Automated indexing using NLM's Medical Text Indexer (MTI) compared to human indexing in Medline: a pilot study
Objective: In 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM announced that it would fully automate its indexing in Medline with an improved MTI by mid-2022. This pilot study examines indexing using a samp...
Saved in:
| Published in: | Journal of the Medical Library Association Vol. 111; no. 3; pp. 684 - 695 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
Medical Library Association
10.07.2023
University Library System, University of Pittsburgh |
| Subjects: | |
| ISSN: | 1536-5050, 1558-9439, 1558-9439 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Objective: In 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM announced that it would fully automate its indexing in Medline with an improved MTI by mid-2022. This pilot study examines indexing using a sample of records in Medline from 2000, and how an early, public version of MTI's outputs compares to records created by human indexers.
Methods: This pilot study examines twenty Medline records from 2000, a year before the MTI was introduced as a MeSH term recommender. We identified twenty higher- and lower-impact biomedical journals based on Journal Impact Factor (JIF) and examined the indexing of papers by feeding their PubMed records into the Interactive MTI tool.
Results: In the sample, we found key differences between automated and human-indexed Medline records: MTI assigned more terms and used them more accurately for citations in the higher JIF group, and MTI tended to rank the Male check tag more highly than the Female check tag and to omit Aged check tags. Sometimes MTI chose more specific terms than human indexers but was inconsistent in applying specificity principles.
Conclusion: NLM’s transition to fully automated indexing of the biomedical literature could introduce or perpetuate inconsistencies and biases in Medline. Librarians and searchers should assess changes to index terms, and their impact on PubMed’s mapping features for a range of topics. Future research should evaluate automated indexing as it pertains to finding clinical information effectively, and in performing systematic searches. |
|---|---|
| AbstractList | Objective: In 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM announced that it would fully automate its indexing in Medline with an improved MTI by mid-2022. This pilot study examines indexing using a sample of records in Medline from 2000, and how an early, public version of MTI's outputs compares to records created by human indexers. Methods: This pilot study examines twenty Medline records from 2000, a year before the MTI was introduced as a MeSH term recommender. We identified twenty higher- and lower-impact biomedical journals based on Journal Impact Factor (JIF) and examined the indexing of papers by feeding their PubMed records into the Interactive MTI tool. Results: In the sample, we found key differences between automated and human-indexed Medline records: MTI assigned more terms and used them more accurately for citations in the higher JIF group, and MTI tended to rank the Male check tag more highly than the Female check tag and to omit Aged check tags. Sometimes MTI chose more specific terms than human indexers but was inconsistent in applying specificity principles. Conclusion: NLM’s transition to fully automated indexing of the biomedical literature could introduce or perpetuate inconsistencies and biases in Medline. Librarians and searchers should assess changes to index terms, and their impact on PubMed’s mapping features for a range of topics. Future research should evaluate automated indexing as it pertains to finding clinical information effectively, and in performing systematic searches. In 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM announced that it would fully automate its indexing in Medline with an improved MTI by mid-2022. This pilot study examines indexing using a sample of records in Medline from 2000, and how an early, public version of MTI's outputs compares to records created by human indexers.ObjectiveIn 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM announced that it would fully automate its indexing in Medline with an improved MTI by mid-2022. This