Early developmental trajectory phenotypes for risk stratification of autism spectrum disorder in very preterm infants: a machine learning approach
Li-Wen Chen, Yi-Tien Li, Chi-Hsiang Chu, Chin-Chin Wu, Ching-Lin Chu, Lan-Wan Wang, Han-Yi Tsai, Chung-Hsin Chiang, Chao-Ching Huang · 2025
Read Early developmental trajectory phenotypes for risk stratification of autism spectrum disorder in very preterm infants: a machine learning approach by Li-Wen Chen, Yi-Tien Li, Chi-Hsiang Chu, Chin-Chin Wu, Ching-Lin Chu, Lan-Wan Wang, Han-Yi Tsai, Chung-Hsin Chiang, Chao-Ching Huang (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12805792.txt.
Description
Babies born very early face a higher risk of autism, but early signs are hard to read because other delays overlap with them. The nine authors followed 583 infants born before 32 weeks in 2011 to 2018. They tested the infants at 6, 12, and 24 months on thinking, understanding speech, speaking, and fine and gross movement. Autism was judged at age five. Seventy-five children, or 12.9 percent, were diagnosed.
Children later diagnosed scored lower on thinking across the first two years. They also fell further behind in understanding speech, speaking, and fine movement during the second year. Gross movement did not differ between groups. A support vector machine model using the scores plus birth risks reached 71.8 percent accuracy. Its high negative predictive value of 93.6 percent made it best at ruling autism out. The authors call its overall power modest and note it came from one region.
Catalog record
| CREATOR | Li-Wen Chen, Yi-Tien Li, Chi-Hsiang Chu, Chin-Chin Wu, Ching-Lin Chu, Lan-Wan Wang, Han-Yi Tsai, Chung-Hsin Chiang, Chao-Ching Huang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |