Developing Smartphone-Based Objective Assessments of Physical Function in Rheumatoid Arthritis Patients: The PARADE Study

Assessment of physical activity patterns in patients with rheumatoid arthritis using the UK Biobank

Measures of physical activity patterns that may characterize rheumatoid arthritis status were investigated, using actigraphy data from a large, prospective database study (UK Biobank). Population characterization identified 1080 individuals with rheumatoid arthritis who participated in accelerometer-measured physical activity data collection and met the eligibility criteria; these individuals were subsequently matched with 2160 non-rheumatoid arthritis controls. Raw actigraphy data were pre-processed to interpretable acceleration magnitude and general signal-based features were used to derive activity labels from a human activity recognition model. Qualitative assessment of average activity profiles indicated small differences between groups for activity in the first 5 hours of the day, engagement in moderate-to-vigorous activity, and evening sleep patterns. Of 145 metrics capturing different aspects of physical activity, 57 showed an ability to differentiate between participants with rheumatoid arthritis and non-rheumatoid arthritis controls, most notably activities related to moderate-to-vigorous activity, sleep and the ability to perform sustained activity, which remained different when adjusting for baseline imbalances. Objective measures derived from wrist-worn accelerometer data may be used to assess and quantify the impact of rheumatoid arthritis on daily activity and may reflect rheumatoid arthritis symptoms. This work represents an initial step towards the characterization of such impact. Importantly, this study offers a glimpse of the potential use of large-scale datasets to support the analysis of smaller clinical study datasets.

Digital health technologies to strengthen patient-centred outcome assessment in clinical trials in inflammatory arthritis

Common to all inflammatory arthritides, namely rheumatoid arthritis, psoriatic arthritis, axial spondyloarthritis, and juvenile idiopathic arthritis, is a potential for reduced mobility that manifests through joint pain, swelling, stiffness, and ultimately joint damage. Across these conditions, consensus has been reached on the need to capture outcomes related to mobility, such as functional capacity and physical activity, as core domains in randomised controlled trials. Existing endpoints within these core domains rely wholly on self-reported questionnaires that capture patients' perceptions of their symptoms and activities. These questionnaires are subjective, inherently vulnerable to recall bias, and do not capture the granularity of fluctuations over time. Several early adopters have integrated sensor-based digital health technology (DHT)-derived endpoints to measure physical function and activity in randomised controlled trials for conditions including Parkinson's disease, Duchenne's muscular dystrophy, chronic obstructive pulmonary disease, and heart failure. Despite these applications, there have been no sensor-based DHT-derived endpoints in clinical trials recruiting patients with inflammatory arthritis. Borrowing from case studies across medicine, we outline the opportunities and challenges in developing novel sensor-based DHT-derived endpoints that capture the symptoms and disease manifestations most relevant to patients with inflammatory arthritis.

Novel Digital Biomarkers for Fine Motor Skills Assessment in Psoriatic Arthritis: The DaktylAct Touch-Based Serious Game Approach

Psoriatic Arthritis (PsA) is a chronic, inflammatory disease affecting joints, substantially impacting patients' quality of life, with European guidelines for managing PsA emphasizing the importance of assessing hand function. Here, we present a set of novel digital biomarkers (dBMs) derived from a touchscreen-based serious game approach, DaktylAct, intended as a proxy, gamified, objective assessment of hand impairment, with emphasis on fine motor skills, caused by PsA. This is achieved by its design, where the user controls a cannon to aim at and hit targets using two finger pinch-in/out and wrist rotation gestures. In-game metrics (targets hit and score) and statistical features (mean, standard deviation) of gameplay actions (duration of gestures, applied pressure, and wrist rotation angle) produced during gameplay serve as informative dBMs. DaktylAct was tested on a cohort comprising 16 clinically verified PsA patients and nine healthy controls (HC). Correlation analysis demonstrated a positive correlation between average pinch-in duration and disease activity (DA) and a negative correlation between standard deviation of applied pressure during wrist rotation and joint inflammation. Logistic regression models achieved 83% and 91% classification performance discriminating HC from PsA patients with low DA (LDA) and PsA patients with and without joint inflammation, respectively. Results presented here are promising and create a proof-of-concept, paving the way for further validation in larger cohorts.

