Use of artificial intelligence large language models as a clinical tool in rehabilitation medicine: a comparative test case
Objective: To explore the potential use of artificial intelligence language models in formulating rehabilitation prescriptions and International Classification of Functioning, Disability and Health (ICF) codes. Design: Comparative study based on a single case report compared to standard answers fro...
Saved in:
| Published in | Journal of rehabilitation medicine Vol. 55; p. jrm13373 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Medical Journals Sweden AB
11.09.2023
Medical Journals Sweden |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1651-2081 1650-1977 1651-2081 |
| DOI | 10.2340/jrm.v55.13373 |
Cover
| Abstract | Objective: To explore the potential use of artificial intelligence language models in formulating rehabilitation prescriptions and International Classification of Functioning, Disability and Health (ICF) codes.
Design: Comparative study based on a single case report compared to standard answers from a textbook.
Subjects: A stroke case from textbook.
Methods: Chat Generative Pre-Trained Transformer-4 (ChatGPT-4)was used to generate comprehensive medical and rehabilitation prescription information and ICF codes pertaining to the stroke case. This information was compared with standard answers from textbook, and 2 licensed Physical Medicine and Rehabilitation (PMR) clinicians reviewed the artificial intelligence recommendations for further discussion.
Results: ChatGPT-4 effectively formulated rehabilitation prescriptions and ICF codes for a typical stroke case, together with a rationale to support its recommendations. This information was generated in seconds. Compared with standard answers, the large language model generated broader and more general prescriptions in terms of medical problems and management plans, rehabilitation problems and management plans, as well as rehabilitation goals. It also demonstrated the ability to propose specified approaches for each rehabilitation therapy. The language model made an error regarding the ICF category for the stroke case, but no mistakes were identified in the ICF codes assigned.
Conclusion: This test case suggests that artificial intelligence language models have potential use in facilitating clinical practice and education in the field of rehabilitation medicine. |
|---|---|
| AbstractList | To explore the potential use of artificial intelligence language models in formulating rehabilitation prescriptions and International Classification of Functioning, Disability and Health (ICF) codes. Design: Comparative study based on a single case report compared to standard answers from a textbook.OBJECTIVETo explore the potential use of artificial intelligence language models in formulating rehabilitation prescriptions and International Classification of Functioning, Disability and Health (ICF) codes. Design: Comparative study based on a single case report compared to standard answers from a textbook.A stroke case from textbook. Methods: Chat Generative Pre-Trained Transformer-4 (ChatGPT-4)was used to generate comprehensive medical and rehabilitation prescription information and ICF codes pertaining to the stroke case. This information was compared with standard answers from textbook, and 2 licensed Physical Medicine and Rehabilitation (PMR) clinicians reviewed the artificial intelligence recommendations for further discussion.SUBJECTSA stroke case from textbook. Methods: Chat Generative Pre-Trained Transformer-4 (ChatGPT-4)was used to generate comprehensive medical and rehabilitation prescription information and ICF codes pertaining to the stroke case. This information was compared with standard answers from textbook, and 2 licensed