Use of ChatGPT for Determining Clinical and Surgical Treatment of Lumbar Disc Herniation With Radiculopathy: A North American Spine Society Guideline Comparison
Objective: Large language models like chat generative pre-trained transformer (ChatGPT) have found success in various sectors, but their application in the medical field remains limited. This study aimed to assess the feasibility of using ChatGPT to provide accurate medical information to patients,...
Saved in:
| Published in: | Neurospine Vol. 21; no. 1; pp. 149 - 158 |
|---|---|
| Main Authors: | , , , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Korean Spinal Neurosurgery Society
01.03.2024
대한척추신경외과학회 |
| Subjects: | |
| ISSN: | 2586-6583, 2586-6591 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Objective: Large language models like chat generative pre-trained transformer (ChatGPT) have found success in various sectors, but their application in the medical field remains limited. This study aimed to assess the feasibility of using ChatGPT to provide accurate medical information to patients, specifically evaluating how well ChatGPT versions 3.5 and 4 aligned with the 2012 North American Spine Society (NASS) guidelines for lumbar disk herniation with radiculopathy.Methods: ChatGPT's responses to questions based on the NASS guidelines were analyzed for accuracy. Three new categories—overconclusiveness, supplementary information, and incompleteness—were introduced to deepen the analysis. Overconclusiveness referred to recommendations not mentioned in the NASS guidelines, supplementary information denoted additional relevant details, and incompleteness indicated omitted crucial information from the NASS guidelines.Results: Out of 29 clinical guidelines evaluated, ChatGPT-3.5 demonstrated accuracy in 15 responses (52%), while ChatGPT-4 achieved accuracy in 17 responses (59%). ChatGPT-3.5 was overconclusive in 14 responses (48%), while ChatGPT-4 exhibited overconclusiveness in 13 responses (45%). Additionally, ChatGPT-3.5 provided supplementary information in 24 responses (83%), and ChatGPT-4 provided supplemental information in 27 responses (93%). In terms of incompleteness, ChatGPT-3.5 displayed this in 11 responses (38%), while ChatGPT-4 showed incompleteness in 8 responses (23%).Conclusion: ChatGPT shows promise for clinical decision-making, but both patients and healthcare providers should exercise caution to ensure safety and quality of care. While these results are encouraging, further research is necessary to validate the use of large language models in clinical settings. |
|---|---|
| AbstractList | Objective: Large language models like chat generative pre-trained transformer (ChatGPT) have found success in various sectors, but their application in the medical field remains limited. This study aimed to assess the feasibility of using ChatGPT to provide accurate medical information to patients, specifically evaluating how well ChatGPT versions 3.5 and 4 aligned with the 2012 North American Spine Society (NASS) guidelines for lumbar disk herniation with radiculopathy.
Methods: ChatGPT's responses to questions based on the NASS guidelines were analyzed for accuracy. Three new categories—overconclusiveness, supplementary information, and incompleteness—were introduced to deepen the analysis. Overconclusiveness referred to recommendations not mentioned in the NASS guidelines, supplementary information denoted additional relevant details, and incompleteness indicated omitted crucial information from the NASS guidelines.
Results: Out of 29 clinical guidelines evaluated, ChatGPT-3.5 demonstrated accuracy in 15 responses (52%), while ChatGPT-4 achieved accuracy in 17 responses (59%). ChatGPT-3.5 was overconclusive in 14 responses (48%), while ChatGPT-4 exhibited overconclusiveness in 13 responses (45%). Additionally, ChatGPT-3.5 provided supplementary information in 24 responses (83%), and ChatGPT-4 provided supplemental information in 27 responses (93%). In terms of incompleteness, ChatGPT-3.5 displayed this in 11 responses (38%), while ChatGPT-4 showed incompleteness in 8 responses (23%).