COTIDIANA Dataset - Smartphone-Collected Data on the Mobility, Finger Dexterity, and Mental Health of People With Rheumatic and Musculoskeletal Diseases

Rheumatic and Musculoskeletal Diseases (RMDs) are very common and can negatively impact patients' quality of life. The current care of patients with RMDs is episodic, based on a few yearly doctor visits, which may not provide an adequate picture of the patient's condition. Researchers have hypothesized that RMDs could be passively monitored using smartphones or sensors, however, there are no datasets to support this development. We introduce the COTIDIANA Dataset: a holistic, multimodal, multidimensional, and open-access resource that gathers data on mobility and physical activity, finger dexterity, and mental health, key dimensions affected by RMDs. We gathered smartphone and self-reported data from 31 patients and 28 age-matched controls, including inertial sensors, keyboard metrics, communication logs, and reference tests/scales. A preliminary analysis showed the potential for extracted metrics to predict RMD diagnosis and condition characteristics. Our dataset shall enable the community to create mobile and wearable-based solutions for patients with RMDs.

Clinical Validation of Digitally Acquired Clinical Data and Machine Learning Models for Remote Measurement of Psoriasis and Psoriatic Arthritis: A Proof-of-Concept Study

OBJECTIVE

Psoriatic disease remains underdiagnosed and undertreated. We developed and validated a suite of novel, sensor-based smartphone assessments (Psorcast app) that can be self-administered to measure cutaneous and musculoskeletal signs and symptoms of psoriatic disease.

METHODS

Participants with psoriasis (PsO) or psoriatic arthritis (PsA) and healthy controls were recruited between June 5, 2019, and November 10, 2021, at 2 academic medical centers. Concordance and accuracy of digital measures and image-based machine learning models were compared to their analogous clinical measures from trained rheumatologists and dermatologists.

RESULTS

Of 104 study participants, 51 (49%) were female and 53 (51%) were male, with a mean age of 42.3 years (SD 12.6). Seventy-nine (76%) participants had PsA, 16 (15.4%) had PsO, and 9 (8.7%) were healthy controls. Digital patient assessment of percent body surface area (BSA) affected with PsO demonstrated very strong concordance (Lin concordance correlation coefficient [CCC] 0.94 [95% CI 0.91-0.96]) with physician-assessed BSA. The in-clinic and remote target plaque physician global assessments showed fair-to-moderate concordance (CCCerythema 0.72 [0.59-0.85]; CCCinduration 0.72 [0.62-0.82]; CCCscaling 0.60 [0.48-0.72]). Machine learning models of hand photos taken by patients accurately identified clinically diagnosed nail PsO with an accuracy of 0.76. The Digital Jar Open assessment categorized physician-assessed upper extremity involvement, considering joint tenderness or enthesitis (AUROC 0.68 [0.47-0.85]).

CONCLUSION

The Psorcast digital assessments achieved significant clinical validity, although they require further validation in larger cohorts before use in evidence-based medicine or clinical trial settings. The smartphone software and analysis pipelines from the Psorcast suite are open source and freely available.

Statistical analysis of actigraphy data with generalised additive models

There is a growing interest in the use of physical activity data in clinical studies, particularly in diseases that limit mobility in patients. High-frequency data collected with digital sensors are typically summarised into actigraphy features aggregated at epoch level (e.g., by minute). The statistical analysis of such volume of data is not straightforward. The general trend is to derive metrics, capturing specific aspects of physical activity, that condense (say) a week worth of data into a single numerical value. Here we propose to analyse the entire time-series data using Generalised Additive Models (GAMs). GAMs are semi-parametric models that allow inclusion of both parametric and non-parametric terms in the linear predictor. The latter are smooth terms (e.g., splines) and, in the context of actigraphy minute-by-minute data analysis, they can be used to assess daily patterns of physical activity. This in turn can be used to better understand changes over time in longitudinal studies as well as to compare treatment groups. We illustrate the application of GAMs in two clinical studies where actigraphy data was collected: a non-drug, single-arm study in patients with amyotrophic lateral sclerosis, and a physical-activity sub-study included in a phase 2b clinical trial in patients with chronic obstructive pulmonary disease.

