Perceptions of bariatric surgery in patients with type 2 diabetes: data from a self-administered questionnaire.

BACKGROUND: Although bariatric surgery (BS) is recommended for patients with type 2 diabetes (T2D) and moderate to severe obesity, only approximately 2% of patients undergo surgery. OBJECTIVE: To compare the knowledge and perception of BS with that of other treatments for diabetes among patients with diabetes. SETTING: French social media platforms. METHODS: A self-administered questionnaire was distributed from May 13 to June 3, 2020, via different French social media, including patients with T2D (main target), and patients with type 1 diabetes (control population). Different profiles of reluctance to BS were identified using a factorial analysis. RESULTS: Of the 4481 responders (50.4% women, 33.9% aged over 65), 60% had T2D. Of the 1736 patients who had heard of BS (38.7%), 1493 declared they never addressed it with their physician. Among T2D patients, BS is the treatment that elicits the most negative response, with more than 10% showing reluctance. Four reluctance profiles were identified: (1) cluster 1 (43.4%), fear of consequences on their eating habits and irreversibility of the procedure; (2) cluster 2 (34.9%), fear of poorer diabetes control; (3) cluster 3 (9.3%), fear of surgical risk; and (4) cluster 4 (12.4%), fear of side effects. In all clusters, the opinion of their physician would be the most important factor to change their mind. CONCLUSION: Bariatric surgery for T2D is rarely addressed in routine medical visits. Fear of operative risks and irreversibility of the procedure largely explains the reluctance to BS. Information and education campaigns on the benefit of metabolic surgery for patients with T2D remain necessary.

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.

Wearable Activity Trackers in the Management of Rheumatic Diseases: Where Are We in 2020?

In healthcare, physical activity can be monitored in two ways: self-monitoring by the patient himself or external monitoring by health professionals. Regarding self-monitoring, wearable activity trackers allow automated passive data collection that educate and motivate patients. Wearing an activity tracker can improve walking time by around 1500 steps per day. However, there are concerns about measurement accuracy (e.g., lack of a common validation protocol or measurement discrepancies between different devices). For external monitoring, many innovative electronic tools are currently used in rheumatology to help support physician time management, to reduce the burden on clinic time, and to prioritize patients who may need further attention. In inflammatory arthritis, such as rheumatoid arthritis, regular monitoring of patients to detect disease flares improves outcomes. In a pilot study applying machine learning to activity tracker steps, we showed that physical activity was strongly linked to disease flares and that patterns of physical activity could be used to predict flares with great accuracy, with a sensitivity and specificity above 95%. Thus, automatic monitoring of steps may lead to improved disease control through potential early identification of disease flares. However, activity trackers have some limitations when applied to rheumatic patients, such as tracker adherence, lack of clarity on long-term effectiveness, or the potential multiplicity of trackers.

EULAR points to consider for the use of big data in rheumatic and musculoskeletal diseases.

BACKGROUND: Tremendous opportunities for health research have been unlocked by the recent expansion of big data and artificial intelligence. However, this is an emergent area where recommendations for optimal use and implementation are needed. The objective of these European League Against Rheumatism (EULAR) points to consider is to guide the collection, analysis and use of big data in rheumatic and musculoskeletal disorders (RMDs). METHODS: A multidisciplinary task force of 14 international experts was assembled with expertise from a range of disciplines including computer science and artificial intelligence. Based on a literature review of the current status of big data in RMDs and in other fields of medicine, points to consider were formulated. Levels of evidence and strengths of recommendations were allocated and mean levels of agreement of the task force members were calculated. RESULTS: Three overarching principles and 10 points to consider were formulated. The overarching principles address ethical and general principles for dealing with big data in RMDs. The points to consider cover aspects of data sources and data collection, privacy by design, data platforms, data sharing and data analyses, in particular through artificial intelligence and machine learning. Furthermore, the points to consider state that big data is a moving field in need of adequate reporting of methods and benchmarking, careful data interpretation and implementation in clinical practice. CONCLUSION: These EULAR points to consider discuss essential issues and provide a framework for the use of big data in RMDs.

