Activity level classification algorithm using SHIMMER™ wearable sensors for individuals with rheumatoid arthritis

The Digital Way to Intercept Psoriatic Arthritis

Psoriasis (PsO) and Psoriatic Arthritis (PsA) are chronic, immune-mediated diseases that share common etiopathogenetic pathways. Up to 30% of PsO patient may later develop PsA. In nearly 75% of cases, skin psoriatic lesions precede arthritic symptoms, typically 10 years prior to the onset of joint symptoms, while PsO diagnosis occurring after the onset of arthritis is described only in 15% of cases. Therefore, skin involvement offers to the rheumatologist a unique opportunity to study PsA in a very early phase, having a cohort of psoriatic “risk patients” that may develop the disease and may benefit from preventive treatment. Progression from PsO to PsA is often characterized by non-specific musculoskeletal symptoms, subclinical synovio-entheseal inflammation, and occasionally asymptomatic digital swelling such as painless toe dactylitis, that frequently go unnoticed, leading to diagnostic delay. The early diagnosis of PsA is crucial for initiating a treatment prior the development of significant and permanent joint damage. With the ongoing development of pharmacological treatments, early interception of PsA has become a priority, but many obstacles have been reported in daily routine. The introduction of digital technology in rheumatology may fill the gap in the physician-patient relationship, allowing more targeted monitoring of PsO patients. Digital technology includes telemedicine, virtual visits, electronic health record, wearable technology, mobile health, artificial intelligence, and machine learning. Overall, this digital revolution could lead to earlier PsA diagnosis, improved follow-up and disease control as well as maximizing the referral capacity of rheumatic centers.

Digital Approaches for a Reliable Early Diagnosis of Psoriatic Arthritis

Psoriatic arthritis (PsA) is a chronic inflammatory disease that develops in up to 30% of patients with psoriasis. In the vast majority of cases, cutaneous symptoms precede musculoskeletal complaints. Progression from psoriasis to PsA is characterized by subclinical synovio-entheseal inflammation and often non-specific musculoskeletal symptoms that are frequently unreported or overlooked. With the development of increasingly effective therapies and a broad drug armamentarium, prevention of arthritis development through careful clinical monitoring has become priority. Identifying high-risk psoriasis patients before PsA onset would ensure early diagnosis, increased treatment efficacy, and ultimately better outcomes; ideally, PsA development could even be averted. However, the current model of care for PsA offers only limited possibilities of early intervention. This is attributable to the large pool of patients to be monitored and the limited resources of the health care system in comparison. The use of digital technologies for health (eHealth) could help close this gap in care by enabling faster, more targeted and more streamlined access to rheumatological care for patients with psoriasis. eHealth solutions particularly include telemedicine, mobile technologies, and symptom checkers. Telemedicine enables rheumatological visits and consultations at a distance while mobile technologies can improve monitoring by allowing patients to self-report symptoms and disease-related parameters continuously. Symptom checkers have the potential to direct patients to medical attention at an earlier point of their disease and therefore minimizing diagnostic delay. Overall, these interventions could lead to earlier diagnoses of arthritis, improved monitoring, and better disease control while simultaneously increasing the capacity of referral centers.

Determining Physical Activity Characteristics from Wristband Data for Use in Automated Insulin Delivery Systems

Algorithms that can determine the type of physical activity (PA) and quantify the intensity can allow precision medicine approaches, such as automated insulin delivery systems that modulate insulin administration in response to PA. In this work, data from a multi-sensor wristband is used to design classifiers to distinguish among five different physical states (PS) (resting, activities of daily living, running, biking, and resistance training), and to develop models to estimate the energy expenditure (EE) of the PA for diabetes therapy. The data collected are filtered, features are extracted from the reconciled signals, and the extracted features are used by machine learning algorithms, including deep-learning techniques, to obtain accurate PS classification and EE estimation. The various machine learning techniques have different success rates ranging from 75.7% to 94.8% in classifying the five different PS. The deep neural network model with long short-term memory has 94.8% classification accuracy. We achieved 0.5 MET (Metabolic Equivalent of Task) root-mean-square error for EE estimation accuracy, relative to indirect calorimetry with randomly selected testing data (10% of collected data). We also demonstrate a 5% improvement in PS classification accuracy and a 0.34 MET decrease in the mean absolute error when using multi-sensor approach relative to using only accelerometer data.

Physical Activity Comparison Between Body Sides in Hemiparetic Patients Using Wearable Motion Sensors in Free-Living and Therapy: A Case Series

Background: Physical activity (PA) is essential in stroke rehabilitation of hemiparetic patients to avoid health risks, and moderate to vigorous PA could promote patients' recovery. However, PA assessments are limited to clinical environments. Little is known about PA in unguided free-living. Wearable sensors could reveal patients' PA during rehabilitation, and day-long long-term measurements over several weeks might reveal recovery trends of affected and less-affected body sides.

Methods: We investigated PA in an observation study during outpatient rehabilitation in a day-care center. PA of affected and less-affected body sides, including upper and lower limbs were derived using wearable motion sensors. In this analysis we focused on PA during free-living and clinician guided therapies, and investigated differences between body-sides. Linear regressions were used to estimate metabolic equivalents for each limb at comparable scale. Non-parametric statistics were derived to quantify PA differences between body sides.