Conclusion: ChatGPT shows promise for clinical decision-making, but both patients and healthcare providers should exercise caution to ensure safety and quality of care. While these results are encouraging, further research is necessary to validate the use of large language models in clinical settings. KCI Citation Count: 0 Objective Large language models like chat generative pre-trained transformer (ChatGPT) have found success in various sectors, but their application in the medical field remains limited. This study aimed to assess the feasibility of using ChatGPT to provide accurate medical information to patients, specifically evaluating how well ChatGPT versions 3.5 and 4 aligned with the 2012 North American Spine Society (NASS) guidelines for lumbar disk herniation with radiculopathy. Methods ChatGPT's responses to questions based on the NASS guidelines were analyzed for accuracy. Three new categories—overconclusiveness, supplementary information, and incompleteness—were introduced to deepen the analysis. Overconclusiveness referred to recommendations not mentioned in the NASS guidelines, supplementary information denoted additional relevant details, and incompleteness indicated omitted crucial information from the NASS guidelines. Results Out of 29 clinical guidelines evaluated, ChatGPT-3.5 demonstrated accuracy in 15 responses (52%), while ChatGPT-4 achieved accuracy in 17 responses (59%). ChatGPT-3.5 was overconclusive in 14 responses (48%), while ChatGPT-4 exhibited overconclusiveness in 13 responses (45%). Additionally, ChatGPT-3.5 provided supplementary information in 24 responses (83%), and ChatGPT-4 provided supplemental information in 27 responses (93%). In terms of incompleteness, ChatGPT-3.5 displayed this in 11 responses (38%), while ChatGPT-4 showed incompleteness in 8 responses (23%). Conclusion ChatGPT shows promise for clinical decision-making, but both patients and healthcare providers should exercise caution to ensure safety and quality of care. While these results are encouraging, further research is necessary to validate the use of large language models in clinical settings. Large language models like chat generative pre-trained transformer (ChatGPT) have found success in various sectors, but their application in the medical field remains limited. This study aimed to assess the feasibility of using ChatGPT to provide accurate medical information to patients, specifically evaluating how well ChatGPT versions 3.5 and 4 aligned with the 2012 North American Spine Society (NASS) guidelines for lumbar disk herniation with radiculopathy.OBJECTIVELarge language models like chat generative pre-trained transformer (ChatGPT) have found success in various sectors, but their application in the medical field remains limited. This study aimed to assess the feasibility of using ChatGPT to provide accurate medical information to patients, specifically evaluating how well ChatGPT versions 3.5 and 4 aligned with the 2012 North American Spine Society (NASS) guidelines for lumbar disk herniation with radiculopathy.ChatGPT's responses to questions based on the NASS guidelines were analyzed for accuracy. Three new categories-overconclusiveness, supplementary information, and incompleteness-were introduced to deepen the analysis. Overconclusiveness referred to