Current status of use of big data and artificial intelligence in RMDs: a systematic literature review informing EULAR recommendations.

Objective: To assess the current use of big data and artificial intelligence (AI) in the field of rheumatic and musculoskeletal diseases (RMDs). Methods: A systematic literature review was performed in PubMed MEDLINE in November 2018, with key words referring to big data, AI and RMDs. All original reports published in English were analysed. A mirror literature review was also performed outside of RMDs on the same number of articles. The number of data analysed, data sources and statistical methods used (traditional statistics, AI or both) were collected. The analysis compared findings within and beyond the field of RMDs. Results: Of 567 articles relating to RMDs, 55 met the inclusion criteria and were analysed, as well as 55 articles in other medical fields. The mean number of data points was 746 million (range 2000-5 billion) in RMDs, and 9.1 billion (range 100 000-200 billion) outside of RMDs. Data sources were varied: in RMDs, 26 (47%) were clinical, 8 (15%) biological and 16 (29%) radiological. Both traditional and AI methods were used to analyse big data (respectively, 10 (18%) and 45 (82%) in RMDs and 8 (15%) and 47 (85%) out of RMDs). Machine learning represented 97% of AI methods in RMDs and among these methods, the most represented was artificial neural network (20/44 articles in RMDs). Conclusions: Big data sources and types are varied within the field of RMDs, and methods used to analyse big data were heterogeneous. These findings will inform a European League Against Rheumatism taskforce on big data in RMDs.

Detection of Flares by Decrease in Physical Activity, Collected Using Wearable Activity Trackers in Rheumatoid Arthritis or Axial Spondyloarthritis: An Application of Machine Learning Analyses in Rheumatology.

OBJECTIVE: Flares in rheumatoid arthritis (RA) and axial spondyloarthritis (SpA) may influence physical activity. The aim of this study was to assess longitudinally the association between patient-reported flares and activity-tracker-provided steps per minute, using machine learning. METHODS: This prospective observational study (ActConnect) included patients with definite RA or axial SpA. For a 3-month time period, physical activity was assessed continuously by number of steps/minute, using a consumer grade activity tracker, and flares were self-assessed weekly. Machine-learning techniques were applied to the data set. After intrapatient normalization of the physical activity data, multiclass Bayesian methods were used to calculate sensitivities, specificities, and predictive values of the machine-generated models of physical activity in order to predict patient-reported flares. RESULTS: Overall, 155 patients (1,339 weekly flare assessments and 224,952 hours of physical activity assessments) were analyzed. The mean ± SD age for patients with RA (n = 82) was 48.9 ± 12.6 years and was 41.2 ± 10.3 years for those with axial SpA (n = 73). The mean ± SD disease duration was 10.5 ± 8.8 years for patients with RA and 10.8 ± 9.1 years for those with axial SpA. Fourteen patients with RA (17.1%) and 41 patients with axial SpA (56.2%) were male. Disease was well-controlled (Disease Activity Score in 28 joints mean ± SD 2.2 ± 1.2; Bath Ankylosing Spondylitis Disease Activity Index score mean ± SD 3.1 ± 2.0), but flares were frequent (22.7% of all weekly assessments). The model generated by machine learning performed well against patient-reported flares (mean sensitivity 96% [95% confidence interval (95% CI) 94-97%], mean specificity 97% [95% CI 96-97%], mean positive predictive value 91% [95% CI 88-96%], and negative predictive value 99% [95% CI 98-100%]). Sensitivity analyses were confirmatory. CONCLUSION: Although these pilot findings will have to be confirmed, the correct detection of flares by machine-learning processing of activity tracker data provides a framework for future studies of remote-control monitoring of disease activity, with great precision and minimal patient burden.