pilot study examines indexing using a sample of records in Medline from 2000, and how an early, public version of MTI's outputs compares to records created by human indexers.This pilot study examines twenty Medline records from 2000, a year before the MTI was introduced as a MeSH term recommender. We identified twenty higher- and lower-impact biomedical journals based on Journal Impact Factor (JIF) and examined the indexing of papers by feeding their PubMed records into the Interactive MTI tool.MethodsThis pilot study examines twenty Medline records from 2000, a year before the MTI was introduced as a MeSH term recommender. We identified twenty higher- and lower-impact biomedical journals based on Journal Impact Factor (JIF) and examined the indexing of papers by feeding their PubMed records into the Interactive MTI tool.In the sample, we found key differences between automated and human-indexed Medline records: MTI assigned more terms and used them more accurately for citations in the higher JIF group, and MTI tended to rank the Male check tag more highly than the Female check tag and to omit Aged check tags. Sometimes MTI chose more specific terms than human indexers but was inconsistent in applying specificity principles.ResultsIn the sample, we found key differences between automated and human-indexed Medline records: MTI assigned more terms and used them more accurately for citations in the higher JIF group, and MTI tended to rank the Male check tag more highly than the Female check tag and to omit Aged check tags. Sometimes MTI chose more specific terms than human indexers but was inconsistent in applying specificity principles.NLM's transition to fully automated indexing of the biomedical literature could introduce or perpetuate inconsistencies and biases in Medline. Librarians and searchers should assess changes to index terms, and their impact on PubMed's mapping features for a range of topics. Future research should evaluate automated indexing as it pertains to finding clinical information effectively, and in performing systematic searches.ConclusionNLM's transition to fully automated indexing of the biomedical literature could introduce or perpetuate inconsistencies and biases in Medline. Librarians and searchers should assess changes to index terms, and their impact on PubMed's mapping features for a range of topics. Future research should evaluate automated indexing as it pertains to finding clinical information effectively, and in performing systematic searches. Objective: In 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM announced that it would fully automate its indexing in Medline with an improved MTI by mid-2022. This pilot study examines indexing using a sample of records in Medline from 2000, and how an early, public version of MTI's outputs compares to records created by human indexers. Methods: This pilot study examines twenty Medline records from 2000, a year before the MTI was introduced as a MeSH term recommender. We identified twenty higher- and lower-impact biomedical journals based on Journal Impact Factor (JIF) and examined the indexing of papers by feeding their PubMed records into the Interactive MTI tool. Results: In the sample, we found key differences between automated and human-indexed Medline records: MTI assigned more terms and used them more accurately for citations in the higher JIF group, and MTI tended to rank the Male check tag more highly than the Female check tag and to omit Aged check tags. Sometimes MTI chose more specific terms than human indexers but was inconsistent in applying specificity principles. Conclusion: NLM’s transition to fully automated indexing of the biomedical literature could introduce or perpetuate inconsistencies and biases in Medline. Librarians and searchers should assess changes to index terms, and their impact on PubMed’s mapping features for a range of topics. Future research should evaluate automated indexing as it pertains to finding clinical information effectively, and in performing systematic searches. In 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM announced that it would fully automate its indexing in Medline with an improved MTI by mid-2022. This pilot study examines indexing using a sample of records in Medline from 