Predicting Multiple Sclerosis Outcomes During the COVID-19 Stay-at-home Period: Observational Study Using Passively Sensed Behaviors and Digital Phenotyping

Chikersal, Prerna; Venkatesh, Shruthi; Masown, Karman; Walker, Elizabeth; Quraishi, Danyal; Dey, Anind K.; Goel, Mayank; Xia, Zongqi

doi:10.2196/38495

Cited by 12 publications

(12 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared the regression results to random – that predicts a random number within the expected range – and average – that always predicts the average score in the dataset – baselines. To evaluate models’ performance, we calculate the F1-score (F1) for classification tasks and mean absolute error (MAE) for regression tasks over stratified group 5-fold cross-validation (SG5FCV), similar to 22 , 23 . We split the data into non-overlapping participant training and test sets to investigate the performance of our approach to a new, unseen group of subjects.…”

Section: Resultsmentioning

confidence: 99%

“…Such devices have already been used to monitor the fatigability 5 , 18 , fatigue 4 , EDSS level 19 – 22 and other outcomes of PwMS 23 . For instance, Motl et al use a two-minute walk test 19 and the timed 25-foot walk test 20 , which reflect the walking disability level, to approximate the EDSS level.…”

Section: Introductionmentioning

confidence: 99%

“…Indeed, a recent analysis of 119 clinical trials related to MS registered in ClinicalTrials.gov shows that 77.31% of the studies focus on motor function tracking and only 5.88% on more novel digital measures (e.g., sleep and cognition tracking) 17 , showing the need for more comprehensive analysis. Other studies use data collected in a specific context, e.g., during the COVID-19 pandemic 23 or at home 24 , which are difficult to generalize to natural settings. The majority of these studies use simple statistical analysis to show a correlation between disease and objective measures 5 , 25 – 27 , which are not meant for automated predictions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Modeling multiple sclerosis using mobile and wearable sensor data

Gashi,

Oldrati,

Moebus

et al. 2024

npj Digit. Med.

View full text Add to dashboard Cite

Multiple sclerosis (MS) is a neurological disease of the central nervous system that is the leading cause of non-traumatic disability in young adults. Clinical laboratory tests and neuroimaging studies are the standard methods to diagnose and monitor MS. However, due to infrequent clinic visits, it is fundamental to identify remote and frequent approaches for monitoring MS, which enable timely diagnosis, early access to treatment, and slowing down disease progression. In this work, we investigate the most reliable, clinically useful, and available features derived from mobile and wearable devices as well as their ability to distinguish people with MS (PwMS) from healthy controls, recognize MS disability and fatigue levels. To this end, we formalize clinical knowledge and derive behavioral markers to characterize MS. We evaluate our approach on a dataset we collected from 55 PwMS and 24 healthy controls for a total of 489 days conducted in free-living conditions. The dataset contains wearable sensor data – e.g., heart rate – collected using an arm-worn device, smartphone data – e.g., phone locks – collected through a mobile application, patient health records – e.g., MS type – obtained from the hospital, and self-reports – e.g., fatigue level – collected using validated questionnaires administered via the mobile application. Our results demonstrate the feasibility of using features derived from mobile and wearable sensors to monitor MS. Our findings open up opportunities for continuous monitoring of MS in free-living conditions and can be used to evaluate and guide the effectiveness of treatments, manage the disease, and identify participants for clinical trials.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling multiple sclerosis using mobile and wearable sensor data

Gashi,

Oldrati,

Moebus

et al. 2024

npj Digit. Med.

View full text Add to dashboard Cite

show abstract

“…This cross-sectional study included 368 participants (primary cohort) who enrolled in a clinicbased prospective cohort study (Prospective Investigation of Multiple Sclerosis in the Three Rivers Region, PROMOTE; Pittsburgh, PA) during 2017-2021 (Figure 1). [31][32][33][34][35][36][37][38][39][40][41][42] The cohort enrollment criteria included adults 18 years or older with a neurologist-confirmed diagnosis of MS according to the 2017 McDonald criteria. Given the clinical outcome of interest is relapse event indicative of inflammatory disease activity, we included pwMS of relapsing remitting (RRMS) and secondary progressive (SPMS) type and excluded primary progressive type (PPMS), which is not characterized by relapse events.…”