Physical Activity Assessment Using an Activity Tracker in Patients with Rheumatoid Arthritis and Axial Spondyloarthritis: Prospective Observational Study.

BACKGROUND: Physical activity can be tracked using mobile devices and is recommended in rheumatoid arthritis (RA) and axial spondyloarthritis (axSpA) management. The World Health Organization (WHO) recommends at least 150 min per week of moderate to vigorous physical activity (MVPA). OBJECTIVE: The objectives of this study were to assess and compare physical activity and its patterns in patients with RA and axSpA using an activity tracker and to assess the feasibility of mobile devices in this population. METHODS: This multicentric prospective observational study (ActConnect) included patients who had definite RA or axSpA, and a smartphone. Physical activity was assessed over 3 months using a mobile activity tracker, recording the number of steps per minute. The number of patients reaching the WHO recommendations was calculated. RA and axSpA were compared, using linear mixed models, for number of steps, proportion of morning steps, duration of total activity, and MVPA. Physical activity trajectories were identified using the K-means method, and factors related to the low activity trajectory were explored by logistic regression. Acceptability was assessed by the mean number of days the tracker was worn over the 3 months (ie, adherence), the percentage of wearing time, and by an acceptability questionnaire. RESULTS: A total of 157 patients (83 RA and 74 axSpA) were analyzed; 36.3% (57/157) patients were males, and their mean age was 46 (standard deviation [SD] 12) years and mean disease duration was 11 (SD 9) years. RA and axSpA patients had similar physical activity levels of 16 (SD 11) and 15 (SD 12) min per day of MVPA (P=.80), respectively. Only 27.4% (43/157) patients reached the recommendations with a mean MVPA of 106 (SD 77) min per week. The following three trajectories were identified with constant activity: low (54.1% [85/157] of patients), moderate (42.7% [67/157] of patients), and high (3.2% [5/157] of patients) levels of MVPA. A higher body mass index was significantly related to less physical activity (odds ratio 1.12, 95% CI 1.11-1.14). The activity trackers were worn during a mean of 79 (SD 17) days over the 90 days follow-up. Overall, patients considered the use of the tracker very acceptable, with a mean score of 8 out 10. CONCLUSIONS: Patients with RA and axSpA performed insufficient physical activity with similar levels in both groups, despite the differences between the 2 diseases. Activity trackers allow longitudinal assessment of physical activity in these patients. The good adherence to this study and the good acceptability of wearing activity trackers confirmed the feasibility of the use of a mobile activity tracker in patients with rheumatic diseases.

An e-health interactive self-assessment website (Sanoia®) in rheumatoid arthritis. A 12-month randomized controlled trial in 320 patients.

INTRODUCTION: Sanoia is an online interactive electronic e-health platform developed to allow patient self-assessment and self-monitoring. The objective was to assess in rheumatoid arthritis (RA) patients, the efficacy on patient-physician interactions, of giving access to Sanoia. METHODS: In this French, multi-center, 12-months randomized controlled trial (CarNET: NCT02200068), patients with RA and internet access were randomized to: access without incentives to the Sanoia platform after minimal training, or usual care. The primary outcome was the change from baseline in patient-physician interactions, by the patient-reported Perceived Efficacy in Patient-Physician Interactions (PEPPI-5) questionnaire. The number of accesses to Sanoia was recorded and satisfaction with the platform was assessed through a 0-10 numeric rating scale. Analyses were in intention to treat (ITT), on SAS. RESULTS: Of 320 RA patients (159 Sanoia versus 161 usual care), mean (standard deviation) age was 57.0 (12.7) years, mean (SD) disease duration was 14.6 (11.1) years, 216 (67.5%) were taking a biologic and 253 (79.1%) were female. Mean (SD) PEPPI scores at baseline and 12 months were 38.6 (8.2) and 39.2 (8.0) (delta=+0.60 [5.52]) versus 39.7 (7.3) and 38.8 (8.0) (delta=-0.91 [6.08]) in the Sanoia and control group, respectively (P=0.01). Although mean satisfaction with the platform was very high (1.46 [1.52]), 41 patients (25.7%) never accessed Sanoia. CONCLUSION: Giving RA patients access to the interactive Sanoia e-health platform led to a small improvement in patient-perceived patient-physician interactions. A disjunction between patient satisfaction and access to the platform was noted. E-Health platforms are promising in RA.

