Advancing autism screening
A NEW artificial intelligence (AI) model is reshaping how autism spectrum disorder (ASD) is screened, offering faster, more accurate and more scalable detection across age groups.
Developed through an international research collaboration that included INTI International University, the model achieved up to 99.06% accuracy in identifying ASD in children, adolescents and adults, outperforming many existing diagnostic systems.
At the centre of the study is the Chaotic Binary Butterfly Optimisation Algorithm-based Feature Selection and Data Classification (CBBOAFS-DC) model. It analyses behavioural and developmental data to identify the traits most relevant to autism, supporting healthcare professionals in making earlier assessments.
For many families, autism diagnosis is often delayed due to long wait times, limited access to specialists, or a lack of services in rural and underserved areas.
These delays can mean children miss out on early intervention support that has been shown to improve communication, behaviour and learning outcomes significantly. Traditional screening tools also face consistency challenges, particularly when applied across different age groups or populations.
INTI International University Faculty of Data Sciences and Information Technology academic Prof Dr Siti Sarah Maidinat (pic) said the new model is not a replacement for conventional methods.
'It's a tool to support healthcare providers, especially in early screening. The earlier autism is detected, the earlier children can receive the necessary interventions.
'We're helping to bridge the gap between limited diagnostic resources and the growing need for early autism detection.
'The idea is to support, not substitute, clinical expertise – especially in underprivileged communities,' she said.
CBBOAFS-DC uses AI to process data from screening tools quickly and consistently, reducing reliance on time-intensive manual evaluations. Its hybrid architecture sets it apart from conventional approaches, according to an INTI press release dated May 23.
While traditional models often rely on algorithms like decision trees or logistic regression, the new model uses a three-step design.
'It selects only the most relevant features using a butterfly-inspired optimisation technique, applies a deep learning engine to detect subtle behavioural patterns, and then finetunes its internal parameters using a bacterial colony optimisation algorithm,' the press release read.
It added that this layered approach allows the model to handle the complexity of ASD traits across age groups and adapt to a variety of screening contexts – bringing researchers closer to a more universal screening solution.
The research was conducted in collaboration with Sri Manakula Vinayagar Engineering College and Vellore Institute of Technology in India, as well as institutions in Saudi Arabia.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
The Star
an hour ago
- The Star
Too good to be true ADHD videos on TikTok are often misleading, US study finds.
On TikTok, misinformation about attention-deficit/hyperactivity disorder (ADHD) can be tricky to spot, according to a new study, published this month in the scientic journal PLOS One (published by Public Library of Science, based in California, the United States), found that fewer than 50% of the claims made in some of the most popular ADHD videos on TikTok offered information that matched diagnostic criteria or professional treatment recommendations for the disorder. And, the researchers found, even study participants who had already been diagnosed with ADHD had trouble discerning which information was most reliable. About half of the TikTok creators included in the study were using the platform to sell products, such as fidget spinners, or services like coaching. None of them were licensed mental health professionals. The lack of nuance is concerning, said Vasileia Karasavva, a doctoral student in clinical psychology at Canada's University of British Columbia in Vancouver and the lead author of the study. If TikTok creators talk about difficulty concentrating, she added, they don't typically mention that the symptom is not specific to ADHD or that it could also be a manifestation of a different mental disorder, like depression or anxiety. Just because a video or post goes viral doesn't mean it is accurate. "The last thing we want to do is discourage people from expressing how they're feeling, what they're experiencing and finding community online," Karasavva said. "At the same time, it might be that you self-diagnose with something that doesn't apply to you, and then you don't get the help that you actually need." Karasavva's results echo those of a 2022 study that also analysed 100 popular TikTok videos about ADHD and found that half of them were misleading. "The data are alarming," said Stephen P. Hinshaw, a professor of psychology and an expert in ADHD at the University of California, Berkeley, who was not involved in either study. The themes of the videos might easily resonate with viewers, he added, but "accurate diagnosis takes access, time and money." In Karasavva's study, the researchers began by selecting the 100 most viewed videos on a single day in January 2023 and asked two licensed clinical psychologists to review each video. The psychologists were called to assess whether the videos accurately captured the symptoms of adult or adolescent ADHD that are characterised in the fifth edition of the Diagnostic and Statistical Manual of Mental Disorders, which is used by medical professionals in the US to diagnose and classify mental health conditions. If a video's claim didn't match up with the manual, the psychologists then established whether the symptoms in the video better reflected a different type of disorder or something that anyone, including those without ADHD, might experience. Finally, they rated on a scale of one to five whether they would recommend the video to help educate other people about ADHD. One limitation of the study was that it did not rely on a large panel of experts to evaluate the videos. The researchers then asked more than 840 undergraduate students to rate the videos using the same scale used by the psychologists. The study participants who were the most frequent consumers of ADHD-related TikTok content were more likely than the other participants to recommend the top five most reputable videos. But they were also more likely to recommend the bottom five videos. And that was true regardless of whether they had been diagnosed with ADHD or not. Karasavva said this could be because the TikTok algorithm serves videos that are similar to those a person has already watched - and as we come across the same information again and again, it's tempting to think that "all these people can't be wrong." "In the end, you might come to believe things that don't really match up with the science," she said. Notably, the students in the study also vastly overestimated how many people actually had ADHD. In an email, TikTok said that it strongly encourages people to seek professional medical advice if they are in need of support and that the platform directs users to reliable resources when they search for ADHD-related content. The information on TikTok "doesn't always tell you the full story, and it can also lead the loudest voices to be overrepresented,' said Margaret Sibley, a professor of psychiatry and behavioral sciences at the University of Washington School of Medicine in Seattle who was not involved in the study. "People might not be discerning about what aspect of their experience is ADHD versus something else." - ©2025 The New York Times