Results: We analyzed 102 full-day movement data recordings from eleven hemiparetic patients during individual rehabilitation periods up to 79 days. The comparison between free-living and clinician guided therapy showed on average 16.1 % higher PA in the affected arm during therapy and 5.3 % higher PA in the affected leg during therapy. Average differences between free-living and therapy in the less-affected side were below 4.5 %.

Conclusion: We analyzed PA of patients with a hemiparesis in two distinct rehabilitation settings, including free-living and clinician guided therapies over several weeks and compared MET values of affected and less-affected body sides. In particular, we investigated PA using individual regression models for each limb. We demonstrated that wearable motion sensors provide insights in patient's PA during rehabilitation. Although, no clear PA trends were found, our analysis showed patients' tendency to sedentary behavior, confirming previous lab study results. Our PA analysis approach could be used beyond clinical rehabilitation to devise personalized patient and limb-specific exercise recommendations in future remote rehabilitation.

Measuring the impact of ambulatory red blood cell transfusion on home functional status: study protocol for a pilot randomized controlled trial

Background

Red blood cell (RBC) transfusion is frequently employed in both ambulatory and hospital environments with the aim of improving patient functional status. In the ambulatory setting, this practice is particularly common in patients with malignancy due to anemia associated with their cancer therapy. Increasingly, the efficacy of this US$10.5 billion per year practice has been called into question. While it is often standard of care for patients with chemotherapy-induced anemia to receive ambulatory RBC transfusions, it is unclear to what extent such transfusions affect home functional status. It is also unclear whether or not changes in functional status in this population can be objectively quantified using wearable activity monitors. We propose to directly measure the impact of outpatient RBC transfusions on at-home functional status by recording several physiological parameters and quantifiable physical activity metrics, e.g., daily energy expenditure and daily total step count, using the ActiGraph wGT3X-BT. This device is an accelerometer-based wearable activity monitor similar in size to a small watch and is worn at the waist. Study participants will wear the device during the course of their daily activities giving us quantifiable insight into activity levels in the home environment.

Methods/design

This will be a randomized crossover pilot clinical trial with a participant study duration of 28 days. The crossover nature allows each patient to serve as their own control. Briefly, patients presenting at a tertiary medical center’s Ambulatory Infusion Center (AIC) will be randomized to either: (1) receive an RBC transfusion as scheduled (transfusion) or (2) abstain from the scheduled transfusion (no transfusion). After an appropriate washout period, participants will crossover from the transfusion arm to the no-transfusion arm or vice versa. Activity levels will be recorded continuously throughout the study using an accelerometry monitor. In addition to device data, functional status and health outcomes will be collected via a weekly telephone interview. The primary outcome measure will be daily energy expenditure. Performance metrics, such as step count changes, will also be evaluated. Additional secondary outcome measures will include daily sedentary time and Patient-reported Outcomes Measurement Information System (PROMIS) Global 10 Survey scores.

Discussion

This trial will provide important information on the feasibility and utility of using accelerometry monitors to directly assess the impact of RBC transfusion on patients’ functional status. The results of the study will inform the merit and methods of a more definitive future trial evaluating the impact of ambulatory RBC transfusions in the target population.

Trial registration

ClinicalTrials.gov, identifier: NCT02835937. Registered on 15 July 2016.

Electronic supplementary material

The online version of this article (doi:10.1186/s13063-017-1873-z) contains supplementary material, which is available to authorized users.

Accelerometry measuring the outcome of robot-supported upper limb training in chronic stroke: a randomized controlled trial

PURPOSE

This study aims to assess the extent to which accelerometers can be used to determine the effect of robot-supported task-oriented arm-hand training, relative to task-oriented arm-hand training alone, on the actual amount of arm-hand use of chronic stroke patients in their home situation.

METHODS

This single-blind randomized controlled trial included 16 chronic stroke patients, randomly allocated using blocked randomization (n = 2) to receive task-oriented robot-supported arm-hand training or task-oriented (unsupported) arm-hand training. Training lasted 8 weeks, 4 times/week, 2 × 30 min/day using the (T-)TOAT ((Technology-supported)-Task-Oriented-Arm-Training) method. The actual amount of arm-hand use, was assessed at baseline, after 8 weeks training and 6 months after training cessation. Duration of use and intensity of use of the affected arm-hand during unimanual and bimanual activities were calculated.

RESULTS

Duration and intensity of use of the affected arm-hand did not change significantly during and after training, with or without robot-support (i.e. duration of use of unimanual use of the affected arm-hand: median difference of -0.17% in the robot-group and -0.08% in the control group between baseline and after training cessation; intensity of the affected arm-hand: median difference of 3.95% in the robot-group and 3.32% in the control group between baseline and after training cessation). No significant between-group differences were found.

CONCLUSIONS

Accelerometer data did not show significant changes in actual amount of arm-hand use after task-oriented training, with or without robot-support. Next to the amount of use, discrimination between activities performed and information about quality of use of the affected arm-hand are essential to determine actual arm-hand performance.

TRIAL REGISTRATION

Controlled-trials.com ISRCTN82787126.