Flares assessed weekly in patients with rheumatoid arthritis or axial spondyloarthritis and relationship with physical activity measured using a connected activity tracker: a 3-month study.

BACKGROUND: The evolution of rheumatoid arthritis (RA) and axial spondyloarthritis (axSpA) is marked by flares, although their frequency is unclear. Flares may impact physical activity. Activity can be assessed objectively using activity trackers. The objective was to assess longitudinally the frequency of flares and the association between flares and objective physical activity. METHODS: This prospective observational study (ActConnect) included patients with definite clinician-confirmed RA or axSpA, owning a smartphone. During 3 months, physical activity was assessed continuously by number of steps/day, using an activity tracker, and disease flares were self-assessed weekly using a specific flare question and, if relevant, the duration of the flare. The relationship between flares and physical activity for each week (time point) was assessed by linear mixed models. RESULTS: In all, 170/178 patients (91 patients with RA and 79 patients with axSpA; 1553 time points) were analysed: mean age was 45.5±12.4 years, mean disease duration was 10.3±8.7 years, 60 (35.3%) were men and 90 (52.9%) received biologics. The disease was well-controlled (mean Disease Activity Score 28: 2.3±1.2; mean Bath Ankylosing Spondylitis Disease Activity Index score: 3.3±2.1). Patients self-reported flares in 28.2%±28.1% of the weekly assessments. Most flares (78.9%±31.4%) lasted ≤3 days. Persistent flares lasting more than 3 days were independently associated with less weekly physical activity (p=0.03), leading to a relative decrease of 12%-21% and an absolute decrease ranging from 836 to 1462 steps/day. CONCLUSION: Flares were frequent but usually of short duration in these stable patients with RA and axSpA. Persistent flares were related to a moderate decrease in physical activity, confirming objectively the functional impact of patient-reported flares.

Evaluation of a prototype electronic personal health record for patients with idiopathic thrombocytopenic purpura.

BACKGROUND: Patients with rare diseases often lack information about the disease itself and appropriate health care, leading to poor quality of life. Personal health records provide health information which can then be shared between multiple health care providers. Personal health records may also offer a tool for capturing patients' reported outcomes, thus enhancing their empowerment and improving communication with health care professionals. We conducted a pilot study to evaluate the usability of Sanoia, a freely accessible personal health record, which was customized for patients with the rare disease, idiopathic thrombocytopenic purpura (ITP). METHODS: The Sanoia interface was expanded with ITP-specific tools. A prospective study was conducted at the referent center to evaluate the usability of this new interface (referred to here as the "tool") by patients. Forty-three patients were randomized into groups to use or to not use the tool. Its use was evaluated by a specific questionnaire and by surveying individual patient adherence profiles. Evaluation of health-related quality of life using the ITP patient assessment questionnaire, was performed at baseline and after 1, 3, and 6 months via postal mail. RESULTS: The groups were similar at inclusion in terms of characteristics, including global quality of life. During the study period, the tool was used to update the personal records of 19/28 patients (68%), with a median of two connections to the tool (range 1-12) plus access by various health care professionals (n = 22). In addition, 15/19 (78%) patients used the "personal notes" section at least once. We observed no significant changes in quality of life between patients with or without the tool during the study period. CONCLUSION: This pilot study demonstrates the good usability of the new customized Sanoia interface for patients with ITP. Additional studies will increase its usability further, and its interface could be adapted for use with other rare chronic diseases.