Physical Medicine and Rehabilitation (PMR) clinicians reviewed the artificial intelligence recommendations for further discussion.ChatGPT-4 effectively formulated rehabilitation prescriptions and ICF codes for a typical stroke case, together with a rationale to support its recommendations. This information was generated in seconds. Compared with standard answers, the large language model generated broader and more general prescriptions in terms of medical problems and management plans, rehabilitation problems and management plans, as well as rehabilitation goals. It also demonstrated the ability to propose specified approaches for each rehabilitation therapy. The language model made an error regarding the ICF category for the stroke case, but no mistakes were identified in the ICF codes assigned. Conclusion: This test case suggests that artificial intelligence language models have potential use in facilitating clinical practice and education in the field of rehabilitation medicine.RESULTSChatGPT-4 effectively formulated rehabilitation prescriptions and ICF codes for a typical stroke case, together with a rationale to support its recommendations. This information was generated in seconds. Compared with standard answers, the large language model generated broader and more general prescriptions in terms of medical problems and management plans, rehabilitation problems and management plans, as well as rehabilitation goals. It also demonstrated the ability to propose specified approaches for each rehabilitation therapy. The language model made an error regarding the ICF category for the stroke case, but no mistakes were identified in the ICF codes assigned. Conclusion: This test case suggests that artificial intelligence language models have potential use in facilitating clinical practice and education in the field of rehabilitation medicine. Objective: To explore the potential use of artificial intelligence language models in formulating rehabilitation prescriptions and International Classification of Functioning, Disability and Health (ICF) codes. Design: Comparative study based on a single case report compared to standard answers from a textbook. Subjects: A stroke case from textbook. Methods: Chat Generative Pre-Trained Transformer-4 (ChatGPT-4)was used to generate comprehensive medical and rehabilitation prescription information and ICF codes pertaining to the stroke case. This information was compared with standard answers from textbook, and 2 licensed Physical Medicine and Rehabilitation (PMR) clinicians reviewed the artificial intelligence recommendations for further discussion. Results: ChatGPT-4 effectively formulated rehabilitation prescriptions and ICF codes for a typical stroke case, together with a rationale to support its recommendations. This information was generated in seconds. Compared with standard answers, the large language model generated broader and more general prescriptions in terms of medical problems and management plans, rehabilitation problems and management plans, as well as rehabilitation goals. It also demonstrated the ability to propose specified approaches for each rehabilitation therapy. The language model made an error regarding the ICF category for the stroke case, but no mistakes were identified in the ICF codes assigned. Conclusion: This test case suggests that artificial intelligence language models have potential use in facilitating clinical practice and education in the field of rehabilitation medicine. Objective: To explore the potential use of artificial intelligence language models in formulating rehabilitation prescriptions and International Classification of Functioning, Disability and Health (ICF) codes. Design: Comparative study based on a single case report compared