Automated AI based identification of autism spectrum disorder from home videos

Autism spectrum disorder (ASD) is a prevalent childhood-onset neurodevelopmental condition. Early diagnosis remains challenging by the time, cost, and expertise required for traditional assessments, creating barriers to timely identification. We developed an AI-based screening system leveraging home-recorded videos to improve early ASD detection. Three task-based video protocols under 1 min each-name-response, imitation, and ball-playing-were developed, and home videos following these protocols were collected from 510 children (253 ASD, 257 typically developing), aged 18-48 months, across 9 hospitals in South Korea. Task-specific features were extracted using deep learning models and combined with demographic data through machine learning classifiers. The ensemble model achieved an area under the receiver operating characteristic curve of 0.83 and an accuracy of 0.75. This fully automated approach, based on short home-video protocols that elicit children's natural behaviors, complements clinical evaluation and may aid in prioritizing referrals and enabling earlier intervention in resource-limited settings.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2025-10-10
DOI
https://doi.org/10.1038/s41746-025-01993-5
Citations
2
Primary Topic
Autism Spectrum Disorder Research
Type
article
Field-Weighted Citation Impact
2.86

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Automated AI based identification of autism spectrum disorder from home videos

Yoojeong Lee, Youmin Shin, Eunji Jung, You Bin Lim et al.
2 citations
npj Digital Medicine
Autism Spectrum Disorder Research
2.86
article

Automated AI based identification of autism spectrum disorder from home videos

Yoojeong Lee, Youmin Shin, Eunji Jung, You Bin Lim, Hangnyoung Choi, Sungchul Cho, Helena Sim, Hee‐Jeong Yoo, Jaeeun Yu, Bung-Nyun Kim, Guiyoung Bong, Jung-Woo Son, Keun‐Ah Cheon, Chan-Mo Yang, Johanna Inhyang Kim, Hyung Jin Sung, Hayoung Lim, Geonhee Lee, Ara Cho, Sungji Ha, Jeeyoung Chun, Seungwon Chung, Junghan Lee, Chae Rim Lee, Seong Woo Jeon, Min-Hyeon Park, Seyeon Park, Jinseong Jang, Jae Hyun Yoo, Hanna Kim, Dong‐Ho Lee, Sooyeon Lee, Sohyun Park, Dong Yeong Kim, Hyo-Won Kim, Young-Gon Kim, Wooseok Choi, Boa Jang, Je Ahn, Ryemi Do
article en
2 citations

Abstract

Autism spectrum disorder (ASD) is a prevalent childhood-onset neurodevelopmental condition. Early diagnosis remains challenging by the time, cost, and expertise required for traditional assessments, creating barriers to timely identification. We developed an AI-based screening system leveraging home-recorded videos to improve early ASD detection. Three task-based video protocols under 1 min each-name-response, imitation, and ball-playing-were developed, and home videos following these protocols were collected from 510 children (253 ASD, 257 typically developing), aged 18-48 months, across 9 hospitals in South Korea. Task-specific features were extracted using deep learning models and combined with demographic data through machine learning classifiers. The ensemble model achieved an area under the receiver operating characteristic curve of 0.83 and an accuracy of 0.75. This fully automated approach, based on short home-video protocols that elicit children's natural behaviors, complements clinical evaluation and may aid in prioritizing referrals and enabling earlier intervention in resource-limited settings.

npj Digital MedicineVol. 8(1)
Ulsan College (KR), Seoul National University (KR), Yonsei University (KR), Severance Hospital (KR), Asan Medical Center (KR), New Generation University College (ET), Seoul National University Hospital (KR), Seoul National University Bundang Hospital (KR), University of Ulsan (KR), St. Mary's Hospital (US), Eunpyeong Hospital (KR), National University College (PR), St. Mary's Hospital (US), Korea Telecom (South Korea) (KR), The Catholic University of Korea Seoul St. Mary's Hospital (KR), Yonsei University Health System (KR), Chungbuk National University Hospital (KR), Hanyang University (KR), Wonkwang University (KR), Catholic University of Korea (KR)
National Center for Mental Health
Openalex Percentile: Top 8%
Autism Spectrum Disorder Research
2.86
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.