recommendations not mentioned in the NASS guidelines, supplementary information denoted additional relevant details, and incompleteness indicated omitted crucial information from the NASS guidelines.METHODSChatGPT's responses to questions based on the NASS guidelines were analyzed for accuracy. Three new categories-overconclusiveness, supplementary information, and incompleteness-were introduced to deepen the analysis. Overconclusiveness referred to recommendations not mentioned in the NASS guidelines, supplementary information denoted additional relevant details, and incompleteness indicated omitted crucial information from the NASS guidelines.Out of 29 clinical guidelines evaluated, ChatGPT-3.5 demonstrated accuracy in 15 responses (52%), while ChatGPT-4 achieved accuracy in 17 responses (59%). ChatGPT-3.5 was overconclusive in 14 responses (48%), while ChatGPT-4 exhibited overconclusiveness in 13 responses (45%). Additionally, ChatGPT-3.5 provided supplementary information in 24 responses (83%), and ChatGPT-4 provided supplemental information in 27 responses (93%). In terms of incompleteness, ChatGPT-3.5 displayed this in 11 responses (38%), while ChatGPT-4 showed incompleteness in 8 responses (23%).RESULTSOut of 29 clinical guidelines evaluated, ChatGPT-3.5 demonstrated accuracy in 15 responses (52%), while ChatGPT-4 achieved accuracy in 17 responses (59%). ChatGPT-3.5 was overconclusive in 14 responses (48%), while ChatGPT-4 exhibited overconclusiveness in 13 responses (45%). Additionally, ChatGPT-3.5 provided supplementary information in 24 responses (83%), and ChatGPT-4 provided supplemental information in 27 responses (93%). In terms of incompleteness, ChatGPT-3.5 displayed this in 11 responses (38%), while ChatGPT-4 showed incompleteness in 8 responses (23%).ChatGPT shows promise for clinical decision-making, but both patients and healthcare providers should exercise caution to ensure safety and quality of care. While these results are encouraging, further research is necessary to validate the use of large language models in clinical settings.CONCLUSIONChatGPT shows promise for clinical decision-making, but both patients and healthcare providers should exercise caution to ensure safety and quality of care. While these results are encouraging, further research is necessary to validate the use of large language models in clinical settings. |
| Author | Arroyave, Juan Sebastian Zaidat, Bashar Ahmed, Wasil Cho, Samuel K. Mejia, Mateo Restrepo Rajjoub, Rami Ndjonko, Laura Chelsea Mazudie Zapolsky, Ivan Saturno, Michael |
| Author_xml | – sequence: 1 givenname: Mateo Restrepo orcidid: 0009-0003-0457-3308 surname: Mejia fullname: Mejia, Mateo Restrepo – sequence: 2 givenname: Juan Sebastian orcidid: 0009-0003-9480-0657 surname: Arroyave fullname: Arroyave, Juan Sebastian – sequence: 3 givenname: Michael surname: Saturno fullname: Saturno, Michael – sequence: 4 givenname: Laura Chelsea Mazudie orcidid: 0000-0002-3153-4967 surname: Ndjonko fullname: Ndjonko, Laura Chelsea Mazudie – sequence: 5 givenname: Bashar orcidid: 0000-0002-8823-720X surname: Zaidat fullname: Zaidat, Bashar – sequence: 6 givenname: Rami orcidid: 0009-0005-2990-7874 surname: Rajjoub fullname: Rajjoub, Rami – sequence: 7 givenname: Wasil orcidid: 0009-0001-0904-1891 surname: Ahmed fullname: Ahmed, Wasil – sequence: 8 givenname: Ivan surname: Zapolsky fullname: Zapolsky, Ivan – sequence: 9 givenname: Samuel K. orcidid: 0000-0001-7511-2486 surname: Cho fullname: Cho, Samuel K. |