2000, and how an early, public version of MTI's outputs compares to records created by human indexers. This pilot study examines twenty Medline records from 2000, a year before the MTI was introduced as a MeSH term recommender. We identified twenty higher- and lower-impact biomedical journals based on Journal Impact Factor (JIF) and examined the indexing of papers by feeding their PubMed records into the Interactive MTI tool. In the sample, we found key differences between automated and human-indexed Medline records: MTI assigned more terms and used them more accurately for citations in the higher JIF group, and MTI tended to rank the Male check tag more highly than the Female check tag and to omit Aged check tags. Sometimes MTI chose more specific terms than human indexers but was inconsistent in applying specificity principles. NLM's transition to fully automated indexing of the biomedical literature could introduce or perpetuate inconsistencies and biases in Medline. Librarians and searchers should assess changes to index terms, and their impact on PubMed's mapping features for a range of topics. Future research should evaluate automated indexing as it pertains to finding clinical information effectively, and in performing systematic searches. Objective: In 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM announced that it would fully automate its indexing in Medline with an improved MTI by mid-2022. This pilot study examines indexing using a sample of records in Medline from 2000, and how an early, public version of MTI's outputs compares to records created by human indexers. Methods: This pilot study examines twenty Medline records from 2000, a year before the MTI was introduced as a MeSH term recommender. We identified twenty higher- and lower-impact biomedical journals based on Journal Impact Factor (JIF) and examined the indexing of papers by feeding their PubMed records into the Interactive MTI tool. Results: In the sample, we found key differences between automated and human-indexed Medline records: MTI assigned more terms and used them more accurately for citations in the higher JIF group, and MTI tended to rank the Male check tag more highly than the Female check tag and to omit Aged check tags. Sometimes MTI chose more specific terms than human indexers but was inconsistent in applying specificity principles. Conclusion: NLM's transition to fully automated indexing of the biomedical literature could introduce or perpetuate inconsistencies and biases in Medline. Librarians and searchers should assess changes to index terms, and their impact on PubMed's mapping features for a range of topics. Future research should evaluate automated indexing as it pertains to finding clinical information effectively, and in performing systematic searches. Keywords: Automated indexing; human indexers; information retrieval; Medical Text Indexer (MTI); Medline; PubMed. |
| Audience | Academic |
| Author | Giustini, Dean Bullard, Julia Chen, Yin Yin |
| Author_xml | – sequence: 1 givenname: Yin Yin orcidid: 0000-0003-0350-0513 surname: Chen fullname: Chen, Yin Yin – sequence: 2 givenname: Julia orcidid: 0000-0002-6815-0609 surname: Bullard fullname: Bullard, Julia – sequence: 3 givenname: Dean orcidid: 0000-0002-6197-8788 surname: Giustini fullname: Giustini, Dean |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37483360$$D View this record in MEDLINE/PubMed |
| BookMark | eNp1ks2P0zAQxSO0iP2AK0cUiQPLocWOnTjZC6pWfFRq4VLO1sSedF0ldokdtPvfY9NllyKQpXjkvPeLJ_POsxPrLGbZS0rmJW3Kd7uhh3lBCjanZV0_yc5oWdazhrPmJNWsmpWkJKfZufc7QqioBXmWnTLBa8YqcpbZxRTcAAF1bqzGW2O3-eTT88tq_cbna9RGQZ9v8Dbky6TAMb9cb5Zvc-WGPYzRGFx-Mw1gHwnGJmNvLF7lkO9N70Luw6TvnmdPO-g9vrjfL7JvHz9srj_PVl8_La8Xq5kqCx5mrSCNIJUA0dQtIVp3Xcl4o3XBlWiwwQpFy7iqObRYc0oKKEFXwIBTxNjbRbY8cLWDndyPZoDxTjow8teBG7cSxmBUj7LgXY1t1RW05LFsQVNOgZOqYALquois9wfWfmoH1AptGKE_gh6_seZGbt0PSQmr0jgi4fKeMLrvE_ogB-MV9j1YdJOXRWyBkzjA9LHXB-kW4t2M7VxEqiSXCxEnXFAmkmr-D1VcGgejYkI6E8-PDK_-7OHh8r-D8EhUo_N-xO5BQolMSZMpaTIlTaakRQP_y6BMgGBc-gem_5_tJ-a-1hs |
| CitedBy_id | crossref_primary_10_1038_s41597_023_02869_7 crossref_primary_10_1080_03007995_2024_2350612 crossref_primary_10_1186_s13643_024_02551_y crossref_primary_10_1016_j_sapharm_2025_05_008 crossref_primary_10_1080_02763869_2025_2537075 crossref_primary_10_1093_ijpp_riae042 crossref_primary_10_1016_j_sapharm_2024_06_003 |
