Machine learning helps spot gait problems in individuals with multiple sclerosis
2021-03-29
(Press-News.org) CHAMPAIGN, Ill. -- Monitoring the progression of multiple sclerosis-related gait issues can be challenging in adults over 50 years old, requiring a clinician to differentiate between problems related to MS and other age-related issues. To address this problem, researchers are integrating gait data and machine learning to advance the tools used to monitor and predict disease progression.
A new study of this approach led by University of Illinois Urbana Champaign graduate student Rachneet Kaur, kinesiology and community health professor Manuel Hernandez and industrial and enterprise engineering and mathematics professor Richard Sowers is published in the journal Institute of Electrical and Electronics Engineers Transactions on Biomedical Engineering.
Multiple sclerosis can present itself in many ways in the approximately 2 million people that it affects globally, and walking problems are a common symptom. About half of the patients need walking assistance within 15 years of onset, the study reports.
"We wanted to get a sense of the interactions between aging and concurrent MS disease-related changes, and whether we can also differentiate between the two in older adults with MS," Hernandez said. "Machine-learning techniques seem to work particularly well at spotting complex hidden changes in performance. We hypothesized that these analysis techniques might also be useful in predicting sudden gait changes in persons with MS."
Using an instrumented treadmill, the team collected gait data - normalized for body size and demographics - from 20 adults with MS and 20 age-, weight-, height- and gender-matched older adults without MS. The participants walked at a comfortable pace for up to 75 seconds while specialized software captured gait events, corresponding ground reaction forces and center-of-pressure positions during each walk. The team extracted each participant's characteristic spatial, temporal and kinetic features in their strides to examine variations in gait during each trial.
Changes in various gait features, including a data feature called the butterfly diagram, helped the team detect differences in gait patterns between participants. The diagram gains its name from the butterfly-shaped curve created from the repeated center-of-pressure trajectory for multiple continuous strides during a subject's walk and is associated with critical neurological functions, the study reports.
Click here to see a video describing this research.
"We study the effectiveness of a gait dynamics-based machine-learning framework to classify strides of older persons with MS from healthy controls to generalize across different walking tasks and over new subjects," Kaur said. "This proposed methodology is an advancement toward developing an assessment marker for medical professionals to predict older people with MS who are likely to have a worsening of symptoms in the near term."
Future studies can provide more thorough examinations to manage the study's small cohort size, Sowers said.
"Biomechanical systems, such as walking, are poorly modeled systems, making it difficult to spot problems in a clinical setting," Sowers said. "In this study, we are trying to extract conclusions from data sets that include many measurements of each individual, but a small number of individuals. The results of this study make significant headway in the area of clinical machine learning-based disease-prediction strategies."
INFORMATION:
Hernandez also is affiliated with the Beckman Institute of Advanced Science and Technology and the the Carle Illinois College of Medicine.
Editor's notes:
To reach Rachneet Kaur, email rk4@illinois.edu.
To reach Manuel Hernandez, email mhernand@illinois.edu.
To reach Richard Sowers, call 217-333-6246; email r-sowers@illinois.edu.
The paper "Predicting multiple sclerosis from gait dynamics using an
instrumented treadmill - A machine learning approach" is available online and from the U. of I. News. DOI: 10.1109/TBME.2020.3048142
[Attachments] See images for this press release:
ELSE PRESS RELEASES FROM THIS DATE:
2021-03-29
United Methodist churches -- whether the congregation is white or not -- have higher attendance when located within white neighborhoods. But racial diversity within a church is associated with higher average attendance over time, according to a new study.
"This is a startling contrast to previous research that reported multiracial congregations are less stable," said lead author Kevin D. Dougherty, Ph.D., associate professor of sociology at Baylor University.
The study is published in the journal Social Forces.
Previous research has found that it is difficult for congregations to build and sustain racially diverse memberships, ...
2021-03-28
A new study suggests that clearing the invasive woody weed Prosopis julifora and grassland restoration in Baringo County, Kenya, may have significant financial benefits for local stakeholders and contribute to climate change mitigation.
Climate change, land degradation, and invasive alien species (IAS) such as Prosopis julifora are major threats to people's livelihoods in arid and semi-arid areas with each of these having negative impacts on ecosystem services - including vegetation biomass, which is a prime resource for pastoralists and agro-pastoralists.
The team, comprising PhD students and established scientists from four countries and different ...
2021-03-26
LOS ALAMOS, N.M., March 26, 2021--New research has demonstrated that a magnetic uranium compound can have strong thermoelectric properties, generating four times the transverse voltage from heat than the previous record in a cobalt-manganese-gallium compound. The result unlocks a new potential for the actinide elements at the bottom of the periodic table and point to a fresh direction in research on topological quantum materials.
