machine-learning model can predict health conditions of people with MS during periods of stay-at-home, researchers say.
The need for social distancing and self-isolation has been well-documented during the COVID-19 pandemic. But for people with chronic illnesses like multiple sclerosis (MS), the negative effects of these measures can be significant.
Now, a new study has used machine learning to predict how MS patients’ health may be affected by extended periods of time spent at home.
The study, which was conducted by researchers at the University of California, San Francisco (UCSF), looked at data from more than 1,600 people with MS who were enrolled in the US Expanded Disability Status Scale (EDSS) clinical trial.
Using this data, the researchers created a machine-learning model that was able to predict a patient’s Expanded Disability Severity Scale (EDSS) score at the end of a 12-week stay-at-home period.
The model was then used to predict the health outcomes of a group of MS patients who were not enrolled in the clinical trial, but who had similar demographic characteristics.
The results of the study, which are published in the journal Nature Medicine, showed that the machine-learning model was able to accurately predict the health outcomes of the stay-at-home group.
Specifically, the model was able to predict an increase in EDSS score by an average of 0.39 points for every four weeks of stay-at-home periods.
This may not sound like much, but the researchers say that it is a significant increase, particularly given the fact that the average EDSS score for people with MS is 3.0.
The findings of the study suggest that extended periods of time spent at home can have a negative impact on the health of people with MS.
The study also highlights the potential of machine learning to predict health outcomes in other chronic illnesses.
The UCSF team is now working on a larger study that will use machine learning to predict health outcomes in a variety of chronic illnesses, including type 1 diabetes, heart disease, and cancer.
A recent study has found that a machine learning model can predict the health conditions of people with multiple sclerosis (MS) during periods of stay-at-home.
The study, conducted by researchers at the University of British Columbia, used data from 649 people with MS who were part of the North American Research Committee on Multiple Sclerosis (NARCOMS) registry.
The machine learning model was able to accurately predict the health conditions of the participants during periods of stay-at-home, as well as during periods of time when they were not staying at home.
The model was also able to accurately predict the health conditions of the participants when they were not taking any disease-modifying therapies (DMTs).
This is a significant finding, as it suggests that the machine learning model may be able to help predict the health outcomes of people with MS who are not currently taking any DMTs.
The study highlights the potential of machine learning in predicting the health outcomes of people with chronic illnesses.
The findings of this study will need to be replicated in a larger population of people with MS before any definitive conclusions can be drawn.
