicaltrials.gov/ct2/show/NCT03798288. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/20308.

Usability and Acceptability of an App (SELFBACK) to Support Self-Management of Low Back Pain: Mixed Methods Study.

BACKGROUND: Self-management is the key recommendation for managing nonspecific low back pain (LBP). However, there are well-documented barriers to self-management; therefore, methods of facilitating adherence are required. Smartphone apps are increasingly being used to support self-management of long-term conditions such as LBP. OBJECTIVE: The aim of this study was to assess the usability and acceptability of the SELFBACK smartphone app, designed to support and facilitate self-management of non-specific LBP. The app provides weekly self-management plans, comprising physical activity, strength and flexibility exercises, and patient education. The plans are tailored to the patient's characteristics and symptom progress by using case-based reasoning methodology. METHODS: The study was carried out in 2 stages using a mixed-methods approach. All participants undertook surveys, and semistructured telephone interviews were conducted with a subgroup of participants. Stage 1 assessed an app version with only the physical activity component and a web questionnaire that collects information necessary for tailoring the self-management plans. The physical activity component included monitoring of steps recorded by a wristband, goal setting, and a scheme for sending personalized, timely, and motivational notifications to the user's smartphone. Findings from Stage 1 were used to refine the app and inform further development. Stage 2 investigated an app version that incorporated 3 self-management components (physical activity, exercises, and education). A total of 16 participants (age range 23-71 years) with ongoing or chronic nonspecific LBP were included in Stage 1, and 11 participants (age range 32-56 years) were included in Stage 2. RESULTS: In Stage 1, 15 of 16 participants reported that the baseline questionnaire was easy to answer, and 84% (13/16) found the completion time to be acceptable. Overall, participants were positive about the usability of the physical activity component but only 31% (5/16) found the app functions to be well integrated. Of the participants, 90% (14/16) were satisfied with the notifications, and they were perceived as being personalized (12/16, 80%). In Stage 2, all participants reported that the web questionnaire was easy to answer and the completion time acceptable. The physical activity and exercise components were rated useful by 80% (8/10), while 60% (6/10) rated the educational component useful. Overall, participants were satisfied with the usability of the app; however, only 50% (5/10) found the functions to be well integrated, and 20% (2/10) found them to be inconsistent. Overall, 80% (8/10) of participants reported it to be useful for self-management. The interviews largely reinforced the survey findings in both stages. CONCLUSIONS: This study has demonstrated that participants considered the SELFBACK app to be acceptable and usable and that they thought it would be useful for supporting self-management of LBP. However, we identified some limitations and suggestions useful to guide further development of the SELFBACK app and other mobile health interventions.