{"doi":"10.3233/jad-240116","title":"Semantic Harmonization of Alzheimer’s Disease Datasets Using AD-Mapper","abstract":"Background: Despite numerous past endeavors for the semantic harmonization of Alzheimer's disease (AD) cohort studies, an automatic tool has yet to be developed. Objective: As cohort studies form the basis of data-driven analysis, harmonizing them is crucial for cross-cohort analysis. We aimed to accelerate this task by constructing an automatic harmonization tool. Methods: We created a common data model (CDM) through cross-mapping data from 20 cohorts, three CDMs, and ontology terms, which was then used to fine-tune a BioBERT model. Finally, we evaluated the model using three previously unseen cohorts and compared its performance to a string-matching baseline model. Results: Here, we present our AD-Mapper interface for automatic harmonization of AD cohort studies, which outperformed a string-matching baseline on previously unseen cohort studies. We showcase our CDM comprising 1218 unique variables. Conclusion: AD-Mapper leverages semantic similarities in naming conventions across cohorts to improve mapping performance.","journal":"Journal of Alzheimer s Disease","year":2024,"id":476794,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":2,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.8391,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1314276,"name":"Helena Balabin","orcid":"0000-0002-6392-9306","position":1,"is_corresponding":false},{"id":1314277,"name":"Mehmet Can Ay","orcid":"0000-0002-2977-7695","position":2,"is_corresponding":false},{"id":556948,"name":"Sarah Bauermeister","orcid":"0000-0001-9463-6971","position":3,"is_corresponding":false},{"id":1314673,"name":"Lewis Killin","orcid":null,"position":4,"is_corresponding":false},{"id":29791,"name":"John Gallacher","orcid":"0000-0002-2394-5299","position":5,"is_corresponding":false},{"id":575866,"name":"Martin Hofmann‐Apitius","orcid":"0000-0001-9012-6720","position":6,"is_corresponding":false},{"id":811512,"name":"Yasamin Salimi","orcid":"0000-0002-7773-7786","position":7,"is_corresponding":false},{"id":243718,"name":"for the Alzheimer’s Disease Neuroimaging Initiative","orcid":null,"position":8,"is_corresponding":false},{"id":812004,"name":"the Japanese Alzheimer’s Disease Neuroimaging Initiative","orcid":null,"position":9,"is_corresponding":false},{"id":1314674,"name":"the Aging Brain: Vasculature, Ischemia, and Behavior Study","orcid":null,"position":10,"is_corresponding":false},{"id":812006,"name":"the Alzheimer’s Disease Repository Without Borders Investigators","orcid":null,"position":11,"is_corresponding":false},{"id":1314275,"name":"Philipp Wegner","orcid":"0000-0003-1159-9269","position":0,"is_corresponding":true}],"reference_count":35,"raw_metadata":null,"created_at":"2026-07-19T02:06:29.605760Z","pmid":"38759012","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}