| BackLink | https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART003067530$$DAccess content in National Research Foundation of Korea (NRF) |
| BookMark | eNp1kk1vEzEQhleoiJbQM1cfEVJaf9vLBUUB0kgRoCYVR8vrnU1Md-3g3UXKv-Gn4iYFqUicxh6_76MZz7wszkIMUBSvCb4inHJxHforyrjCgl4JKp8VF1RoOZWiJGd_z5qdF5d97yvMuRKcMfKiOGealkRxeVH8uusBxQbNd3ZYfN2gJib0AQZInQ8-bNG8zdHZFtlQo_WYtsfLJoEdOgjDg3U1dpXNLt87dAMpeDv4GNA3P-zQra29G9u4t8Pu8A7N0OeYcnrWQcqggNZ7HwCto_MwHNBi9DW0D5l57PY2-T6GV8XzxrY9XD7GSXH36eNmfjNdfVks57PV1DGt5JQQ5iSucAWNxpw4DC63i2uOayEorahgYKXTTPOGO10SqxllBNfQKGkrzSbF2xM3pMbcO2-i9ce4jeY-mdntZmlIJmsmcRYvT-I62u9mn3xn0-HoOCZi2hqbBu9aMFBiVkvtBFENF6oqgTleSlUpkI3iTWa9P7H2Y9VB7fKvJts-gT59CX6Xi_qZqylLKvNEJ8WbR0KKP0boB9PlWUDb2gBx7A0tKRaKYayyVJykLsW-T9AY54fjvDLat5lpjqtlQradVsvk1cq-6398f-r7n-M3p7TRzg |
| CitedBy_id | crossref_primary_10_1016_j_xnsj_2024_100580 crossref_primary_10_1016_j_jposna_2024_100135 crossref_primary_10_14245_ns_2550094_047 crossref_primary_10_1007_s00586_025_08994_8 crossref_primary_10_1002_jeo2_70393 crossref_primary_10_1177_15563316251340696 crossref_primary_10_1007_s11657_025_01587_4 crossref_primary_10_1177_20552076241311939 crossref_primary_10_2196_59607 crossref_primary_10_1177_20552076251367645 crossref_primary_10_3390_jcm14165876 crossref_primary_10_1097_BPO_0000000000002890 crossref_primary_10_1177_24730114251352494 crossref_primary_10_3389_fdgth_2025_1574287 crossref_primary_10_1186_s12883_025_04280_8 crossref_primary_10_1007_s00701_025_06610_8 crossref_primary_10_1097_MS9_0000000000003519 crossref_primary_10_1038_s41746_025_01752_6 crossref_primary_10_1186_s40001_025_02296_x crossref_primary_10_1016_j_wneu_2024_05_172 crossref_primary_10_1016_j_arthro_2025_03_066 crossref_primary_10_2196_64486 crossref_primary_10_1007_s13755_025_00368_0 crossref_primary_10_1016_j_spinee_2025_02_010 crossref_primary_10_1186_s13018_025_05831_y crossref_primary_10_1007_s10143_025_03785_7 crossref_primary_10_1016_j_fas_2024_12_003 crossref_primary_10_31616_asj_2024_0301 |
| Cites_doi | 10.1016/j.jor.2013.07.005 10.7759/cureus.35179 10.3928/01477447-20210618-11 10.1007/s00234-023-03252-4 10.1371/journal.pdig.0000198 10.3889/oamjms.2019.679 10.48550/arXiv.2304.14454 10.1016/j.ncl.2007.01.008 10.1016/j.wneu.2022.06.023 10.7759/cureus.48078 10.3390/healthcare11060887 10.1186/s12962-021-00272-w 10.48550/arXiv.2302.12813 10.1016/j.spinee.2020.01.015 10.1177/2192568220968772 10.7759/cureus.40895 10.1016/j.spinee.2013.08.003 10.1016/j.spinee.2023.07.015 |
| ContentType | Journal Article |
| Copyright | Copyright © 2024 by the Korean Spinal Neurosurgery Society 2024 |
| Copyright_xml | – notice: Copyright © 2024 by the Korean Spinal Neurosurgery Society 2024 |
| DBID | AAYXX CITATION 7X8 5PM DOA ACYCR |
| DOI | 10.14245/ns.2347052.526 |
| DatabaseName | CrossRef MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals Korean Citation Index |
| DatabaseTitle | CrossRef MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 2586-6591 |
| EndPage | 158 |
| ExternalDocumentID | oai_kci_go_kr_ARTI_10418360 oai_doaj_org_article_e903d68c517f457b9e3c4967b7e6f74f PMC10992643 10_14245_ns_2347052_526 |