to standard answers from a textbook. Subjects: A stroke case from textbook. Methods: Chat Generative Pre-Trained Transformer-4 (ChatGPT-4)was used to generate comprehensive medical and rehabilitation prescription information and ICF codes pertaining to the stroke case. This information was compared with standard answers from textbook, and 2 licensed Physical Medicine and Rehabilitation (PMR) clinicians reviewed the artificial intelligence recommendations for further discussion. Results: ChatGPT-4 effectively formulated rehabilitation prescriptions and ICF codes for a typical stroke case, together with a rationale to support its recommendations. This information was generated in seconds. Compared with standard answers, the large language model generated broader and more general prescriptions in terms of medical problems and management plans, rehabilitation problems and management plans, as well as rehabilitation goals. It also demonstrated the ability to propose specified approaches for each rehabilitation therapy. The language model made an error regarding the ICF category for the stroke case, but no mistakes were identified in the ICF codes assigned. Conclusion: This test case suggests that artificial intelligence language models have potential use in facilitating clinical practice and education in the field of rehabilitation medicine. |
| Author | Mukaino, Masahiko Yamada, Shin Tashiro, Syoichi Zhang, Liang |
| Author_xml | – sequence: 1 givenname: Liang surname: Zhang fullname: Zhang, Liang – sequence: 2 givenname: Syoichi surname: Tashiro fullname: Tashiro, Syoichi – sequence: 3 givenname: Masahiko surname: Mukaino fullname: Mukaino, Masahiko – sequence: 4 givenname: Shin surname: Yamada fullname: Yamada, Shin |
| BookMark | eNqFkcuLFDEQxhtZcR969N5HLz3m0Ul6vIgsPhYWvLjnUElX92ZIJ2PSPbL4z5veGcQVRAhJUanvR1V9l9VZiAGr6jUlG8Zb8naXps1BiA3lXPFn1QWVgjaMdPTsj_i8usx5RwhVgqsX1TlXckvbrbqoft5lrONQQ5rd4KwDX7swo_duxGCx9pDG9Q7jAiWYYo8-11BObb0LzhbBHOOqqhPeg3HezTC7GOoJ-wIM-G6tjdMeUskfsJ4xz7WFjC-r5wP4jK9O71V19-njt-svze3XzzfXH24by1vJGyrRmqHru14wKQfKLAwdtYLZMhlQ0rZdL2UvLBihbGs4yM50SnUECRHI-VV1c-T2EXZ6n9wE6UFHcPoxEdOo1_GtR82YYRwFI0Rhy_qtYWZoWwRU0BqphsLaHFlL2MPDD_D-N5ASvTqiiyO6OKIfHSmC90fBfjFlIxbDnMA_6eLpT3D3eoyHghOE8k4UwpsTIcXvS1menly2xSIIGJesWSeLn5IwVUqbY6lNMeeEw3-b43_V25N7pRXn_6H6Bdk_xpw |
| CitedBy_id | crossref_primary_10_1097_PHM_0000000000002440 crossref_primary_10_1177_15459683241309587 crossref_primary_10_2196_63494 crossref_primary_10_1038_s41598_024_58514_9 crossref_primary_10_1001_jama_2024_21700 crossref_primary_10_35460_2546_1621_2023_0084 crossref_primary_10_5772_acrt_20240045 crossref_primary_10_5498_wjp_v14_i2_330 crossref_primary_10_1007_s41666_024_00171_8 crossref_primary_10_1038_s41598_024_71020_2 crossref_primary_10_7759_cureus_67347 crossref_primary_10_3390_life13102061 crossref_primary_10_1016_j_apmr_2024_08_014 crossref_primary_10_1017_gmh_2024_114 crossref_primary_10_3389_fmed_2023_1336175 |
| Cites_doi | 10.1056/NEJMsr2214184 10.1016/j.eururo.2023.03.037 10.1053/apmr.2000.6275 10.1186/s12913-020-4911-6 10.1038/s41586-023-05881-4 10.1186/s12874-021-01302-0 10.1016/S2589-7500(23)00021-3 10.1016/j.ajog.2023.03.009 |
| ContentType | Journal Article |
| Copyright | Published by Medical Journals Sweden, on behalf of the Foundation for Rehabilitation Information 2023 |
| Copyright_xml | – notice: Published by Medical Journals Sweden, on behalf of the Foundation for Rehabilitation Information 2023 |
| DBID | AAYXX CITATION 7X8 5PM ADTOC UNPAY DOA |
| DOI | 10.2340/jrm.v55.13373 |
| DatabaseName | CrossRef MEDLINE - Academic PubMed Central (Full Participant titles) Unpaywall for CDI: Periodical Content Unpaywall DOAJ Directory of Open Access Journals |