Digital health technologies and machine learning augment patient reported outcomes to remotely characterise rheumatoid arthritis

Digital measures of health status captured during daily life could greatly augment current in-clinic assessments for rheumatoid arthritis (RA), to enable better assessment of disease progression and impact. This work presents results from weaRAble-PRO, a 14-day observational study, which aimed to investigate how digital health technologies (DHT), such as smartphones and wearables, could augment patient reported outcomes (PRO) to determine RA status and severity in a study of 30 moderate-to-severe RA patients, compared to 30 matched healthy controls (HC). Sensor-based measures of health status, mobility, dexterity, fatigue, and other RA specific symptoms were extracted from daily iPhone guided tests (GT), as well as actigraphy and heart rate sensor data, which was passively recorded from patients' Apple smartwatch continuously over the study duration. We subsequently developed a machine learning (ML) framework to distinguish RA status and to estimate RA severity. It was found that daily wearable sensor-outcomes robustly distinguished RA from HC participants (F1, 0.807). Furthermore, by day 7 of the study (half-way), a sufficient volume of data had been collected to reliably capture the characteristics of RA participants. In addition, we observed that the detection of RA severity levels could be improved by augmenting standard patient reported outcomes with sensor-based features (F1, 0.833) in comparison to using PRO assessments alone (F1, 0.759), and that the combination of modalities could reliability measure continuous RA severity, as determined by the clinician-assessed RAPID-3 score at baseline (r2, 0.692; RMSE, 1.33). The ability to measure the impact of the disease during daily life-through objective and remote digital outcomes-paves the way forward to enable the development of more patient-centric and personalised measurements for use in RA clinical trials.

Machine learning to detect, stage and classify diseases and their symptoms based on inertial sensor data: a mapping review

This article presents a systematic review aimed at mapping the literature published in the last decade on the use of machine learning (ML) for clinical decision-making through wearable inertial sensors. The review aims to analyze the trends, perspectives, strengths, and limitations of current literature in integrating ML and inertial measurements for clinical applications. The review process involved defining four research questions and applying four relevance assessment indicators to filter the search results, providing insights into the pathologies studied, technologies and setups used, data processing schemes, ML techniques applied, and their clinical impact. When combined with ML techniques, inertial measurement units (IMUs) have primarily been utilized to detect and classify diseases and their associated motor symptoms. They have also been used to monitor changes in movement patterns associated with the presence, severity, and progression of pathology across a diverse range of clinical conditions. ML models trained with IMU data have shown potential in improving patient care by objectively classifying and predicting motor symptoms, often with a minimally encumbering setup. The findings contribute to understanding the current state of ML integration with wearable inertial sensors in clinical practice and identify future research directions. Despite the widespread adoption of these technologies and techniques in clinical applications, there is still a need to translate them into routine clinical practice. This underscores the importance of fostering a closer collaboration between technological experts and professionals in the medical field.

Recommendation to implementation of remote patient monitoring in rheumatology: lessons learned and barriers to take

Remote patient monitoring (RPM) leverages advanced technology to monitor and manage patients' health remotely and continuously. In 2022 European Alliance of Associations for Rheumatology (EULAR) points-to-consider for remote care were published to foster adoption of RPM, providing guidelines on where to position RPM in our practices. Sample papers and studies describe the value of RPM. But for many rheumatologists, the unanswered question remains the 'how to?' implement RPM.Using the successful, though not frictionless example of the Southmead rheumatology department, we address three types of barriers for the implementation of RPM: service, clinician and patients, with subsequent learning points that could be helpful for new teams planning to implement RPM. These address, but are not limited to, data governance, selecting high quality cost-effective solutions and ensuring compliance with data protection regulations. In addition, we describe five lacunas that could further improve RPM when addressed: establishing quality standards, creating a comprehensive database of available RPM tools, integrating data with electronic patient records, addressing reimbursement uncertainties and improving digital literacy among patients and healthcare professionals.

