(Press-News.org) A new machine learning model can predict autism in young children from relatively limited information. This is shown in a new study from Karolinska Institutet published in JAMA Network Open. The model can facilitate early detection of autism, which is important to provide the right support.
“With an accuracy of almost 80 percent for children under the age of two, we hope that this will be a valuable tool for healthcare,” says Kristiina Tammimies, Associate Professor at KIND, the Department of Women's and Children's Health, Karolinska Institutet and last author of the study.
The research team used a large US database (SPARK) with information on approximately 30,000 individuals with and without autism spectrum disorders.
By analyzing a combination of 28 different parameters, the researchers developed four distinct machine-learning models to identify patterns in the data. The parameters selected were information about children that can be obtained without extensive assessments and medical tests before 24 months of age. The best-performing model was named 'AutMedAI'.
Among about 12,000 individuals, the AutMedAI model was able to identify about 80% of children with autism. In specific combinations with other parameters, age of first smile, first short sentence and the presence of eating difficulties were strong predictors of autism.
“The results of the study are significant because they show that it is possible to identify individuals who are likely to have autism from relatively limited and readily available information,” says study first author Shyam Rajagopalan, an affiliated researcher at the same department at Karolinska Institutet and currently assistant professor at the Institute of Bioinfomatics and Applied Technology,India.
Early diagnosis is critical, according to the researchers, to implement effective interventions that can help children with autism develop optimally.
“This can drastically change the conditions for early diagnosis and interventions, and ultimately improve the quality of life for many individuals and their families,” says Shyam Rajagopalan.
In the study, the AI model showed good results in identifying children with more extensive difficulties in social communication and cognitive ability and having more general developmental delays.
The research team is now planning further improvements and validation of the model in clinical settings. Work is also underway to include genetic information in the model, which may lead to even more specific and accurate predictions.
“To ensure that the model is reliable enough to be implemented in clinical contexts, rigorous work and careful validation are required. I want to emphasize that our goal is for the model to become a valuable tool for health care, and it is not intended to replace a clinical assessment of autism,” says Kristiina Tammimies.
The study was funded by the Swedish Foundation for Strategic Research, Hjärnfonden and Stratneuro.
Publication: “Machine Learning Prediction of Autism Spectrum Disorder from a Minimal Set of Medical and Background Information”, Shyam Sundar Rajagopalan, Yali Zhang, Ashraf Yahia, Kristiina Tammimies. Jama Network Open, online August 19, 2024, doi: 10.1001/jamanetworkopen.2024.29229
END
AI model aids early detection of autism
2024-08-19
ELSE PRESS RELEASES FROM THIS DATE:
A common fatty acid may help restore healthy vaginal bacteria after infection
2024-08-19
More than half of women globally experience bacterial vaginosis (BV) — an imbalance of naturally occurring microbes in the female genital tract — at least once in their life. The condition can cause painful symptoms and vaginal discharge, and although treatable with antibiotics, it frequently comes back within a short time. If left untreated, BV can lead to problems with pregnancy and an increased risk of sexually transmitted infections, including HIV.
A team of researchers at the Broad Institute of MIT and Harvard; the Ragon Institute of Mass General ...
Outcomes of mitral valve surgery in atrial functional mitral regurgitation
2024-08-19
Mitral regurgitation (MR) is a serious heart condition that often requires corrective surgery. It is characterized by the backflow or "regurgitation" of blood from the heart's left ventricle into the left atrium. Atrial Functional Mitral Regurgitation (AFMR), characterized by normal mitral valve (MV) function and left ventricular function but with atrial dilation and defects in the ring-like structure that supports the MV leaflets (mitral annulus), poses diagnostic and therapeutic challenges due to its distinct pathophysiological mechanisms. Historically, studies on AFMR have been limited by small ...
Searching old stem cells that stay young forever
2024-08-19
The sea anemone Nematostella vectensis is potentially immortal. Using molecular genetic methods, developmental biologists led by Ulrich Technau from the University of Vienna have now identified possible candidates for multipotent stem cells in the sea anemone for the first time. These stem cells are regulated by evolutionary highly conserved genes, which in humans are usually only active in the formation of egg and sperm cells, but give ancient animal phyla such as cnidarians a high degree of regenerative capacity to even escape ageing. The results are currently being published in Science Advances and could also provide insights into the human ...
