PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Can a computer tell patients how their multiple sclerosis will progress?

Can a computer tell patients how their multiple sclerosis will progress?
2024-07-25
(Press-News.org) Machine learning models can reliably inform clinicians about the disability progression of multiple sclerosis, according to a new study published this week in the open-access journal PLOS Digital Health by Edward De Brouwer of KU Leuven, Belgium, and colleagues.

Multiple sclerosis (MS) is a chronic progressive autoimmune disease that leads to severe disability over time through a complex pattern of progression, recovery, and relapse. Its global prevalence has increased by more than 30% over the last decade. Yet there are few tools that can predict the progression of MS to help clinicians and patients make life planning and treatment decision-making. 

In the new study, De Brouwer and colleagues used data on 15,240 adults with at least three years of MS history who were being treated at 146 MS centers in 40 countries. Data on two years of each patient’s disease progression was used to train state-of-the-art machine learning models to predict the probability of disease progression over the subsequent months and years. The models were trained and validated using strict clinical guidelines, promoting applicability of the models in clinical practice. While individual models varied in performance across different patient subgroups, the models had an average area under the ROC curve (ROC-AUC) of 0.71 ± 0.01. The study found that the history of disability progression was more predictive for future disability progression than treatment or relapse history.

The authors conclude that the models developed in the study have the potential to greatly enhance planning for individuals with MS and could be evaluated in a clinical impact study.

De Brouwer adds: “Using the clinical history of more than 15,000 people with multiple sclerosis, we trained a machine learning model capable of reliably predicting the probability of disability progression in the next two years. The model only uses routinely collected clinical variables, which makes it widely applicable. Our rigorous benchmarking and external validation support the vast potential of machine learning models for helping patients planning their lives and clinicians optimizing treatment strategies.”

 

############

In your coverage, please use this URL to provide access to the freely available article in PLOS Digital Health: https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0000533

 

Citation: De Brouwer E, Becker T, Werthen-Brabants L, Dewulf P, Iliadis D, Dekeyser C, et al. (2024) Machine-learning-based prediction of disability progression in multiple sclerosis: An observational, international, multi-center study. PLOS Digit Health 3(7): e0000533. https://doi.org/10.1371/journal.pdig.0000533

Author Countries: Argentina, Australia, Belgium, Canada, Czech Republic, Greece, Hungary, Italy, Ireland, Kuwait, Lebanon, Malta, The Netherlands, Oman, Spain, Saudi Arabia, Switzerland, Turkey, Romania, United Kingdom, United States

Funding: This study was funded by the Research Foundation Flanders (FWO) and the Flemish government through the Onderzoeksprogramma Artificiele Intelligentie (AI) Vlaanderen program (https://www.flandersairesearch.be/en). This funding was awarded to YM, LB, TD, DD, WW, and BDB and funded EBD, TB, LWB, PD, DI, MS, YM, LB, TD, DD, WW, and BDB. EDB was also concomitantly funded by a FWO-SB fellowship (1S98821N - https://fwo.be). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

END


[Attachments] See images for this press release:
Can a computer tell patients how their multiple sclerosis will progress? Can a computer tell patients how their multiple sclerosis will progress? 2 Can a computer tell patients how their multiple sclerosis will progress? 3

ELSE PRESS RELEASES FROM THIS DATE:

Novel human lung organoids can form lifelike models for tuberculosis infection, and might be used to test efficacy of anti-TB drugs

2024-07-25
Novel human lung organoids can form lifelike models for tuberculosis infection, and might be used to test efficacy of anti-TB drugs. #### Article URL: http://journals.plos.org/plospathogens/article?id=10.1371/journal. ppat.1012295 Article Title: Advances in an In Vitro Tuberculosis Infection Model Using Human Lung Organoids for Host-Directed Therapies Author Countries: Republic of Korea Funding: This research was supported by the Korea National Institutes of Health (NIH) (No. 2021-ER2001-00) awarded to E.M.K., the Korea Institute of Toxicology, Republic of Korea (No. 1711195891) awarded to E.M.K., the Korea Environment Industry & Technology ...