| 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: UNPAY name: Unpaywall url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/ sourceTypes: Open Access Repository |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Physical Therapy |
| EISSN | 1651-2081 |
| ExternalDocumentID | oai_doaj_org_article_22b23e52007e42d9b2bf44eae7a4b67f 10.2340/jrm.v55.13373 PMC10501385 10_2340_jrm_v55_13373 |
| GroupedDBID | --- 29L 2WC 36B 5GY 6NX 6PF AAFWJ AAWTL AAYXX ABNNA ACCJX ACGEJ ACGFO ADBBV ADXPE AENEX AFPKN ALMA_UNASSIGNED_HOLDINGS BAWUL BCNDV CITATION COF CS3 DIK DU5 EBD EBS EJD EMOBN F5P FIJ GROUPED_DOAJ H13 IPNFZ MSJ RPM SJN SV3 WH7 7X8 5PM .GJ 1CY 1KJ 53G 5VS ADTOC AJWEG CAG FEDTE HVGLF N4W OHT OVD RIG TEORI UNPAY ZGI ZXP |
| ID | FETCH-LOGICAL-c3463-16ecbf8d8d5266f12caf81c52c081a10448d66d5cab57c4b3a68b87780e005e33 |
| IEDL.DBID | DOA |
| ISSN | 1651-2081 1650-1977 |
| IngestDate | Fri Oct 03 12:44:59 EDT 2025 Sun Oct 26 04:06:31 EDT 2025 Thu Aug 21 18:36:45 EDT 2025 Thu Oct 02 12:06:14 EDT 2025 Tue Jul 01 03:39:03 EDT 2025 Thu Apr 24 23:05:27 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://creativecommons.org/licenses/by-nc/4.0 This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (https://creativecommons.org/licenses/by-nc/4.0/) cc-by-nc |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3463-16ecbf8d8d5266f12caf81c52c081a10448d66d5cab57c4b3a68b87780e005e33 |
| Notes | ObjectType-Case Study-2 SourceType-Scholarly Journals-1 ObjectType-Feature-4 content type line 23 ObjectType-Report-1 ObjectType-Article-3 These authors contributed equally to this paper. |
| OpenAccessLink | https://doaj.org/article/22b23e52007e42d9b2bf44eae7a4b67f |
| PMID | 37691497 |
| PQID | 2863766027 |
| PQPubID | 23479 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_22b23e52007e42d9b2bf44eae7a4b67f unpaywall_primary_10_2340_jrm_v55_13373 pubmedcentral_primary_oai_pubmedcentral_nih_gov_10501385 proquest_miscellaneous_2863766027 crossref_primary_10_2340_jrm_v55_13373 crossref_citationtrail_10_2340_jrm_v55_13373 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 20230911 |
| PublicationDateYYYYMMDD | 2023-09-11 |
| PublicationDate_xml | – month: 9 year: 2023 text: 20230911 day: 11 |
| PublicationDecade | 2020 |
| PublicationTitle | Journal of rehabilitation medicine |
| PublicationYear | 2023 |
| Publisher | Medical Journals Sweden AB Medical Journals Sweden |
| Publisher_xml | – name: Medical Journals Sweden AB – name: Medical Journals Sweden |
| References | 37947 37948 37949 37940 37941 37942 37943 37944 37945 37946 |
| References_xml | – ident: 37940 – ident: 37941 doi: 10.1056/NEJMsr2214184 – ident: 37944 doi: 10.1016/j.eururo.2023.03.037 – ident: 37947 doi: 10.1053/apmr.2000.6275 – ident: 37948 doi: 10.1186/s12913-020-4911-6 – ident: 37946 – ident: 37942 doi: 10.1038/s41586-023-05881-4 – ident: 37949 doi: 10.1186/s12874-021-01302-0 – ident: 37943 doi: 10.1016/S2589-7500(23)00021-3 – ident: 37945 doi: 10.1016/j.ajog.2023.03.009 |
| SSID | ssj0017537 |
| Score | 2.4967146 |
| Snippet | Objective: To explore the potential use of artificial intelligence language models in formulating rehabilitation prescriptions and International Classification... To explore the potential use of artificial intelligence language models in formulating rehabilitation prescriptions and International Classification of... |
| SourceID | doaj unpaywall pubmedcentral proquest crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Enrichment Source Index Database |
| StartPage | jrm13373 |
| SubjectTerms | Artificial Intelligence International Classification of Functioning, Disability, and Health (ICF) codes Large Language Models Rehabilitation Prescriptions Short Communication |