"We found that the large spin-orbit coupling and strong electronic correlations in a system of uranium-cobalt-aluminum doped with ruthenium resulted in a colossal anomalous Nernst conductivity," said Filip Ronning, lead investigator on the paper published today in Science Advances. Ronning ...
2021-03-26
Presents a brief overview of the eight COVID-19 editorials published in DMPHP over the past year and using them as a framework to follow the evolution of the Pandemic over time. A review of the salient epidemiological and clinical dimensions of COVID-19 over time is given as well as a discussion of the medical and public health impacts of the disease and the interventions and policies put in place to contain and mediate the virus.
The concluding discussion questions the validity of the criteria used in selection of priority groups for vaccination in the US and notes that had a uniform program supporting the immunization of all over age 65 (accounting for 80% ...
2021-03-26
How do different parts of the body communicate? Scientists at St. Jude are studying how signals sent from skeletal muscle affect the brain.
The team studied fruit flies and cutting-edge brain cell models called organoids. They focused on the signals muscles send when stressed. The researchers found that stress signals rely on an enzyme called Amyrel amylase and its product, the disaccharide maltose.
The scientists showed that mimicking the stress signals can protect the brain and retina from aging. The signals work by preventing the buildup of misfolded protein aggregates. Findings suggest that tailoring this signaling may potentially help combat neurodegenerative conditions like age-related dementia and Alzheimer's disease.
"We found that a stress response ...
2021-03-26
The Environmental Protection Agency (EPA) is underestimating methane emissions from oil and gas production in its annual Inventory of U.S. Greenhouse Gas Emissions and Sinks, according to new research from the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS). The research team found 90 percent higher emissions from oil production and 50 percent higher emissions for natural gas production than EPA estimated in its latest inventory.
The paper is published in the journal Atmospheric Chemistry and Physics.
The research team, led by Joannes Maasakkers, a former graduate student at SEAS, developed a method to trace and map ...
2021-03-26
Australian researchers have discovered a new way to target an aggressive childhood cancer, neuroblastoma, one of the most common and dangerous cancers in young children.
The discovery may also have important implications for some other aggressive cancers in children, including certain brain tumours, as well as some adult cancers, including ovarian and prostate cancer.
The new research, led by scientists at Children's Cancer Institute and published in Nature Communications, has discovered that a cellular protein called ALYREF plays a crucial role in accelerating the effects of the cancer driver gene, MYCN, in neuroblastoma.
Scientists have known for some time that the one third of children with neuroblastoma who have ...
2021-03-26
Tumor targeting and intratumoral penetration are long-standing issues for cancer therapeutics.
Researchers from the Institute of Process Engineering (IPE) of the Chinese Academy of Sciences and the University of Chinese Academy of Sciences (UCAS) have developed a new platelet-based formulation which demonstrated potent therapeutic effects against cancer in murine models.
The scientists utilized the aggregation and activation features of the platelets to address issues of tumor targeting and intratumoral penetration. Upon carrying photothermal nanoparticles and immunostimulators, this biomimetic formulation also achieves an efficient combination therapy against multiple types of cancer.
This study was published in Science Advances on March 26.
Recently, photothermal ...
2021-03-26
One million species are under threat of extinction worldwide, primarily due to adverse human impact. The loss of a species is an ethical tragedy, but additionally, it can have dramatic effects on the functioning of ecosystems on Earth. In each ecosystem, species have their roles, just like actors do in a play. These roles depend on the characteristics of the species, like their size, weight, shape, reproductive capacity, or the food resources they use. If some species are similar, they can sometimes substitute each other and keep the ecosystem going even if one of them is lost. However, the accumulated ...
2021-03-26
For people with tooth decay, drinking a cold beverage can be agony.
"It's a unique kind of pain," says David Clapham, vice president and chief scientific officer of the Howard Hughes Medical Institute (HHMI). "It's just excruciating."
Now, he and an international team of scientists have figured out how teeth sense the cold and pinpointed the molecular and cellular players involved. In both mice and humans, tooth cells called odontoblasts contain cold-sensitive proteins that detect temperature drops, the team reports March 26, 2021, in the journal Science Advances. Signals from these cells can ultimately trigger a jolt of pain to the brain.
The work offers an explanation for how one ...
LAST 30 PRESS RELEASES:
[Press-News.org] Machine learning helps spot gait problems in individuals with multiple sclerosis