Spin qubits go trampolining

Spin qubits go trampolining
2024-07-25
Researchers at QuTech developed somersaulting spin qubits for universal quantum logic. This achievement may enable efficient control of large semiconductor qubit arrays. The research group published their demonstration of hopping spins in Nature Communications and their work on somersaulting spins in Science.  In 1998, Loss and DiVincenzo published the seminal work ‘quantum computation with quantum dots’. In their original work, hopping of spins was proposed as a basis for qubit logic, but an experimental implementation has remained lacking. After more than 20 years, experiments have caught up with theory. Researchers ...

Seven steps to achieving the right to clean indoor air post-pandemic

2024-07-25
Professor Morawska, director of THRIVE, from QUT’s School of School of Earth and Atmospheric Sciences said the rapid global spread of Covid-19 had soon made it clear the world was unprepared to respond appropriately. “In the early days of the pandemic the World Health Organisation and many national health authorities claimed the virus was ‘not in the air’ but rather present in large quantities on surfaces. This led to a misconception about how the virus was transmitted,” ...

Scientists study how to bring you ‘climate-smart coffee’

Scientists study how to bring you ‘climate-smart coffee’
2024-07-25
Crave that cup of coffee in the morning? Globally, consumers drink more than 2.2 billion cups daily. Someone grows all that joe: More than 100 million farmers worldwide produce coffee. Coffee beans consumed across the globe come from two species: Coffea arabica and Coffea canephora, also known as Robusta (or Conilon) coffee. Historically, coffee drinkers prefer Arabica beans for their specific flavor and aroma, said Felipe Ferrao, a University of Florida research assistant scientist in horticultural sciences. But by 2050, about 80% of Arabica production is predicted to decrease because of climate change. So, Ferrao and colleagues from France (RD2 Vision) and Brazil (Incaper ...

New study shows at-home colon cancer screening test reduces risk of colorectal cancer death, as effective as screening colonoscopy

2024-07-25
COLUMBUS, Ohio – A noninvasive colorectal cancer screening test that can be done at home could reduce the risk of colorectal cancer death by 33%, according to a new study published in JAMA Network Open. This is the first study to evaluate this tool’s effectiveness in specific racial groups. For this study, researchers at The Ohio State University Comprehensive Cancer Center – Arthur G. James Cancer Hospital and the Richard J. Solove Research Institute (OSUCCC – James), and Kaiser Permanente evaluated data from nearly 11,000 patients who underwent at-home FIT (fecal immunochemical testing) among ...

A cool solution

A cool solution
2024-07-25
Artificial intelligence (AI) is hot right now. Also hot: the data centers that power the technology. And keeping those centers cool requires a tremendous amount of energy. The problem is only going to grow as high-powered AI-based computers and devices become commonplace. That’s why University of Missouri researcher Chanwoo Park is devising a new type of cooling system that promises to dramatically reduce energy demands. “Cooling and chip manufacturing go hand-in-hand,” said Park, a professor of mechanical and aerospace engineering in the Mizzou College of Engineering. “Without proper cooling, components overheat and fail. Energy-efficient data centers will be key ...

Electrical currents may make body’s cancer-killing cells even better killers

2024-07-25
Scientists have discovered that electrical currents may make Natural Killer (NK) cells – our very own cancer-killing immune cells – even better killers, which could have significant implications for treating some cancers.  The scientists found that Tumour Treating Fields (TTF) in the laboratory (which mimic exposure of  brain tumours to electric currents via a simple hat worn by patients) evoked an even more deadly response from NK cells. They hope their promising findings may open the door to new combined therapies for people living with certain brain tumours, such as glioblastoma. Glioblastoma is an aggressive, common ...