Section: Study Design Participants and Samplesmentioning

confidence: 99%

Aging-dependent Change in Th17 and Cytokine Response in Multiple Sclerosis

Zhu,

Revu,

Chen

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Multiple sclerosis (MS) is a chronic autoimmune disease damaging the central nervous system. Diminished inflammatory disease activities (DAs) as people with MS (pwMS) age justified randomized clinical trials assessing disease-modifying therapy (DMT) discontinuation in older pwMS given the concern for risk outweighing benefit. Objective: This study aims to examine the effect of age on DAs and the peripheral production of Myelin Basic Protein (MBP)-driven cytokine response in pwMS. Methods: We included the clinical data of 368 adult pwMS between 2017 and 2021 from a clinic-based registry. In a subset of 80 participants, we isolated fresh peripheral blood mononuclear cells (PBMCs) and cultured with 50 μg/ml of MBP for 24 hours. We assayed cell culture supernatants for IL-17 and IFN-gamma; using Enzyme-Linked Immunosorbent Assay. We further analyzed a subset of the supernatant samples using the Luminex xMAP platform human cytokine/chemokine array. We examined associations between age and inflammatory DA [annualized relapse rate (ARR)] as well as age and MBP-stimulated cytokine production (by cultured PBMC) using covariate-adjusted linear regression. We determined the extent of the MBP-driven cytokine responses in driving the association between age and ARR using mediation analyses. Results: Among the 386 pwMS (mean age 53.1±12.6 years, 79.9% women, 92.1% non-Hispanic White), ARR declined with age (β=-0.003, p<0.001). Among the 80 pwMS with cultured PBMC, MBP-driven IL-17 production declined with age in women (β=-0.27, p=0.04) but not men (β=-0.1, p=0.73). MBP-driven IL-17 response partially mediated the association between older age and lower ARR (24.7% in women, 15.3% in men). Further, older pwMS (≥50 years) had significantly lower (IL-4, MCP2, MCP3, PDGF.AA, PDGF.AB.BB) and higher (Fractalkine, MDC) concentrations of several cytokines when compared to younger pwMS (<50 years). These cytokines affected the association between age and ARR in different ways, with some of them (MCP-2 and MDC) likely mediating the effect of age on ARR, while the others likely counteracting the effect of age on ARR. Conclusion: This study suggests some of the potential biological mechanisms driving aging-dependent decline in MS inflammatory DA.

show abstract

“…In this context, mobile applications (or mobile apps) have been used extensively to support CNSD patients with the regular monitoring or management of their disease [ 21 , 22 , 23 , 24 , 25 ], which is largely possible because of their sensing and communication capabilities and the fact that they are accessible, acceptable, and easily adopted [ 26 ]. In light of the COVID-19 pandemic, during which the enforcement of social isolation measures and consequent drastic behavioral changes were observed, the use of mobile apps to support patients with CNSDs, facilitate remote communication with the care team, and enable the tracking of disease progression, is both timely and necessary [ 27 , 28 , 29 ].…”

Section: Introductionmentioning

confidence: 99%

Mobile App Interventions for Parkinson’s Disease, Multiple Sclerosis and Stroke: A Systematic Literature Review

Triantafyllidis

Segkouli

Zygouris

et al. 2023

Sensors

View full text Add to dashboard Cite

Central nervous system diseases (CNSDs) lead to significant disability worldwide. Mobile app interventions have recently shown the potential to facilitate monitoring and medical management of patients with CNSDs. In this direction, the characteristics of the mobile apps used in research studies and their level of clinical effectiveness need to be explored in order to advance the multidisciplinary research required in the field of mobile app interventions for CNSDs. A systematic review of mobile app interventions for three major CNSDs, i.e., Parkinson’s disease (PD), multiple sclerosis (MS), and stroke, which impose significant burden on people and health care systems around the globe, is presented. A literature search in the bibliographic databases of PubMed and Scopus was performed. Identified studies were assessed in terms of quality, and synthesized according to target disease, mobile app characteristics, study design and outcomes. Overall, 21 studies were included in the review. A total of 3 studies targeted PD (14%), 4 studies targeted MS (19%), and 14 studies targeted stroke (67%). Most studies presented a weak-to-moderate methodological quality. Study samples were small, with 15 studies (71%) including less than 50 participants, and only 4 studies (19%) reporting a study duration of 6 months or more. The majority of the mobile apps focused on exercise and physical rehabilitation. In total, 16 studies (76%) reported positive outcomes related to physical activity and motor function, cognition, quality of life, and education, whereas 5 studies (24%) clearly reported no difference compared to usual care. Mobile app interventions are promising to improve outcomes concerning patient’s physical activity, motor ability, cognition, quality of life and education for patients with PD, MS, and Stroke. However, rigorous studies are required to demonstrate robust evidence of their clinical effectiveness.

show abstract

Predicting Multiple Sclerosis Outcomes During the COVID-19 Stay-at-home Period: Observational Study Using Passively Sensed Behaviors and Digital Phenotyping

Cited by 12 publications

References 66 publications

Modeling multiple sclerosis using mobile and wearable sensor data

Modeling multiple sclerosis using mobile and wearable sensor data

Aging-dependent Change in Th17 and Cytokine Response in Multiple Sclerosis

Mobile App Interventions for Parkinson’s Disease, Multiple Sclerosis and Stroke: A Systematic Literature Review

Contact Info

Product

Resources

About