Computer vision detects inflammatory arthritis in standardized smartphone photographs in an Indian patient cohort

Introduction

Computer vision extracts meaning from pixelated images and holds promise in automating various clinical tasks. Convolutional neural networks (CNNs), a deep learning network used therein, have shown promise in analyzing X-ray images and joint photographs. We studied the performance of a CNN on standardized smartphone photographs in detecting inflammation in three hand joints and compared it to a rheumatologist's diagnosis.

Methods

We enrolled 100 consecutive patients with inflammatory arthritis with an onset period of less than 2 years, excluding those with deformities. Each patient was examined by a rheumatologist, and the presence of synovitis in each joint was recorded. Hand photographs were taken in a standardized manner, anonymized, and cropped to include joints of interest. A ResNet-101 backbone modified for two class outputs (inflamed or not) was used for training. We also tested a hue-augmented dataset. We reported accuracy, sensitivity, and specificity for three joints: wrist, index finger proximal interphalangeal (IFPIP), and middle finger proximal interphalangeal (MFPIP), taking the rheumatologist's opinion as the gold standard.

Results

The cohort consisted of 100 individuals, of which 22 of them were men, with a mean age of 49.7 (SD 12.9) years. The majority of the cohort (n = 68, 68%) had rheumatoid arthritis. The wrist (125/200, 62.5%), MFPIP (94/200, 47%), and IFPIP (83/200, 41.5%) were the three most commonly inflamed joints. The CNN achieved the highest accuracy, sensitivity, and specificity in detecting synovitis in the MFPIP (83, 77, and 88%, respectively), followed by the IFPIP (74, 74, and 75%, respectively) and the wrist (62, 90, and 21%, respectively).

Discussion

We have demonstrated that computer vision was able to detect inflammation in three joints of the hand with reasonable accuracy on standardized photographs despite a small dataset. Feature engineering was not required, and the CNN worked despite a diversity in clinical diagnosis. Larger datasets are likely to improve accuracy and help explain the basis of classification. These data suggest a potential use of computer vision in screening and follow-up of inflammatory arthritis.

Participant Engagement and Adherence to Providing Smartwatch and Patient-Reported Outcome Data: Digital Tracking of Rheumatoid Arthritis Longitudinally (DIGITAL) Real-World Study

BACKGROUND

Digital health studies using electronic patient-reported outcomes (ePROs) and wearables bring new challenges, including the need for participants to consistently provide trial data.

OBJECTIVE

This study aims to characterize the engagement, protocol adherence, and data completeness among participants with rheumatoid arthritis enrolled in the Digital Tracking of Arthritis Longitudinally (DIGITAL) study.

METHODS

Participants were invited to participate in this app-based study, which included a 14-day run-in and an 84-day main study. In the run-in period, data were collected via the ArthritisPower mobile app to increase app familiarity and identify the individuals who were motivated to participate. Successful completers of the run-in period were mailed a wearable smartwatch, and automated and manual prompts were sent to participants, reminding them to complete app input or regularly wear and synchronize devices, respectively, during the main study. Study coordinators monitored participant data and contacted participants via email, SMS text messaging, and phone to resolve adherence issues per a priori rules, in which consecutive spans of missing data triggered participant contact. Adherence to data collection during the main study period was defined as providing requested data for >70% of 84 days (daily ePRO, ≥80% daily smartwatch data) or at least 9 of 12 weeks (weekly ePRO).

RESULTS

Of the 470 participants expressing initial interest, 278 (59.1%) completed the run-in period and qualified for the main study. Over the 12-week main study period, 87.4% (243/278) of participants met the definition of adherence to protocol-specified data collection for weekly ePRO, and 57.2% (159/278) did so for daily ePRO. For smartwatch data, 81.7% (227/278) of the participants adhered to the protocol-specified data collection. In total, 52.9% (147/278) of the participants met composite adherence.

CONCLUSIONS

Compared with other digital health rheumatoid arthritis studies, a short run-in period appears useful for identifying participants likely to engage in a study that collects data via a mobile app and wearables and gives participants time to acclimate to study requirements. Automated or manual prompts (ie, "It's time to sync your smartwatch") may be necessary to optimize adherence. Adherence varies by data collection type (eg, ePRO vs smartwatch data).

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.2196/14665.