In Illinois, ‘older adults are at increased risk for suicide’

2024-07-25
Most (83%) suicide deaths were among men Firearms were the most frequently used weapon (59%) Among those who died by suicide, 20% had been diagnosed with depression; only 14.1% of them were receiving treatment CHICAGO --- Nearly 20% of suicides in Illinois between 2020 and 2021 were among people 65 years and older, according to recently released data from Northwestern University Feinberg School of Medicine. The suicides disproportionately affected white men between the ages of 65 and 74 years, with ...

Raindrops grow with turbulence in clouds

2024-07-25
Scientists for decades have attempted to learn more about the complex and mysterious chain of events by which tiny droplets in clouds grow large enough to begin falling toward the ground. Better understanding this process, known as the “rain formation bottleneck,” is fundamental to improving computer model simulations of weather and climate and ultimately generating better forecasts.   Now a research team led by scientists at the U.S. National Science Foundation National Center for Atmospheric Research (NSF NCAR) ...

Penn researchers reveal how a bacterium supports healing of chronic diabetic wounds

2024-07-25
PHILADELPHIA – There are many important reasons for keeping cuts and sores clean, but new research from the Perelman School of Medicine at the University of Pennsylvania shows that a certain bug, Alcaligenes faecalis (A. faecalis), can facilitate healing of hard-to-treat wounds among people with diabetes. While there are many studies done on potentially harmful bacteria in wounds, the researchers discovered that A. faecalis, a bacterium found in many types of chronic wounds, actually boosts healing of diabetic wounds. The researchers found that the beneficial bacterium can promote ...

LAST 30 PRESS RELEASES:

Patrick Tan appointed as Duke-NUS Dean to lead next era of medical innovation and education

Development of a novel modified selective medium cefixime–tellurite-phosphate-xylose-rhamnose MacConkey agar for isolation of Escherichia albertii and its evaluation with food samples

KIST develops full-color-emitting upconversion nanoparticle technology for color displays with ultra-high color reproducibility

Towards a fully automated approach for assessing English proficiency

Increase in alcohol deaths in England an ‘acute crisis’

Government urged to tackle inequality in ‘low-carbon tech’ like solar panels and electric cars

Moffitt-led international study finds new drug delivery system effective against rare eye cancer

Boston stroke neurologist elected new American Academy of Neurology president

Center for Open Science launches collaborative health research replication initiative

Crystal L. Mackall, MD, FAACR, recognized with the 2025 AACR-Cancer Research Institute Lloyd J. Old Award in Cancer Immunology

A novel strategy for detecting trace-level nanoplastics in aquatic environments: Multi-feature machine learning-enhanced SERS quantification leveraging the coffee ring effect

Blending the old and the new: Phase-change perovskite enable traditional VCSEL to achieve low-threshold, tunable single-mode lasers

Enhanced photoacoustic microscopy with physics-embedded degeneration learning

Light boosts exciton transport in organic molecular crystal

On-chip multi-channel near-far field terahertz vortices with parity breaking and active modulation

The generation of avoided-mode-crossing soliton microcombs

Unlocking the vibrant photonic realm: A new horizon for structural colors

Integrated photonic polarizers with 2D reduced graphene oxide

Shouldering the burden of how to treat shoulder pain

Stevens researchers put glycemic response modeling on a data diet

Genotype-to-phenotype map of human pelvis illuminates evolutionary tradeoffs between walking and childbirth

Pleistocene-age Denisovan male identified in Taiwan

KATRIN experiment sets most precise upper limit on neutrino mass: 0.45 eV

How the cerebellum controls tongue movements to grab food

It’s not you—it’s cancer

Drug pollution alters migration behavior in salmon

Scientists decode citrus greening resistance and develop AI-assisted treatment

Venom characteristics of a deadly snake can be predicted from local climate

Brain pathway links inflammation to loss of motivation, energy in advanced cancer

Researchers discover large dormant virus can be reactivated in model green alga

[Press-News.org] Can a computer tell patients how their multiple sclerosis will progress?