| GroupedDBID | AAYXX ABDBF ADBBV ALMA_UNASSIGNED_HOLDINGS AOIJS BCNDV CITATION GROUPED_DOAJ HYE PGMZT RPM 7X8 M~E 5PM ACYCR OK1 |
| ID | FETCH-LOGICAL-c3876-113c60b0bef8041c0ec4750d40d5522b253ea6c8384f4c891a832310def76ab83 |
| IEDL.DBID | DOA |
| ISSN | 2586-6583 |
| IngestDate | Thu Apr 04 10:27:16 EDT 2024 Fri Oct 03 12:52:59 EDT 2025 Thu Aug 21 18:34:43 EDT 2025 Thu Oct 02 11:51:03 EDT 2025 Tue Nov 18 21:47:01 EST 2025 Sat Nov 29 03:16:12 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| License | This is an open access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3876-113c60b0bef8041c0ec4750d40d5522b253ea6c8384f4c891a832310def76ab83 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 https://doi.org/10.14245/ns.2347052.526 |
| ORCID | 0009-0003-0457-3308 0000-0002-3153-4967 0000-0001-7511-2486 0009-0005-2990-7874 0009-0003-9480-0657 0009-0001-0904-1891 0000-0002-8823-720X |
| OpenAccessLink | https://doaj.org/article/e903d68c517f457b9e3c4967b7e6f74f |
| PMID | 38291746 |
| PQID | 2920573007 |
| PQPubID | 23479 |
| PageCount | 10 |
| ParticipantIDs | nrf_kci_oai_kci_go_kr_ARTI_10418360 doaj_primary_oai_doaj_org_article_e903d68c517f457b9e3c4967b7e6f74f pubmedcentral_primary_oai_pubmedcentral_nih_gov_10992643 proquest_miscellaneous_2920573007 crossref_citationtrail_10_14245_ns_2347052_526 crossref_primary_10_14245_ns_2347052_526 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-03-01 |
| PublicationDateYYYYMMDD | 2024-03-01 |
| PublicationDate_xml | – month: 03 year: 2024 text: 2024-03-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Neurospine |
| PublicationYear | 2024 |
| Publisher | Korean Spinal Neurosurgery Society 대한척추신경외과학회 |
| Publisher_xml | – name: Korean Spinal Neurosurgery Society – name: 대한척추신경외과학회 |
| References | ref13 ref12 ref23 ref14 ref20 ref11 ref22 ref10 ref21 Edmonston (ref6) 2010 ref1 (ref2) 2001 ref19 ref18 ref8 (ref17) 2024 ref7 ref9 Quintans-Júnior (ref16) 2023 ref4 ref3 ref5 Au Yeung (ref15) 2023 |
| References_xml | – ident: ref8 doi: 10.1016/j.jor.2013.07.005 – year: 2001 ident: ref2 – ident: ref23 doi: 10.7759/cureus.35179 – ident: ref7 doi: 10.3928/01477447-20210618-11 – ident: ref21 doi: 10.1007/s00234-023-03252-4 – start-page: 174 volume-title: Infection rate and risk factor analysis in an orthopaedic ambulatory surgical center year: 2010 ident: ref6 – ident: ref1 doi: 10.1371/journal.pdig.0000198 – ident: ref9 doi: 10.3889/oamjms.2019.679 – ident: ref19 doi: 10.48550/arXiv.2304.14454 – ident: ref3 doi: 10.1016/j.ncl.2007.01.008 – ident: ref10 doi: 10.1016/j.wneu.2022.06.023 – volume-title: New models and developer products announced at DevDay [Internet] year: 2024 ident: ref17 – ident: ref22 doi: 10.7759/cureus.48078 – ident: ref20 doi: 10.3390/healthcare11060887 – ident: ref11 doi: 10.1186/s12962-021-00272-w – start-page: 1161098 volume-title: AI chatbots not yet ready for clinical use year: 2023 ident: ref15 – ident: ref14 doi: 10.48550/arXiv.2302.12813 – start-page: e0060 volume-title: ChatGPT: the new panacea of the academic world year: 2023 ident: ref16 – ident: ref12 doi: 10.1016/j.spinee.2020.01.015 – ident: ref13 doi: 10.1177/2192568220968772 – ident: ref18 doi: 10.7759/cureus.40895 – ident: ref4 doi: 10.1016/j.spinee.2013.08.003 – ident: ref5 doi: 10.1016/j.spinee.2023.07.015 |
| SSID | ssib044754331 ssj0002002413 |
