Article Type
Changed
Mon, 10/23/2023 - 14:10

 

A tool kit combining a wearable device with automated algorithms allows for the passive monitoring of disease parameters in people with multiple sclerosis (MS) and may even be able to predict the course of the disease, suggests a pilot study.

Twenty patients were enrolled, only half of whom correctly completed all of the assessments and wore the included smartwatch regularly. Importantly, the data reported back for analysis was in line with expectations, and the patient feedback was positive.

The tool kit “seems feasible and usable to remotely monitor multiple domains of health status in people with multiple sclerosis,” conclude Ludovico Pedullà, PhD, Italian Multiple Sclerosis Foundation, Genoa, and colleagues.

Further analysis of the dataset, including the artificial intelligence and machine-learning algorithms, may allow the prediction of “relevant changes throughout the course of multiple sclerosis” and anticipate the need for therapeutic interventions.

The findings were presented at the 9th Joint ECTRIMS-ACTRIMS meeting.
 

Leveraging big data to improve outcomes

The authors note that the primary aim of the pan-European ALAMEDA project is to leverage “big data” through artificial intelligence and machine learning to provide “clinically actionable information” on patients with brain disorders that “complements medical recommendations” and thus improves treatment.

For the current pilot study, the researchers developed an integrated platform to collect patient-centered data from wearables and mobile devices using digital patient-reported outcomes (ePROs), with the aim of testing the resulting tool kit’s feasibility and usability in people with MS.

Dr. Pedullà said that they wanted to have “passive monitoring” of patients over the course of their daily lives and therefore searched for the best devices and the most relevant patient reported outcomes as well as used “innovative algorithms” to analyze the data to try to predict the disease course.

To reduce dropouts and increase adherence to the tool kit, they described the project to patients with MS and asked for their feedback to determine whether what they had designed was feasible from the patient perspective, Dr. Pedullà said.

This led to some changes in the way data were collected, and the team developed a social network channel so patients would be able to ask for support and stay engaged in the study.
 

Feasible with high levels of confidence

Twenty people with relapsing-remitting MS were enrolled, of whom 14 were women. The mean age was 37.8 years, and the mean disease duration was 9.1 years. The mean Expanded Disability Status Scale was 2.2.

The participants were asked to use the tool kit for 1 year, with half reaching the 6-month milestone. Participants correctly completed 53% of the scheduled ePROs and regularly wore the smartwatch without reporting discomfort.

The team reports that the data from the tool kit “are in line with those reported in the literature.”

It showed that participants took an average of 8,415 steps per day and completed 9.8 minutes of vigorous activity and 14.5 minutes of moderate activity daily. Daily sedentary minutes were 705.1.

Patients had a mean Perceived Deficit Questionnaire score of 25.2, a Beck Anxiety Inventory score of 17.3, a score on the 12-Item Multiple Sclerosis Walking Scale of 37.2, and an arm function on the Multiple Sclerosis Questionnaire of 47.4.

The mean Modified Fatigue Impact Scale score was 18.5, and the Pittsburgh Sleep Quality Index score was 25.2. The System Usability Scale revealed “high levels of confidence” with the tool kit, the team says, as well as “very high” intention of using it in the future.

Dr. Pedullà said that the researchers now want to evaluate the feasibility of the tool kit further by analyzing the adherence and usability data and targeting it to the patients who are most likely to use it.

They also want to determine not only whether the use of wearables in this way can predict relapse in multiple sclerosis but also disease progression, particularly as the current definitions are evolving.
 

 

 

Reducing daily step count

Approached for comment, Riley M. Bove, MD, MSc, Assistant Professor, UCSF Weill Institute for Neurosciences, San Francisco, said that the study is “very interesting and in line with what has been previously published.”

She pointed to a recent study that she co-authored, in which remote monitoring via a continuous step counter revealed that a decreasing average daily step count was associated with the worsening of standard ambulatory measures.

“There are nice benefits of an integrated platform” such as what was used in the current study, Dr. Bove noted, adding that it is “even better if it can also send the data to clinicians.”

The ALAMEDA project has received funding from the European Union’s Horizon 2020 research and innovation program. No relevant financial relationships declared.

A version of this article first appeared on Medscape.com.