Skin Sensitivity Assessment Using Smartphone Haptic Feedback

Goal: This work presents a smartphone application to assess cutaneous sensory perception by establishing Vibrational Perception Thresholds (VPTs). Cutaneous sensory perception diagnostics allow for the early detection and symptom tracking of tactile dysfunction. However, lack of access to healthcare and the limited frequency of current screening tools can leave skin sensation impairments undiscovered or unmonitored. Methods: A 23-participant cross-sectional study in subjects with a range of finger sensation tests Smartphone Established VPTs (SE-VPTs) by varying device vibrational intensity. These are compared against monofilament test scores, a clinical measure of skin sensitivity. Results: We find a strong positive correlation between SE-VPTs and monofilament scores ([Formula: see text] = 0.86, p = 1.65e-07). Conclusions: These results demonstrate the feasibility of using a smartphone as a skin sensation screening tool.

Attitudes towards technology supported rheumatoid arthritis care: investigating patient- and clinician-perceived opportunities and barriers

Objectives

Globally, demand outstrips capacity in rheumatology services, making Mobile Health (mHealth) attractive, with the potential to improve access, empower patient self-management and save costs. Existing mHealth interventions have poor uptake by end users. This study was designed to understand existing challenges, opportunities and barriers for computer technology in the RA care pathway.

Methods

People with RA were recruited from Barts Health NHS Trust rheumatology clinics to complete paper questionnaires and clinicians were recruited from a variety of centres in the UK to complete an online questionnaire. Data collected included demographics, current technology use, challenges managing RA, RA medications and monitoring, clinic appointments, opportunities for technology and barriers to technology.

Results

A total of 109 patient and 41 clinician questionnaires were completed. A total of 83.5% of patients and 93.5% of clinicians use smartphones daily. However, only 25% had ever used an arthritis app and only 5% had persisted with one. Both groups identified managing pain, flares and RA medications as areas of existing need. Access to care, medication support and disease education were mutually agreeable opportunities; however, discrepancies existed between groups with clinicians prioritizing education over access, likely due to concerns of data overwhelm (80.6% considered this a barrier).

Conclusions

In spite of high technology use and willingness from both sides, our cohort did not utilize technology to support care, suggesting inadequacies in the existing software. The lack of an objective biomarker for RA disease activity, existing challenges in the healthcare system and the need for integration with existing technical systems were identified as the greatest barriers.

Trial registration

Registered on the Clinical Research Network registry (IRAS ID: 264690).

Patient-centric assessment of rheumatoid arthritis using a smartwatch and bespoke mobile app in a clinical setting

Rheumatoid arthritis (RA) is a fluctuating progressive disease requiring frequent symptom assessment for appropriate management. Continuous tracking using digital technologies may provide greater insights of a patient's experience. This prospective study assessed the feasibility, reliability, and clinical utility of using novel digital technologies to remotely monitor participants with RA. Participants with moderate to severe RA and non-RA controls were monitored continuously for 14 days using an iPhone with an integrated bespoke application and an Apple Watch. Participants completed patient-reported outcome measures and objective guided tests designed to assess disease-related impact on physical function. The study was completed by 28 participants with RA, 28 matched controls, and 2 unmatched controls. Completion rates for all assessments were > 97% and were reproducible over time. Several guided tests distinguished between RA and control cohorts (e.g., mean lie-to-stand time [seconds]: RA: 4.77, control: 3.25; P < 0.001). Participants with RA reporting greater stiffness, pain, and fatigue had worse guided test performances (e.g., wrist movement [P < 0.001] and sit-to-stand transition time [P = 0.009]) compared with those reporting lower stiffness, pain, and fatigue. This study demonstrates that digital technologies can be used in a well-controlled, remote clinical setting to assess the daily impact of RA.

Body movement as a biomarker for use in chronic pain rehabilitation: An embedded analysis of an RCT of a virtual reality solution for adults with chronic pain

Introduction

Chronic low back pain (CLBP) is a major public health problem. Reliably measuring the effects of chronic pain on movement and activity, and any changes due to treatment, is a healthcare challenge. A recently published paper demonstrated that a novel digital therapeutic (DTxP) was efficacious in reducing fear of movement and increasing the quality of life of adult patients with moderate to severe CLBP. In this paper, we report a study of how data from wearable devices collected in this study could be used as a digital measure for use in studies of chronic low back pain.