| Score | 2.4255893 |
| Snippet | Objective: Large language models like chat generative pre-trained transformer (ChatGPT) have found success in various sectors, but their application in the... Large language models like chat generative pre-trained transformer (ChatGPT) have found success in various sectors, but their application in the medical field... Objective Large language models like chat generative pre-trained transformer (ChatGPT) have found success in various sectors, but their application in the... |
| SourceID | nrf doaj pubmedcentral proquest crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Enrichment Source Index Database |
| StartPage | 149 |
| SubjectTerms | artificial intelligence chatgpt lumbar disk herniation with radiculopathy north american spine society guidelines Original qualitative study 신경외과학 |
| Title | Use of ChatGPT for Determining Clinical and Surgical Treatment of Lumbar Disc Herniation With Radiculopathy: A North American Spine Society Guideline Comparison |
| URI | https://www.proquest.com/docview/2920573007 https://pubmed.ncbi.nlm.nih.gov/PMC10992643 https://doaj.org/article/e903d68c517f457b9e3c4967b7e6f74f https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART003067530 |
| Volume | 21 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| ispartofPNX | Neurospine, 2024, 21(1), , pp.149-158 |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2586-6591 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002002413 issn: 2586-6583 databaseCode: DOA dateStart: 20040101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2586-6591 dateEnd: 99991231 omitProxy: false ssIdentifier: ssib044754331 issn: 2586-6583 databaseCode: M~E dateStart: 20180101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9QwELWg4sAFgQCxQCsjOHBJm8RObPdWln4gQVXRrdibZTt2N2pJquwGiQu_hZ_KTJJdbQ6IC5dEcmzF8Yw9z5nxG0LeKZ76wnEfwWSSEbdZiIyLTcQNN3FhwUQF0yWbEOfncj5XF1upvjAmrKcH7gfuwKuYFbl0WSICz4RVnjmucmGFz4PgAVdfQD1bmynQJGSxw6NAm78tGIrAu1zJaSbzCMwuG3h-0PN3APJNGRdxlu5nSLOwZaI6Jn8wPFUTRiB0HEK5ZZNOHpNHA5ikR_1HPCH3fPWU_L5aeloHOl2Y1enFjAIqpR-HoBewU3RgAr2lpiroZdt0Sx-drQPOsenn9rs10KpcOnrm8eAWio9-K1cL-tUU-MuwxlTGPw_pEe08P3Tt-aGXd4Bb6RAMSk9bpNHCkukm4eEzcnVyPJueRUMehsgxWCyjJGEuj21sfUC2Ihd7B-MbFzwuMoBvNs2YN7mTTPLAnVSJgWUCYGPhg8iNlew52anqyr8g1Avj89zDJicJXFqrFPeAiaRQ1olE2QnZXw-9dgNJOebKuNW4WUFZ6WqpB1lpkNWEvN80uOv5Of5e9QPKclMNibW7AlA3Paib_pe6Tchb0AR948quPd6va33TaNh-fII38wRPxUzIm7WmaJiu6IMxla9b6I9KkYISkNmEyJEKjfo1flKVi474G72YAGDZy__xJa_IwxQmRR9P95rsrJrW75IH7seqXDZ75L6Yy71uUsH1y6_jPwydJHU |
| 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=Use+of+ChatGPT+for+Determining+Clinical+and+Surgical+Treatment+of+Lumbar+Disc+Herniation+With+Radiculopathy%3A+A+North+American+Spine+Society+Guideline+Comparison&rft.jtitle=Neurospine&rft.au=Mejia%2C+Mateo+Restrepo&rft.au=Arroyave%2C+Juan+Sebastian&rft.au=Saturno%2C+Michael&rft.au=Ndjonko%2C+Laura+Chelsea+Mazudie&rft.date=2024-03-01&rft.issn=2586-6583&rft.eissn=2586-6591&rft.volume=21&rft.issue=1&rft.spage=149&rft.epage=158&rft_id=info:doi/10.14245%2Fns.2347052.526&rft.externalDBID=n%2Fa&rft.externalDocID=10_14245_ns_2347052_526 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2586-6583&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2586-6583&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2586-6583&client=summon |