Low cortisol, hair-trigger stress response in the brain may underlie Long COVID
2024-08-19
Proteins left behind by COVID-19 long after initial infection can cause cortisol levels in the brain to plummet, inflame the nervous system and prime its immune cells to hyper-react when another stressor arises, according to new animal research by University of Colorado Boulder scientists.
The study, published in the journal Brain Behavior and Immunity, sheds new light on what might underly the neurological symptoms of Long COVID, an intractable syndrome which impacts as many as 35% of those infected with the ...
What time the malaria-bearing mosquito bites you might make a difference
2024-08-19
What time the malaria-bearing mosquito bites you might make a difference
Circadian rhythms appear to influence vulnerability to malaria parasites
A discovery by McGill-affiliated researchers could lead to more effective treatment of malaria and other parasitic diseases.
When mice are infected in the middle of the night with the parasites causing cerebral malaria, the symptoms of the disease are less severe than for those inflected during the day, and the spread of the parasites within the hosts is more limited, research teams from McGill University, the Douglas Research Centre ...
SwRI develops novel DNA-targeting therapeutic screening technique
2024-08-19
SAN ANTONIO — August 19, 2024 —Southwest Research Institute (SwRI) has developed a unique technology to screen new DNA-targeting therapeutics designed to treat cancer and other diseases. Combining SwRI’s 3D drug screening software tool and machine learning techniques, SwRI scientists successfully predicted the DNA binding affinity and cancer cell toxicity for a variety of relevant drug compounds under development.
SwRI expanded the capabilities of its Rhodium™ drug development tool to visualize and rapidly predict how ...
Swiping through online videos increases boredom, study finds
2024-08-19
Swiping through online videos to relieve boredom may actually make people more bored and less satisfied or engaged with the content, according to research published by the American Psychological Association.
The study included seven experiments with a total of more than 1,200 participants from the United States or college students at the University of Toronto. In two baseline experiments, participants switched from one online video to the next when they were bored, and they predicted they would feel less bored by switching videos instead ...
Kelvin K. Droegemeier on ‘Working Toward a Computational Framework to Support Earth System Science and Climate Projection’
2024-08-19
Editor’s note: NCSA is cohosting an International Summit on a Computational System for Frontier Earth System Science and Climate Simulation & Projection September 29 through October 2, 2024 at the University of Illinois Urbana-Champaign.
Toward a Computational Framework for Earth System Models at Kilometer Resolution to Support Earth System Science and Climate Projection
By Kelvin K. Droegemeier, Professor of Atmospheric Science and Special Advisor to the Chancellor for Science and Policy at the University of Illinois Urbana-Champaign
Almost daily, and often without realizing it, we rely upon computers to guide our decisions. Whether finding the fastest ...
National Academy of Medicine selects FAU for substance use, opioid crises collaborative
2024-08-19
As of 2024, approximately 2.7 million Americans aged 12 and older were estimated to have misused prescription opioids in the past year. Moreover, alcohol, cannabis, cocaine, methamphetamines, among other substances, reflect a complex landscape that requires ongoing efforts aimed at prevention, treatment and policy changes to address the various issues associated with each substance.
Florida Atlantic University was recently selected to participate in the National Academy of Medicine’s (NAM) Action Collaborative on Combatting Substance Use Opioid Crises Core Competency Implementation Pilot Project. To improve coordination ...
Study finds potential link between DNA markers and aging process
2024-08-19
Researchers at Weill Cornell Medicine and the epigenetics company TruDiagnostic have uncovered DNA markers associated with retroelements, remnants of ancient viral genetic material, in our genes that act as highly accurate epigenetic clocks predicting chronological age. The results support the idea that certain retroelements in the human genome may be involved in aging.
Retroelements have been known to impact gene regulation, gene expression, genomic stability and the trajectory of various human diseases, but their potential as biomarkers for aging had been largely unexplored.
The ...