| ContentType | Journal Article |
| Copyright | Copyright © 2023 Eileen Chen, Julia Bullard, Dean Giustini. COPYRIGHT 2023 Medical Library Association Copyright © 2023 Eileen Chen, Julia Bullard, Dean Giustini 2023 |
| Copyright_xml | – notice: Copyright © 2023 Eileen Chen, Julia Bullard, Dean Giustini. – notice: COPYRIGHT 2023 Medical Library Association – notice: Copyright © 2023 Eileen Chen, Julia Bullard, Dean Giustini 2023 |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 5PM DOA |
| DOI | 10.5195/jmla.2023.1588 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic CrossRef MEDLINE |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Library & Information Science |
| EISSN | 1558-9439 |
| EndPage | 695 |
| ExternalDocumentID | oai_doaj_org_article_24f8eb6f21544f8bad141a406237a882 PMC10361558 A758821372 37483360 10_5195_jmla_2023_1588 |
| Genre | Journal Article |
| GeographicLocations | United States |
| GeographicLocations_xml | – name: United States |
| GroupedDBID | --- .4I .GJ 04C 29L 2WC 36B 5GY 5VS 6PF 77I 7RV 7X7 85S 88E 8AO 8FI 8FJ 8G5 8R4 8R5 AAFWJ AAWTL AAYXX ABDBF ABPPZ ABUWG ACGFO ACHQT ACIHN ACUHS ADBBV ADOJX AEAQA AFFHD AFKRA AFPKN AHMBA ALMA_UNASSIGNED_HOLDINGS ALSLI AOIJS AQUVI AZQEC B0M BAIFH BAWUL BBTPI BCNDV BENPR BKEYQ BMSDO BPHCQ BVXVI CCPQU CITATION CNYFK CS3 DU5 DWQXO E3Z EAD EAP EBC EBD EBS ECF ECT EHE EIHBH EJD ELW EMB EMK EMOBN EPL ESX EX3 F5P FYUFA GNUQQ GROUPED_DOAJ GUQSH GX1 HMCUK HML I-F IAO IHR IHW INH INR ITC KQ8 L7B M0T M1O M1P M2O NAPCQ OK1 OVT PCD PHGZM PHGZT PIMPY PJZUB PPXIY PQQKQ PROAC PRQQA PSQYO PV9 Q2X QF3 QF4 QN7 RNS RPM RXW RZL SV3 TR2 TUS UKHRP W2D WOW WQ9 XSB XZL ZXP ~8M 0B8 3V. AFRXU ALIPV CGR CUY CVF DIK ECM EIF M~E NPM 7X8 PUEGO 5PM |
| ID | FETCH-LOGICAL-c524t-b7097067a798b00ddff5349dd24c79e9e6e7b34c84abe84102a5ad6a3a41ee483 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 14 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001031665100005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1536-5050 1558-9439 |
| IngestDate | Mon Nov 10 04:34:43 EST 2025 Tue Nov 04 02:06:31 EST 2025 Fri Sep 05 08:36:08 EDT 2025 Tue Nov 11 10:17:25 EST 2025 Sat Nov 29 10:58:23 EST 2025 Thu Jan 02 22:33:33 EST 2025 Sat Nov 29 05:53:28 EST 2025 Tue Nov 18 22:19:40 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | Automated indexing Medline PubMed Medical Text Indexer (MTI) information retrieval human indexers |
| Language | English |
| License | https://creativecommons.org/licenses/by/4.0 Copyright © 2023 Eileen Chen, Julia Bullard, Dean Giustini. This work is licensed under a Creative Commons Attribution 4.0 International License. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c524t-b7097067a798b00ddff5349dd24c79e9e6e7b34c84abe84102a5ad6a3a41ee483 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-0350-0513 0000-0002-6815-0609 0000-0002-6197-8788 |
| OpenAccessLink | https://doaj.org/article/24f8eb6f21544f8bad141a406237a882 |
| PMID | 37483360 |
| PQID | 2841401582 |
| PQPubID | 23479 |
| PageCount | 12 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_24f8eb6f21544f8bad141a406237a882 pubmedcentral_primary_oai_pubmedcentral_nih_gov_10361558 proquest_miscellaneous_2841401582 gale_infotracmisc_A758821372 gale_infotracacademiconefile_A758821372 pubmed_primary_37483360 crossref_primary_10_5195_jmla_2023_1588 crossref_citationtrail_10_5195_jmla_2023_1588 |
| PublicationCentury | 2000 |
| PublicationDate | 20230710 |
| PublicationDateYYYYMMDD | 2023-07-10 |
| PublicationDate_xml | – month: 7 year: 2023 text: 20230710 day: 10 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Journal of the Medical Library Association |
| PublicationTitleAlternate | J Med Libr Assoc |
| PublicationYear | 2023 |
| Publisher | Medical Library Association University Library System, University of Pittsburgh |
| Publisher_xml | – name: Medical Library Association – name: University Library System, University of Pittsburgh |
| SSID | ssj0017870 |
| Score | 2.4077916 |
| Snippet | Objective: In 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM... In 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM announced that... |
| SourceID | doaj pubmedcentral proquest gale pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 684 |