Methods

Movement, electrodermal recording, general activity and clinical assessment data were collected in a clinical trial of a novel digital therapeutic intervention (DTxP) by using the sensors in commercial Garmin Vivosmart 4, Empatica Embrace2 and Oculus Quest wearables. Wearable data were collected during and between the study interventions (frequent treatment sessions of DTxP). Data were analyzed using exploratory statistical analysis.

Results

A pattern of increased longitudinal velocity in the movement data collected with right-hand, left-hand, and head sensors was observed in the study population. Correlations were observed with the changes in clinical scales (Tampa Scale of Kinesiophobia, EQ5D Overall health VAS, and EQ5D QoL score). The strongest correlation was observed with the increased velocity of head and right-hand sensors (Spearman correlation with increasing head sensor velocity and Tampa Scale of Kinesiophobia -0.45, Overall health VAS +0.67 and EQ5D QoL score -0.66). The sample size limited interpretation of electrodermal and general activity data.

Discussion/Conclusion

We found a novel digital signal for use in monitoring the efficacy of a digital therapeutics (DTxP) in adults with CLBP. We discuss the potential use of such movement based digital markers as surrogate or additional endpoints in studies of chronic musculoskeletal pain.

Clinical Trial Registration

https://clinicaltrials.gov/ct2/show/NCT04225884?cond=NCT04225884&draw=2&rank=1, identifier: NCT04225884.

Smartphone-based behavioral monitoring and patient-reported outcomes in adults with rheumatic and musculoskeletal disease

BACKGROUND

Rheumatic and musculoskeletal diseases (RMD) are associated with depression, fatigue, and disturbed sleep - symptoms that often impact behavior and activity. Patient reported outcomes (PROs) are a way of collecting information on the patient symptom experience directly from the individual. The purpose of this study was to measure and compare user smartphone sensor and activity data in adults with RMDs and assess associations with PROs.

METHODS

We invited adults with RMDs enrolled in the FORWARD Databank to participate by installing a custom app on their smartphone and answering PROs (pain, global, HAQ-II) questions daily and weekly over 3 years. Passive data collected included mobility distance, unique calls and text messages, call durations, and number of missed calls. Confounders included sociodemographic, clinical, passive phone behavior, and seasonal factors. Kappa statistics between PRO and flares were computed to measure agreement. The agreement between daily and weekly VAS pain was estimated using the intraclass (ICC) correlation of a two-way random effect model. The relationship between the weekly PRO outcomes and the passive phone data was analyzed with a linear mixed-effect model (LMM), including a random intercept for participant and slope for time in the study with an unstructured covariate structure.

RESULTS

Of the 446 participants, the mean (SD) age was 54 (12) years, most (65.5%) had rheumatoid arthritis (RA), the vast majority (91%) were female, and the US Northeast has the least representation (12%). Longer reaction times, interaction diversity, and higher mobility were associated with worse PROs while longer text messages were associated with better PROs. Participants in this study showed good levels of adherence which holds promise for future interventions using passive behavior measures in self-management and clinical follow-up.

CONCLUSION

This is the first study to examine passive smartphone behavior with PROs in RMDs and we found significant associations between these behaviors and important health outcomes of pain and function. As smartphone usage continues to change, future studies should validate and expand on our findings with a goal of finding changes in patient symptoms passively through mobile device monitoring.

Smartphones for musculoskeletal research - hype or hope? Lessons from a decennium of mHealth studies

BACKGROUND

Smartphones provide opportunities for musculoskeletal research: they are integrated in participants' daily lives and can be used to collect patient-reported outcomes as well as sensor data from large groups of people. As the field of research with smartphones and smartwatches matures, it has transpired that some of the advantages of this modern technology are in fact double-edged swords. BODY: In this narrative review, we illustrate the advantages of using smartphones for data collection with 18 studies from various musculoskeletal domains. We critically appraised existing literature, debunking some myths around the advantages of smartphones: the myth that smartphone studies automatically enable high engagement, that they reach more representative samples, that they cost little, and that sensor data is objective. We provide a nuanced view of evidence in these areas and discuss strategies to increase engagement, to reach representative samples, to reduce costs and to avoid potential sources of subjectivity in analysing sensor data.

