PubMed

Multimodal LLM vs. Human-Measured Features for AI Predictions of Autism in Home Videos.

PMID: 42375709 · 2025-10-29

P, a, r, n, i, a, n, , A, z, i, z, i, a, n, ;, , M, o, h, a, m, m, a, d, m, a, h, d, i, , H, o, n, a, r, m, a, n, d, ;, , A, d, i, t, i, , J, a, i, s, w, a, l, ;, , A, a, r, o, n, , K, l, i, n, e, ;, , K, a, i, t, l, y, n, , D, u, n, l, a, p, ;, , P, e, t, e, r, , W, a, s, h, i, n, g, t, o, n, ;, , D, e, n, n, i, s, , P, , W, a, l, l

ЖурналAlgorithms

Год2025-10-29

PMID42375709

Аннотация

Autism diagnosis remains a critical healthcare challenge, with current assessments contributing to average diagnostic ages of 5 and extending to 8 in underserved populations. With the FDA approval of CanvasDx in 2021, the paradigm of human-in-the-loop AI diagnostics entered the pediatric market as the first medical device for clinically precise autism diagnosis at scale, while fully automated deep learning approaches have remained underdeveloped. However, the importance of early autism detection

Официальный источник

Открыть в PubMed →

Данные получены из PubMed / NCBI. Полный текст и наиболее актуальную информацию всегда смотрите в официальной записи.