Meeting/Event
Publications
Topics
Sections
Meeting/Event
Meeting/Event

 

A tool kit combining a wearable device with automated algorithms allows for the passive monitoring of disease parameters in people with multiple sclerosis (MS) and may even be able to predict the course of the disease, suggests a pilot study.

Twenty patients were enrolled, only half of whom correctly completed all of the assessments and wore the included smartwatch regularly. Importantly, the data reported back for analysis was in line with expectations, and the patient feedback was positive.

The tool kit “seems feasible and usable to remotely monitor multiple domains of health status in people with multiple sclerosis,” conclude Ludovico Pedullà, PhD, Italian Multiple Sclerosis Foundation, Genoa, and colleagues.

Further analysis of the dataset, including the artificial intelligence and machine-learning algorithms, may allow the prediction of “relevant changes throughout the course of multiple sclerosis” and anticipate the need for therapeutic interventions.

The findings were presented at the 9th Joint ECTRIMS-ACTRIMS meeting.
 

Leveraging big data to improve outcomes

The authors note that the primary aim of the pan-European ALAMEDA project is to leverage “big data” through artificial intelligence and machine learning to provide “clinically actionable information” on patients with brain disorders that “complements medical recommendations” and thus improves treatment.

For the current pilot study, the researchers developed an integrated platform to collect patient-centered data from wearables and mobile devices using digital patient-reported outcomes (ePROs), with the aim of testing the resulting tool kit’s feasibility and usability in people with MS.

Dr. Pedullà said that they wanted to have “passive monitoring” of patients over the course of their daily lives and therefore searched for the best devices and the most relevant patient reported outcomes as well as used “innovative algorithms” to analyze the data to try to predict the disease course.

To reduce dropouts and increase adherence to the tool kit, they described the project to patients with MS and asked for their feedback to determine whether what they had designed was feasible from the patient perspective, Dr. Pedullà said.

This led to some changes in the way data were collected, and the team developed a social network channel so patients would be able to ask for support and stay engaged in the study.
 

Feasible with high levels of confidence

Twenty people with relapsing-remitting MS were enrolled, of whom 14 were women. The mean age was 37.8 years, and the mean disease duration was 9.1 years. The mean Expanded Disability Status Scale was 2.2.

The participants were asked to use the tool kit for 1 year, with half reaching the 6-month milestone. Participants correctly completed 53% of the scheduled ePROs and regularly wore the smartwatch without reporting discomfort.

The team reports that the data from the tool kit “are in line with those reported in the literature.”

It showed that participants took an average of 8,415 steps per day and completed 9.8 minutes of vigorous activity and 14.5 minutes of moderate activity daily. Daily sedentary minutes were 705.1.

Patients had a mean Perceived Deficit Questionnaire score of 25.2, a Beck Anxiety Inventory score of 17.3, a score on the 12-Item Multiple Sclerosis Walking Scale of 37.2, and an arm function on the Multiple Sclerosis Questionnaire of 47.4.

The mean Modified Fatigue Impact Scale score was 18.5, and the Pittsburgh Sleep Quality Index score was 25.2. The System Usability Scale revealed “high levels of confidence” with the tool kit, the team says, as well as “very high” intention of using it in the future.

Dr. Pedullà said that the researchers now want to evaluate the feasibility of the tool kit further by analyzing the adherence and usability data and targeting it to the patients who are most likely to use it.

They also want to determine not only whether the use of wearables in this way can predict relapse in multiple sclerosis but also disease progression, particularly as the current definitions are evolving.
 

 

 

Reducing daily step count

Approached for comment, Riley M. Bove, MD, MSc, Assistant Professor, UCSF Weill Institute for Neurosciences, San Francisco, said that the study is “very interesting and in line with what has been previously published.”

She pointed to a recent study that she co-authored, in which remote monitoring via a continuous step counter revealed that a decreasing average daily step count was associated with the worsening of standard ambulatory measures.

“There are nice benefits of an integrated platform” such as what was used in the current study, Dr. Bove noted, adding that it is “even better if it can also send the data to clinicians.”

The ALAMEDA project has received funding from the European Union’s Horizon 2020 research and innovation program. No relevant financial relationships declared.

A version of this article first appeared on Medscape.com.

 

A tool kit combining a wearable device with automated algorithms allows for the passive monitoring of disease parameters in people with multiple sclerosis (MS) and may even be able to predict the course of the disease, suggests a pilot study.

