Abstract:Generating clinical reports that summarize abnormal patterns, diagnostic findings, and clinical interpretations from long-term EEG recordings remains labor-intensive. We present CELM, the first clinical EEG-to-Language foundation model capable of summarizing long-duration, variable-length EEG recordings and performing end-to-end clinical report generation at multiple scales. CELM integrates pretrained EEG foundation models with language models to enable scalable multimodal learning. We curate a large-scale clinical EEG dataset containing 9,922 reports paired with approximately 11,000 hours of EEG recordings from 9,048 patients to train CELM, and release the benchmark with an automated report-structuring pipeline to facilitate future research. Experimental results show that CELM consistently outperforms existing methods across all evaluation settings. Importantly, we further conduct human evaluation with clinical experts, demonstrating that CELM generates reports that are more clinically coherent, diagnostically reliable, and better aligned with expert interpretation. We release our model and benchmark construction pipeline at this https URL.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Signal Processing (eess.SP) |
| Cite as: | arXiv:2601.22197 [cs.LG] |
| (or arXiv:2601.22197v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2601.22197 arXiv-issued DOI via DataCite |
Submission history
From: Jathurshan Pradeepkumar [view email]
[v1]
Thu, 29 Jan 2026 13:07:30 UTC (18,331 KB)
[v2]
Fri, 6 Mar 2026 18:57:14 UTC (18,328 KB)
[v3]
Wed, 13 May 2026 18:49:28 UTC (21,991 KB)