{"doi":"10.1093/jamia/ocad036","title":"<i>EvidenceMap</i>: a three-level knowledge representation for medical evidence computation and comprehension","abstract":"OBJECTIVE: To develop a computable representation for medical evidence and to contribute a gold standard dataset of annotated randomized controlled trial (RCT) abstracts, along with a natural language processing (NLP) pipeline for transforming free-text RCT evidence in PubMed into the structured representation. MATERIALS AND METHODS: Our representation, EvidenceMap, consists of 3 levels of abstraction: Medical Evidence Entity, Proposition and Map, to represent the hierarchical structure of medical evidence composition. Randomly selected RCT abstracts were annotated following EvidenceMap based on the consensus of 2 independent annotators to train an NLP pipeline. Via a user study, we measured how the EvidenceMap improved evidence comprehension and analyzed its representative capacity by comparing the evidence annotation with EvidenceMap representation and without following any specific guidelines. RESULTS: Two corpora including 229 disease-agnostic and 80 COVID-19 RCT abstracts were annotated, yielding 12 725 entities and 1602 propositions. EvidenceMap saves users 51.9% of the time compared to reading raw-text abstracts. Most evidence elements identified during the freeform annotation were successfully represented by EvidenceMap, and users gave the enrollment, study design, and study Results sections mean 5-scale Likert ratings of 4.85, 4.70, and 4.20, respectively. The end-to-end evaluations of the pipeline show that the evidence proposition formulation achieves F1 scores of 0.84 and 0.86 in the adjusted random index score. CONCLUSIONS: EvidenceMap extends the participant, intervention, comparator, and outcome framework into 3 levels of abstraction for transforming free-text evidence from the clinical literature into a computable structure. It can be used as an interoperable format for better evidence retrieval and synthesis and an interpretable representation to efficiently comprehend RCT findings.","journal":"Journal of the American Medical Informatics Association","year":2023,"id":340819,"datarank":0.8903952264341282,"base_score":2.772588722239781,"endowment":2.772588722239781,"self_citation_contribution":0.41588830833596724,"citation_network_contribution":0.474506918098161,"self_endowment_contribution":0.41588830833596724,"citer_contribution":0.474506918098161,"corpus_percentile":77.31879012918698,"corpus_rank":2933,"citation_count":15,"citer_count":13,"citers_with_citation_signal":11,"citers_with_endowment":11,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.8551,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":859186,"name":"Yingcheng Sun","orcid":"0000-0002-8693-5768","position":1,"is_corresponding":false},{"id":804181,"name":"Jae Hyun Kim","orcid":"0000-0002-8609-7135","position":2,"is_corresponding":false},{"id":2009,"name":"Casey Ta","orcid":"0000-0002-4679-805X","position":3,"is_corresponding":false},{"id":279054,"name":"Adler Perotte","orcid":"0000-0002-6695-0282","position":4,"is_corresponding":false},{"id":1076335,"name":"Kayla Schiffer","orcid":null,"position":5,"is_corresponding":false},{"id":1076336,"name":"Mutong Wu","orcid":null,"position":6,"is_corresponding":false},{"id":236813,"name":"Yang Zhao","orcid":"0000-0002-1501-0565","position":7,"is_corresponding":false},{"id":1076337,"name":"Nour Moustafa-Fahmy","orcid":null,"position":8,"is_corresponding":false},{"id":85506,"name":"Yifan Peng","orcid":"0000-0001-9309-8331","position":9,"is_corresponding":false},{"id":2012,"name":"Chunhua Weng","orcid":"0000-0002-9624-0214","position":10,"is_corresponding":false},{"id":1075865,"name":"Tian Kang","orcid":"0000-0002-8460-7525","position":0,"is_corresponding":true}],"reference_count":39,"raw_metadata":null,"created_at":"2026-07-19T01:10:58.548803Z","pmid":"36921288","pmcid":"PMC10198523","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":[]}