CONCLUSION

If smartphone studies are designed without awareness of the challenges inherent to smartphone use, they may fail or may provide biased results. Keeping participants of smartphone studies engaged longitudinally is a major challenge. Based on prior research, we provide 6 actions by researchers to increase engagement. Smartphone studies often have participants that are younger, have higher incomes and high digital literacy. We provide advice for reaching more representative participant groups, and for ensuring that study conclusions are not plagued by bias resulting from unrepresentative sampling. Costs associated with app development and testing, data storage and analysis, and tech support are substantial, even if studies use a 'bring your own device'-policy. Exchange of information on costs, collective app development and usage of open-source tools would help the musculoskeletal community reduce costs of smartphone studies. In general, transparency and wider adoption of best practices would help bringing smartphone studies to the next level. Then, the community can focus on specific challenges of smartphones in musculoskeletal contexts, such as symptom-related barriers to using smartphones for research, validating algorithms in patient populations with reduced functional ability, digitising validated questionnaires, and methods to reliably quantify pain, quality of life and fatigue.

Dorsal Finger Fold Recognition by Convolutional Neural Networks for the Detection and Monitoring of Joint Swelling in Patients with Rheumatoid Arthritis

Digital biomarkers such as wearables are of increasing interest in monitoring rheumatic diseases, but they usually lack disease specificity. In this study, we apply convolutional neural networks (CNN) to real-world hand photographs in order to automatically detect, extract, and analyse dorsal finger fold lines as a correlate of proximal interphalangeal (PIP) joint swelling in patients with rheumatoid arthritis (RA). Hand photographs of RA patients were taken by a smartphone camera in a standardized manner. Overall, 190 PIP joints were categorized as either swollen or not swollen based on clinical judgement and ultrasound. Images were automatically preprocessed by cropping PIP joints and extracting dorsal finger folds. Subsequently, metrical analysis of dorsal finger folds was performed, and a CNN was trained to classify the dorsal finger lines into swollen versus non-swollen joints. Representative horizontal finger folds were also quantified in a subset of patients before and after resolution of PIP swelling and in patients with disease flares. In swollen joints, the number of automatically extracted deep skinfold imprints was significantly reduced compared to non-swollen joints (1.3, SD 0.8 vs. 3.3, SD 0.49, p < 0.01). The joint diameter/deep skinfold length ratio was significantly higher in swollen (4.1, SD 1.4) versus non-swollen joints (2.1, SD 0.6, p < 0.01). The CNN model successfully differentiated swollen from non-swollen joints based on finger fold patterns with a validation accuracy of 0.84, a sensitivity of 88%, and a specificity of 75%. A heatmap of the original images obtained by an extraction algorithm confirmed finger folds as the region of interest for correct classification. After significant response to disease-modifying antirheumatic drug ± corticosteroid therapy, longitudinal metrical analysis of eight representative deep finger folds showed a decrease in the mean diameter/finger fold length (finger fold index, FFI) from 3.03 (SD 0.68) to 2.08 (SD 0.57). Conversely, the FFI increased in patients with disease flares. In conclusion, automated preprocessing and the application of CNN algorithms in combination with longitudinal metrical analysis of dorsal finger fold patterns extracted from real-world hand photos might serve as a digital biomarker in RA.

Machine learning approaches to improve disease management of patients with rheumatoid arthritis: review and future directions

INTRODUCTION

Although the management of rheumatoid arthritis (RA) has improved in major way over the last decades, this disease still leads to an important burden for patients and society, and there is a need to develop more personalized approaches. Machine learning (ML) methods are more and more used in health-related studies and can be applied to different sorts of data (clinical, radiological, or 'omics' data). Such approaches may improve the management of patients with RA.

AREAS COVERED

In this paper, we propose a review regarding ML approaches applied to RA. A scoping literature search was performed in PubMed, in September 2021 using the following MeSH terms: 'arthritis, rheumatoid' and 'machine learning'. Based on this search, the usefulness of ML methods for RA diagnosis, monitoring, and prediction of response to treatment and RA outcomes, is discussed.

