Researchers have fine-tuned Google's Gemini 2.5 Pro model to analyze short home videos for early autism diagnosis. By training on 400 clinician-rated videos and focusing on 30 validated behavioral features, the model demonstrated a 40% improvement in inter-rater reliability with clinicians. The fine-tuned model also showed an emergent zero-shot capability, improving ASD diagnosis accuracy by 53% and achieving 77% overall accuracy with an AUC of 86%. This advancement suggests that multimodal large language models can be scaled to extract behavioral features for more accessible autism assessment. AI
IMPACT Enhances potential for early autism diagnosis through accessible video analysis, improving clinical outcomes.
RANK_REASON Research paper detailing a novel application of a multimodal LLM for a specific medical diagnosis. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- autism
- CatalyzeX
- DagsHub
- Gemini 2.5 Pro
- Gotit.pub
- Hugging Face
- Mohammadmahdi Honarmand
- ScienceCast
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
