{"ID":2849903,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.23946","arxiv_id":"2510.23946","title":"Leveraging LLMs for Early Alzheimer's Prediction","abstract":"We present a connectome-informed LLM framework that encodes dynamic fMRI connectivity as temporal sequences, applies robust normalization, and maps these data into a representation suitable for a frozen pre-trained LLM for clinical prediction. Applied to early Alzheimer's detection, our method achieves sensitive prediction with error rates well below clinically recognized margins, with implications for timely Alzheimer's intervention.","short_abstract":"We present a connectome-informed LLM framework that encodes dynamic fMRI connectivity as temporal sequences, applies robust normalization, and maps these data into a representation suitable for a frozen pre-trained LLM for clinical prediction. Applied to early Alzheimer's detection, our method achieves sensitive predic...","url_abs":"https://arxiv.org/abs/2510.23946","url_pdf":"https://arxiv.org/pdf/2510.23946v1","authors":"[\"Tananun Songdechakraiwut\"]","published":"2025-10-27T23:59:03Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}