EXPERT OPINION

ML methods have the potential to revolutionize RA-related research and improve disease management and patient care. Nevertheless, these models are not yet ready to contribute fully to rheumatologists' daily practice. Indeed, these methods raise technical, methodological, and ethical issues, which should be addressed properly to allow their implementation. Collaboration between data scientists, clinical researchers, and physicians is therefore required to move this field forward.

Safety of medicines and vaccines - building next generation capability

The systematic safety surveillance of real-world use of medicinal products and related activities (pharmacovigilance) started in earnest as a scientific field only in the 1960s. While developments have occurred over the past 50 years, adding to its complexity and sophistication, the extent to which some of these advances have positively impacted the capability for ensuring patient safety is questionable. We review how the conduct of safety surveillance has changed, highlight recent scientific advances, and argue how they need to be harnessed to enhance pharmacovigilance in the future. Specifically, we describe five changes that we believe should and will need to happen globally in the coming years: (i) better, more diverse data used for safety; (ii) the switch from manual activities to automation; (iii) removal of limited value, extraneous transactional activities and replacement with sharpened focus on scientific efforts to improve patient safety; (iv) patient-involved and focussed safety; and (v) personalised safety.

Evaluation, Acceptance, and Qualification of Digital Measures: From Proof of Concept to Endpoint

To support the successful adoption of digital measures into internal decision making and evidence generation for medical product development, we present a unified lexicon to aid communication throughout this process, and highlight key concepts including the critical role of participant engagement in development of digital measures. We detail the steps of bringing a successful proof of concept to scale, focusing on key decisions in the development of a new digital measure: asking the right question, optimized approaches to evaluating new measures, and whether and how to pursue qualification or acceptance. Building on the V3 framework for establishing verification and analytical and clinical validation, we discuss strategic and practical considerations for collecting this evidence, illustrated with concrete examples of trailblazing digital measures in the field.

The Path Forward for Digital Measures: Suppressing the Desire to Compare Apples and Pineapples

Digital measures are becoming more prevalent in clinical development. Methods for robust evaluation are increasingly well defined, yet the primary barrier for digital measures to transition beyond exploratory usage often relies on a comparison to the existing standards. This article focuses on how researchers should approach the complex issue of comparing across assessment modalities. We discuss comparisons of subjective versus objective assessments, or performance-based versus behavioral measures, and we pay particular attention to the situation where the expected association may be poor or nonlinear. We propose that, rather than seeking to replace the standard, research should focus on a structured understanding of how the new measure augments established assessments, with the ultimate goal of developing a more complete understanding of what is meaningful to patients.

A Thorough Examination of Morning Activity Patterns in Adults with Arthritis and Healthy Controls Using Actigraphy Data

Background

Wearable sensors allow researchers to remotely capture digital health data, including physical activity, which may identify digital biomarkers to differentiate healthy and clinical cohorts. To date, research has focused on high-level data (e.g., overall step counts) which may limit our insights to whether people move differently, rather than how they move differently.

Objective

This study therefore aimed to use actigraphy data to thoroughly examine activity patterns during the first hours following waking in arthritis patients (n = 45) and healthy controls (n = 30).

Methods

Participants wore an Actigraph GT9X Link for 28 days. Activity counts were analysed and compared over varying epochs, ranging from 15 min to 4 h, starting with waking in the morning. The sum, and a measure of rate of change of cumulative activity in the period immediately after waking (area under the curve [AUC]) for each time period, was calculated for each participant, each day, and individual and group means were calculated. Two-tailed independent t tests determined differences between the groups.

Results

No differences were seen for summed activity counts across any time period studied. However, differences were noted in the AUC analysis for the discrete measures of relative activity. Specifically, within the first 15, 30, 45, and 60 min following waking, the AUC for activity counts was significantly higher in arthritis patients compared to controls, particularly at the 30 min period (t = -4.24, p = 0.0002). Thus, while both cohorts moved the same amount, the way in which they moved was different.

Conclusion

This study is the first to show that a detailed analysis of actigraphy variables could identify activity pattern changes associated with arthritis, where the high-level daily summaries did not. Results suggest discrete variables derived from raw data may be useful to help identify clinical cohorts and should be explored further to determine if they may be effective clinical biomarkers.