| SubjectTerms | Abstracting and Indexing - methods Abstracting and Indexing - standards Automated indexing human indexers Indexing information retrieval Libraries Medical Subject Headings Medical Text Indexer (MTI) MEDLINE National Library of Medicine (U.S.) Original Investigation Pilot Projects PubMed Technology application United States |
| Title | Automated indexing using NLM's Medical Text Indexer (MTI) compared to human indexing in Medline: a pilot study |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/37483360 https://www.proquest.com/docview/2841401582 https://pubmed.ncbi.nlm.nih.gov/PMC10361558 https://doaj.org/article/24f8eb6f21544f8bad141a406237a882 |
| Volume | 111 |
| WOSCitedRecordID | wos001031665100005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1558-9439 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017870 issn: 1536-5050 databaseCode: DOA dateStart: 20020101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 1558-9439 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017870 issn: 1536-5050 databaseCode: 7X7 dateStart: 20030101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: Healthcare Administration Database customDbUrl: eissn: 1558-9439 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017870 issn: 1536-5050 databaseCode: M0T dateStart: 20030101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthmanagement providerName: ProQuest – providerCode: PRVPQU databaseName: Library Science Database customDbUrl: eissn: 1558-9439 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017870 issn: 1536-5050 databaseCode: M1O dateStart: 20030101 isFulltext: true titleUrlDefault: https://search.proquest.com/libraryscience providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1558-9439 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017870 issn: 1536-5050 databaseCode: BENPR dateStart: 20030101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Nursing and Allied Health Journals - PSU access expires 11/30/25. customDbUrl: eissn: 1558-9439 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017870 issn: 1536-5050 databaseCode: 7RV dateStart: 20030101 isFulltext: true titleUrlDefault: https://search.proquest.com/nahs providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1558-9439 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017870 issn: 1536-5050 databaseCode: PIMPY dateStart: 20030101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: Research Library customDbUrl: eissn: 1558-9439 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017870 issn: 1536-5050 databaseCode: M2O dateStart: 20030101 isFulltext: true titleUrlDefault: https://search.proquest.com/pqrl providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3Nb9MwFLdg48Bl4nuFrTISYnAIS2wndrh1aBOT1lJNZSony7Ed6FTSaU35-3nPSbtGCHHh8g7xS2K_D7_nxP49Qt7EkqnSeRXxuBSRME5FJpUyYiK1LJesjAOYztWFHI3UdJqPt0p94Z6wBh64EdwxE6XyRVYyhI0pVWFcIhIDYYhxaSA9xNkXsp71Yqr9f4Bm2CClZhHE-LiBa0QklePrn3PEG2L8Q5KGeit34Sig9v85N28Fp-7Gya1IdPaI7LUpJB00XX9M7vnqCTlsDyDQt7Q9YYQSp63rPiXVYFUv4KJ3NAAkQsSiuOf9Ox1dDI-WtP1hQycwWcMTHJZiou-Gk_P3dL1NndYLGkr63T1hVuGNmKl-pIbezOaLmgbA2mfk69np5NPnqK21ENmUiToqZJxLiFxG5go80bmyTLnInWPCytznPvOy4MIqYQqvBKQlJjUuM9yIxHuh-HOyUy0qv09oLj1zLs0kswZUBneXXBQ2jbNCgTZtj0RrkWvbApFjPYy5hgUJqkijijSqSKOKeuRow3_TQHD8lfMENbjhQujscAEMSrcGpf9lUPA61L9GB4duWdOeU4DBIVSWHsAKS7GES-A86HCCY9pO8-u1BWlswt1slV-slhpSAlzXpviyF41FbfqMcECcZ3GPqI6tdQbVbalmPwIueALZCKSH6uX_EMMr8hDlip-xk_iA7NS3K39IHthf9Wx52yf35eUV0qkMVPXJ7snpaHzZD34IdBhPkCZfkDKgu-Pz4fjbb3UhNQU |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Automated+indexing+using+NLM%27s+Medical+Text+Indexer+%28MTI%29+compared+to+human+indexing+in+Medline%3A+a+pilot+study&rft.jtitle=Journal+of+the+Medical+Library+Association&rft.au=Yin+Yin+Chen&rft.au=Julia+Bullard&rft.au=Dean+Giustini&rft.date=2023-07-10&rft.pub=University+Library+System%2C+University+of+Pittsburgh&rft.issn=1536-5050&rft.eissn=1558-9439&rft.volume=111&rft.issue=3&rft_id=info:doi/10.5195%2Fjmla.2023.1588&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_24f8eb6f21544f8bad141a406237a882 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1536-5050&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1536-5050&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1536-5050&client=summon |