{"doi":"10.3390/medsci11020037","title":"Patient Dietary Supplements Use: Do Results from Natural Language Processing of Clinical Notes Agree with Survey Data?","abstract":"<jats:p>There is widespread use of dietary supplements, some prescribed but many taken without a physician’s guidance. There are many potential interactions between supplements and both over-the-counter and prescription medications in ways that are unknown to patients. Structured medical records do not adequately document supplement use; however, unstructured clinical notes often contain extra information on supplements. We studied a group of 377 patients from three healthcare facilities and developed a natural language processing (NLP) tool to detect supplement use. Using surveys of these patients, we investigated the correlation between self-reported supplement use and NLP extractions from the clinical notes. Our model achieved an F1 score of 0.914 for detecting all supplements. Individual supplement detection had a variable correlation with survey responses, ranging from an F1 of 0.83 for calcium to an F1 of 0.39 for folic acid. Our study demonstrated good NLP performance while also finding that self-reported supplement use is not always consistent with the documented use in clinical records.</jats:p>","journal":"Medical Sciences","year":2023,"id":622284,"datarank":0.20794415416798362,"base_score":1.3862943611198906,"endowment":1.3862943611198906,"self_citation_contribution":0.20794415416798362,"citation_network_contribution":0.0,"self_endowment_contribution":0.20794415416798362,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":3,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1607742,"name":"Terri Elizabeth Workman","orcid":null,"position":1,"is_corresponding":false},{"id":682092,"name":"Yijun Shao","orcid":"0000-0001-6419-7963","position":2,"is_corresponding":false},{"id":395185,"name":"Yan Cheng","orcid":"0000-0001-7189-3991","position":3,"is_corresponding":false},{"id":1122376,"name":"Senait Tekle","orcid":"0000-0001-6998-1714","position":4,"is_corresponding":false},{"id":664727,"name":"Jennifer H. Garvin","orcid":"0000-0002-8986-7211","position":5,"is_corresponding":false},{"id":1607743,"name":"Cynthia A. Brandt","orcid":null,"position":6,"is_corresponding":false},{"id":395186,"name":"Qing Zeng‐Treitler","orcid":"0000-0002-8353-7473","position":7,"is_corresponding":false},{"id":1011874,"name":"Douglas Redd","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Patient Dietary Supplements Use: Do Results from Natural Language Processing of Clinical Notes Agree with Survey Data?","abstract":"<jats:p>There is widespread use of dietary supplements, some prescribed but many taken without a physician’s guidance. There are many potential interactions between supplements and both over-the-counter and prescription medications in ways that are unknown to patients. Structured medical records do not adequately document supplement use; however, unstructured clinical notes often contain extra information on supplements. We studied a group of 377 patients from three healthcare facilities and developed a natural language processing (NLP) tool to detect supplement use. Using surveys of these patients, we investigated the correlation between self-reported supplement use and NLP extractions from the clinical notes. Our model achieved an F1 score of 0.914 for detecting all supplements. Individual supplement detection had a variable correlation with survey responses, ranging from an F1 of 0.83 for calcium to an F1 of 0.39 for folic acid. Our study demonstrated good NLP performance while also finding that self-reported supplement use is not always consistent with the documented use in clinical records.</jats:p>","is_dataset_classified":null,"base_score":1.3862943611198906,"endowment":1.3862943611198906,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"37367736","pmcid":"PMC10304046","openalex_id":"https://openalex.org/W4378082549","authors":[],"funders":[{"funder_name":"Clinical and Translational Science Institute at Children’s National (CTSI-CN)","grant_id":"UL1TR001876","title":null},{"funder_name":"Clinical and Translational Science Institute at Children’s National (CTSI-CN)","grant_id":"KL2TR001877","title":null},{"funder_name":"Clinical and Translational Science Institute at Children’s National (CTSI-CN)","grant_id":"PPO 14-382","title":null},{"funder_name":"National Institutes of Health","grant_id":"5KL2TR001877-03","title":"Clinical and Translational Science Institute at Childrens National-Mentored Career Development Core"},{"funder_name":"National Institutes of Health","grant_id":"1UL1TR001876-01","title":"Clinical and Translational Science Institute at Childrens National"}],"total_grants":5,"fwci":0.4278,"citation_percentile":0.57286299,"influential_citations":0,"citation_trend":[{"year":2024,"count":1},{"year":2025,"count":1},{"year":2026,"count":1}],"oa_status":"gold","license":"cc-by","oa_locations":[{"url":"https://www.mdpi.com/2076-3271/11/2/37/pdf?version=1684912395","host_type":"journal"},{"url":"https://www.mdpi.com/2076-3271/11/2/37/pdf?version=1684912395","host_type":"publisher"},{"url":"https://www.mdpi.com/2076-3271/11/2/37/pdf","host_type":"publisher"},{"url":"https://doi.org/10.3390/medsci11020037","host_type":"journal"},{"url":"https://pubmed.ncbi.nlm.nih.gov/37367736","host_type":"repository"},{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10304046","host_type":"repository"},{"url":"https://doaj.org/article/2194dda706fb49a3a595c689357a2764","host_type":"repository"},{"url":"https://dx.doi.org/10.3390/medsci11020037","host_type":"repository"},{"url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10304046/pdf/medsci-11-00037.pdf","host_type":"repository"},{"url":"https://europepmc.org/articles/PMC10304046","host_type":"Europe_PMC"},{"url":"https://europepmc.org/articles/PMC10304046?pdf=render","host_type":"Europe_PMC"},{"url":"http://dx.doi.org/10.3390/medsci11020037","host_type":""}],"fields_of_study":["Pharmaceutical Practices and Patient Outcomes","Complementary and Alternative Medicine Studies","Health Sciences Research and Education","03 medical and health sciences","0302 clinical medicine","Humans","Electronic Health Records","Natural Language Processing","Dietary Supplements","Self Report"],"mesh_terms":["Humans","Natural Language Processing","Dietary Supplements","Electronic Health Records","Self Report"],"keywords":["Medicine","Medical prescription","Dietary supplement","Medical record","Correlation","Alternative medicine","Family medicine","Internal medicine","Pathology","Pharmacology","Dietary Supplements","Machine Learning","Natural Language Processing","R","Humans","Electronic Health Records","Self Report","Article"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Quality Education"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-03T18:59:56.965355Z","pmid":null,"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":[]}