Twenty patients were enrolled, only half of whom correctly completed all of the assessments and wore the included smartwatch regularly. Importantly, the data reported back for analysis was in line with expectations, and the patient feedback was positive.

The tool kit “seems feasible and usable to remotely monitor multiple domains of health status in people with multiple sclerosis,” conclude Ludovico Pedullà, PhD, Italian Multiple Sclerosis Foundation, Genoa, and colleagues.

Further analysis of the dataset, including the artificial intelligence and machine-learning algorithms, may allow the prediction of “relevant changes throughout the course of multiple sclerosis” and anticipate the need for therapeutic interventions.

The findings were presented at the 9th Joint ECTRIMS-ACTRIMS meeting.
 

Leveraging big data to improve outcomes

The authors note that the primary aim of the pan-European ALAMEDA project is to leverage “big data” through artificial intelligence and machine learning to provide “clinically actionable information” on patients with brain disorders that “complements medical recommendations” and thus improves treatment.

For the current pilot study, the researchers developed an integrated platform to collect patient-centered data from wearables and mobile devices using digital patient-reported outcomes (ePROs), with the aim of testing the resulting tool kit’s feasibility and usability in people with MS.

Dr. Pedullà said that they wanted to have “passive monitoring” of patients over the course of their daily lives and therefore searched for the best devices and the most relevant patient reported outcomes as well as used “innovative algorithms” to analyze the data to try to predict the disease course.

To reduce dropouts and increase adherence to the tool kit, they described the project to patients with MS and asked for their feedback to determine whether what they had designed was feasible from the patient perspective, Dr. Pedullà said.

This led to some changes in the way data were collected, and the team developed a social network channel so patients would be able to ask for support and stay engaged in the study.
 

Feasible with high levels of confidence

Twenty people with relapsing-remitting MS were enrolled, of whom 14 were women. The mean age was 37.8 years, and the mean disease duration was 9.1 years. The mean Expanded Disability Status Scale was 2.2.

The participants were asked to use the tool kit for 1 year, with half reaching the 6-month milestone. Participants correctly completed 53% of the scheduled ePROs and regularly wore the smartwatch without reporting discomfort.

The team reports that the data from the tool kit “are in line with those reported in the literature.”

It showed that participants took an average of 8,415 steps per day and completed 9.8 minutes of vigorous activity and 14.5 minutes of moderate activity daily. Daily sedentary minutes were 705.1.

Patients had a mean Perceived Deficit Questionnaire score of 25.2, a Beck Anxiety Inventory score of 17.3, a score on the 12-Item Multiple Sclerosis Walking Scale of 37.2, and an arm function on the Multiple Sclerosis Questionnaire of 47.4.

The mean Modified Fatigue Impact Scale score was 18.5, and the Pittsburgh Sleep Quality Index score was 25.2. The System Usability Scale revealed “high levels of confidence” with the tool kit, the team says, as well as “very high” intention of using it in the future.

Dr. Pedullà said that the researchers now want to evaluate the feasibility of the tool kit further by analyzing the adherence and usability data and targeting it to the patients who are most likely to use it.

They also want to determine not only whether the use of wearables in this way can predict relapse in multiple sclerosis but also disease progression, particularly as the current definitions are evolving.
 

 

 

Reducing daily step count

Approached for comment, Riley M. Bove, MD, MSc, Assistant Professor, UCSF Weill Institute for Neurosciences, San Francisco, said that the study is “very interesting and in line with what has been previously published.”

She pointed to a recent study that she co-authored, in which remote monitoring via a continuous step counter revealed that a decreasing average daily step count was associated with the worsening of standard ambulatory measures.

“There are nice benefits of an integrated platform” such as what was used in the current study, Dr. Bove noted, adding that it is “even better if it can also send the data to clinicians.”

The ALAMEDA project has received funding from the European Union’s Horizon 2020 research and innovation program. No relevant financial relationships declared.

A version of this article first appeared on Medscape.com.

Publications
Publications
Topics
Article Type
Sections
Disallow All Ads
Content Gating
No Gating (article Unlocked/Free)
Alternative CME
Disqus Comments
Default
Use ProPublica
Hide sidebar & use full width
render the right sidebar.
Conference Recap Checkbox
Not Conference Recap
Clinical Edge
Display the Slideshow in this Article
Medscape Article
Display survey writer
Reuters content
Disable Inline Native ads
WebMD Article