{"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/the-effect-of-heterogeneous-data-for","title":"The Effect of Heterogeneous Data for Alzheimer's Disease Detection from Speech","arxiv_id":"1811.12254","date":"2018-11-29","proceeding":null,"authors":["Aparna Balagopalan","Jekaterina Novikova","Frank Rudzicz","Marzyeh Ghassemi"],"abstract":"Speech datasets for identifying Alzheimer's disease (AD) are generally\nrestricted to participants performing a single task, e.g. describing an image\nshown to them. As a result, models trained on linguistic features derived from\nsuch datasets may not be generalizable across tasks. Building on prior work\ndemonstrating that same-task data of healthy participants helps improve AD\ndetection on a single-task dataset of pathological speech, we augment an\nAD-specific dataset consisting of subjects describing a picture with multi-task\nhealthy data. We demonstrate that normative data from multiple speech-based\ntasks helps improve AD detection by up to 9%. Visualization of decision\nboundaries reveals that models trained on a combination of structured picture\ndescriptions and unstructured conversational speech have the least out-of-task\nerror and show the most potential to generalize to multiple tasks. We analyze\nthe impact of age of the added samples and if they affect fairness in\nclassification. We also provide explanations for a possible inductive bias\neffect across tasks using model-agnostic feature anchors. This work highlights\nthe need for heterogeneous datasets for encoding changes in multiple facets of\ncognition and for developing a task-independent AD detection model.","url_abs":"http://arxiv.org/abs/1811.12254v1","url_pdf":"http://arxiv.org/pdf/1811.12254v1.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":[{"paper_slug":"the-effect-of-heterogeneous-data-for","repo_url":"https://github.com/ychnlgy/Chebyshev-Lagrange","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"alzheimer-s-disease-detection","task_name":"Alzheimer's Disease Detection"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1811.12254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12254"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ychnlgy/Chebyshev-Lagrange","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"listed":{"samples":9,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"51ce2272e68bb1d1","entry":"accuracy","repo":"ychnlgy/Chebyshev-Lagrange","repo_kind":"listed","path":"shake-shake_pytorch/utils.py","file_url":"https://github.com/ychnlgy/Chebyshev-Lagrange/blob/HEAD/shake-shake_pytorch/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"51ce2272e68bb1d1"}},{"code_sha256_prefix":"e2dccb948ef4bddc","entry":"chebyshev_node","repo":"ychnlgy/Chebyshev-Lagrange","repo_kind":"listed","path":"shake-shake_pytorch/models/polynomial/chebyshev.py","file_url":"https://github.com/ychnlgy/Chebyshev-Lagrange/blob/HEAD/shake-shake_pytorch/models/polynomial/chebyshev.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e2dccb948ef4bddc"}},{"code_sha256_prefix":"7529a26792fd6da5","entry":"cosine_lr","repo":"ychnlgy/Chebyshev-Lagrange","repo_kind":"listed","path":"shake-shake_pytorch/utils.py","file_url":"https://github.com/ychnlgy/Chebyshev-Lagrange/blob/HEAD/shake-shake_pytorch/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7529a26792fd6da5"}},{"code_sha256_prefix":"21c1e5f90f7652fc","entry":"fetch_bylabel","repo":"ychnlgy/Chebyshev-Lagrange","repo_kind":"listed","path":"shake-shake_pytorch/datasets.py","file_url":"https://github.com/ychnlgy/Chebyshev-Lagrange/blob/HEAD/shake-shake_pytorch/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21c1e5f90f7652fc"}},{"code_sha256_prefix":"d8bff54a6d1cd112","entry":"get_nodes","repo":"ychnlgy/Chebyshev-Lagrange","repo_kind":"listed","path":"shake-shake_pytorch/models/polynomial/chebyshev.py","file_url":"https://github.com/ychnlgy/Chebyshev-Lagrange/blob/HEAD/shake-shake_pytorch/models/polynomial/chebyshev.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d8bff54a6d1cd112"}},{"code_sha256_prefix":"f03d9354d6480eee","entry":"load_dataset","repo":"ychnlgy/Chebyshev-Lagrange","repo_kind":"listed","path":"shake-shake_pytorch/datasets.py","file_url":"https://github.com/ychnlgy/Chebyshev-Lagrange/blob/HEAD/shake-shake_pytorch/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f03d9354d6480eee"}},{"code_sha256_prefix":"11439743f8dc1cb3","entry":"load_mnist","repo":"ychnlgy/Chebyshev-Lagrange","repo_kind":"listed","path":"shake-shake_pytorch/datasets.py","file_url":"https://github.com/ychnlgy/Chebyshev-Lagrange/blob/HEAD/shake-shake_pytorch/datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"11439743f8dc1cb3"}},{"code_sha256_prefix":"1f11794f4c1b7ca5","entry":"predict","repo":"ychnlgy/Chebyshev-Lagrange","repo_kind":"listed","path":"db_adhc.py","file_url":"https://github.com/ychnlgy/Chebyshev-Lagrange/blob/HEAD/db_adhc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f11794f4c1b7ca5"}},{"code_sha256_prefix":"3b16fdcbfad2f72a","entry":"remove_columns_with_any_nans","repo":"ychnlgy/Chebyshev-Lagrange","repo_kind":"listed","path":"db_adhc.py","file_url":"https://github.com/ychnlgy/Chebyshev-Lagrange/blob/HEAD/db_adhc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b16fdcbfad2f72a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}