The Star
a day ago
- The Star
Advancing autism screening
A NEW artificial intelligence (AI) model is reshaping how autism spectrum disorder (ASD) is screened, offering faster, more accurate and more scalable detection across age groups. Developed through an international research collaboration that included INTI International University, the model achieved up to 99.06% accuracy in identifying ASD in children, adolescents and adults, outperforming many existing diagnostic systems. At the centre of the study is the Chaotic Binary Butterfly Optimisation Algorithm-based Feature Selection and Data Classification (CBBOAFS-DC) model. It analyses behavioural and developmental data to identify the traits most relevant to autism, supporting healthcare professionals in making earlier assessments. For many families, autism diagnosis is often delayed due to long wait times, limited access to specialists, or a lack of services in rural and underserved areas. These delays can mean children miss out on early intervention support that has been shown to improve communication, behaviour and learning outcomes significantly. Traditional screening tools also face consistency challenges, particularly when applied across different age groups or populations. INTI International University Faculty of Data Sciences and Information Technology academic Prof Dr Siti Sarah Maidinat (pic) said the new model is not a replacement for conventional methods. 'It's a tool to support healthcare providers, especially in early screening. The earlier autism is detected, the earlier children can receive the necessary interventions. 'We're helping to bridge the gap between limited diagnostic resources and the growing need for early autism detection. 'The idea is to support, not substitute, clinical expertise – especially in underprivileged communities,' she said. CBBOAFS-DC uses AI to process data from screening tools quickly and consistently, reducing reliance on time-intensive manual evaluations. Its hybrid architecture sets it apart from conventional approaches, according to an INTI press release dated May 23. While traditional models often rely on algorithms like decision trees or logistic regression, the new model uses a three-step design. 'It selects only the most relevant features using a butterfly-inspired optimisation technique, applies a deep learning engine to detect subtle behavioural patterns, and then finetunes its internal parameters using a bacterial colony optimisation algorithm,' the press release read. It added that this layered approach allows the model to handle the complexity of ASD traits across age groups and adapt to a variety of screening contexts – bringing researchers closer to a more universal screening solution. The research was conducted in collaboration with Sri Manakula Vinayagar Engineering College and Vellore Institute of Technology in India, as well as institutions in Saudi Arabia.
Focus Malaysia
3 days ago
- Focus Malaysia
PERSAMA announces Jigsaw Puzzle Championship for Autism 2025 during Father's Day celebrations
PERTUBUHAN Sayang Malaysia (PERSAMA), in collaboration with Green Yoga, has announced the Jigsaw Puzzle Championship for Autism during a Father's Day celebration. The Jigsaw Puzzle Championship for Autism 2025 aims to create a platform for children with autism spectrum disorder (ASD) to showcase their strengths and capabilities. Jigsaw puzzles offer a range of cognitive benefits for autistic children. Assembling a puzzle needs problem-solving skills, spatial awareness, and attention to detail. It also encourages logical thinking and can improve memory, fine motor skills, concentration, planning and social skills. Immediately before the announcement, over 100 participants gathered in Klang to celebrate Father's Day, a significant community event specifically designed for children on the autism spectrum and their fathers or caregivers. The celebration featured sensory-friendly fun activities conducted by the founder of Green Yoga, Naneecharam Muniandy who is a certified yoga instructor. The celebration highlighted the role of fathers and male caregivers in the emotional and developmental journey of children with ASD. Participants shared their experiences, taking great strides to raise awareness, break down stereotypes, and reaffirm the community's commitment to empowering autistic children fully. These events are just some of the many ways PERSAMA provides support, capacity building, and outreach activities to families with individuals with autism nationwide. PERSAMA founder noted that the number of children diagnosed with autism nationally has risen to over 58,000 with Selangor having the highest incidence of cases. 'This is a growing issue and needs close collaboration between the government and its agencies, NGOs, parents/caregivers, and teachers to build a sustainable approach for the future,' she added. 'Behind each child is a family attempting to navigate complex challenges and PERSAMA is here to provide support where needed.' All Malaysian with autism are invited to participate in the Jigsaw Puzzle Championship for Autism 2025 which has over RM 7,000 in cash prizes to be won. Jigsaw puzzles are a valuable therapeutic and educational tool that can be tailored to meet the needs of children with autism, fostering a sense of achievement and joy in the process. Benefits of jigsaw puzzles include: Enhances fine motor skills; Develops problem-solving skills; Boosts concentration and focus; Supports visual-spatial skills; Promotes calmness and relaxation; Builds perseverance and patience; and Develops cognitive skills. When: Day : Saturday & Sunday : Saturday & Sunday Date : November 8 & 9, 2025 : November 8 & 9, 2025 Venue: KL/Klang Valley (TBA) Entry fee: 50% discount for PERSAMA members RM 100 for non members Entry requirements: Ages ranging from 4 years and above OKU card or doctor's diagnosis report is compulsory Categories: Age 4-6 Age 7-9 Age 10–12 Age 13-15 Age 16-18 Age 19 and above Register at: Registration closes at midnight on October 15, 2025. For more details, WhatsApp 017-721 1859. ‒ June 20, 2025
