{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/eeg-language-modeling-for-pathology-detection","title":"EEG-Language Modeling for Pathology Detection","arxiv_id":"2409.07480","date":"2024-09-02","proceeding":null,"authors":["Sam Gijsen","Kerstin Ritter"],"abstract":"Multimodal language modeling has enabled breakthroughs for representation learning, yet remains unexplored in the realm of functional brain data for pathology detection. This paper pioneers EEG-language models (ELMs) trained on clinical reports and 15000 EEGs. We propose to combine multimodal alignment in this novel domain with timeseries cropping and text segmentation, enabling an extension based on multiple instance learning to alleviate misalignment between irrelevant EEG or text segments. Our multimodal models significantly improve pathology detection compared to EEG-only models across four evaluations and for the first time enable zero-shot classification as well as retrieval of both neural signals and reports. In sum, these results highlight the potential of ELMs, representing significant progress for clinical applications.","url_abs":"https://arxiv.org/abs/2409.07480v3","url_pdf":"https://arxiv.org/pdf/2409.07480v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"eeg-1","task_name":"EEG"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-segmentation","task_name":"Text Segmentation"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.07480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07480"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/SamGijsen/ELM","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"found_in_text":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"4c75f9586bb19371","entry":"fix_tuh_channel_names","repo":"SamGijsen/ELM","repo_kind":"found_in_text","path":"utils/preprocess_TUEG.py","file_url":"https://github.com/SamGijsen/ELM/blob/HEAD/utils/preprocess_TUEG.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4c75f9586bb19371"}},{"code_sha256_prefix":"0809f9c9181dee9d","entry":"parse_age_and_sex_from_edf_header","repo":"SamGijsen/ELM","repo_kind":"found_in_text","path":"utils/preprocess_TUEG.py","file_url":"https://github.com/SamGijsen/ELM/blob/HEAD/utils/preprocess_TUEG.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0809f9c9181dee9d"}},{"code_sha256_prefix":"6697f803c7fec66e","entry":"read_edf_header","repo":"SamGijsen/ELM","repo_kind":"found_in_text","path":"utils/preprocess_TUEG.py","file_url":"https://github.com/SamGijsen/ELM/blob/HEAD/utils/preprocess_TUEG.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6697f803c7fec66e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}