| SummonAdditionalLinks | – databaseName: Unpaywall dbid: UNPAY link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELbQ9gAXylMsLxkJwYXdTWzHcbgVRFUhUfXQleAU-TGhhW1SbbJUwJ9nJo-lqQRCQsohSiaOH5_jb-LxZ8aei1ZDXQZ0crSaqQId1gwiix2P2KtV3rWyix8O9cFSvf-YDNGEtBbmrJue6Cuyri8Aux8FvX9Zny36ylwE0pGvbFigg5XKBY5CGXrtOzpBOj5hO8vDo71P5Ggh-5jFWbv7Ip7HiAgTdzqbQqqIkpx_S5J5m8poXGrl-0ec82rE5PVNeW6_X9jV6tJwtL_L3FCQLgrl63zTuLn_cUXj8b9Keovd7Mkq3-vMbrNrUN5hu0d90_LjTpHgLvu5rIFXBaf0OkUKfnpJ6pOvKNycD79Gebv7Ts0tHnxYmcmbqqKn-HokHc6Huf_XZPtbqZwjQ264xyH4Hlvuvzt-ezDrd3WYeam0nMUavCtMMAHhoYtYeFuY2CfCY-tY9A6VCVqHxFuXpF45abVxJk1NBPjFACnvs0lZlfCAcR85LWMAR6hyELnUggHkUAEyDyGdsldDm-a-zzftvLHK0fUhCORY1zlCIG-rd8pebM3PO62PPxm-IYBsjUiiu71QrT_nfdPlQjghgVStUlAiZE64QimwkGJedVpM2bMBXjl2aZqnsSVUmzoXRuNnX0cCC2BGuBu9cXynPD1pxcGRL9PkczJlL7cQ_XtpHv6z5SN2QyDHo3CZOH7MJs16A0-QkzXuad_rfgHKLjuV priority: 102 providerName: Unpaywall |
| Title | Use of artificial intelligence large language models as a clinical tool in rehabilitation medicine: a comparative test case |
| URI | https://www.proquest.com/docview/2863766027 https://pubmed.ncbi.nlm.nih.gov/PMC10501385 https://medicaljournalssweden.se/jrm/article/download/13373/22490 https://doaj.org/article/22b23e52007e42d9b2bf44eae7a4b67f |
| UnpaywallVersion | publishedVersion |
| Volume | 55 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1651-2081 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017537 issn: 1651-2081 databaseCode: DOA dateStart: 20170101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVBFR databaseName: Free Medical Journals customDbUrl: eissn: 1651-2081 dateEnd: 20250503 omitProxy: true ssIdentifier: ssj0017537 issn: 1651-2081 databaseCode: DIK dateStart: 20010101 isFulltext: true titleUrlDefault: http://www.freemedicaljournals.com providerName: Flying Publisher – providerCode: PRVAQN databaseName: PubMed Central customDbUrl: eissn: 1651-2081 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017537 issn: 1651-2081 databaseCode: RPM dateStart: 20210101 isFulltext: true titleUrlDefault: https://www.ncbi.nlm.nih.gov/pmc/ providerName: National Library of Medicine |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwEB6hcoALb0R4rIyE4MK2ie3YXm4FUVVIVD10pXKybGciWi1JtQ8Q4s8zdpJlgwRckHJKJortmbG_sSffALzgiUNdVBTkKDmVNQWsM8wdOV5Er04Gn2gXP56o47n8cF6e75T6ijlhHT1wN3AHnHsuMJIDaZS8mnnuaynRoXbSK13H2Tc3syGY6s8PCITrjlGTC5kfXC6_7H8ty30KyLQYrUCJqH-ELn_Pjbyxaa7c929usdhZeI7uwK0eMbLDrqV34Ro29-D2aT--7KyjBbgPP-YrZG3NYpc6Wgh2scO3yRYx55sN-5MslcBZMUcXG36PZOu2jW-x5Yi_mw0H8G-i7C-6cEYwdc0CrYMPYH70_uzd8bQvrTANQioxLRQGX5vKVKQjVRc8uNoUoeSBIIKjEE2aSqmqDM6XOkgvnDLeaG1yJLdFIR7CXtM2-AhYyL0SBaKPqvWYe-3QIAGZCmcBK53B62G4bejbHctfLCzFH1E7lrRjSTs2aSeDl1vxq45w40-Cb6PutkKRJzvdIOuxvfXYf1lPBs8HzVvyq3hY4hpsNyvLjaK5V1HUnoEZmcToi-MnzcXnxNBNoDWeAJcZvNpaz9978_h_9OYJ3OSEwWI6S1E8hb31coPPCDOt_SS5xyRtZk3g-vzk9PDTTws2HGo |
| linkProvider | Directory of Open Access Journals |
| linkToUnpaywall | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELbQ9gAXylMsLxkJwYXdTWzHcbgVRFUhUfXQleAU-TGhhW1SbbJUwJ9nJo-lqQRCQsohSiaOH5_jb-LxZ8aei1ZDXQZ0crSaqQId1gwiix2P2KtV3rWyix8O9cFSvf-YDNGEtBbmrJue6Cuyri8Aux8FvX9Zny36ylwE0pGvbFigg5XKBY5CGXrtOzpBOj5hO8vDo71P5Ggh-5jFWbv7Ip7HiAgTdzqbQqqIkpx_S5J5m8poXGrl-0ec82rE5PVNeW6_X9jV6tJwtL_L3FCQLgrl63zTuLn_cUXj8b9Keovd7Mkq3-vMbrNrUN5hu0d90_LjTpHgLvu5rIFXBaf0OkUKfnpJ6pOvKNycD79Gebv7Ts0tHnxYmcmbqqKn-HokHc6Huf_XZPtbqZwjQ264xyH4Hlvuvzt-ezDrd3WYeam0nMUavCtMMAHhoYtYeFuY2CfCY-tY9A6VCVqHxFuXpF45abVxJk1NBPjFACnvs0lZlfCAcR85LWMAR6hyELnUggHkUAEyDyGdsldDm-a-zzftvLHK0fUhCORY1zlCIG-rd8pebM3PO62PPxm-IYBsjUiiu71QrT_nfdPlQjghgVStUlAiZE64QimwkGJedVpM2bMBXjl2aZqnsSVUmzoXRuNnX0cCC2BGuBu9cXynPD1pxcGRL9PkczJlL7cQ_XtpHv6z5SN2QyDHo3CZOH7MJs16A0-QkzXuad_rfgHKLjuV |
| 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+artificial+intelligence+large+language+models+as+a+clinical+tool+in+rehabilitation+medicine%3A+a+comparative+test+case&rft.jtitle=Journal+of+rehabilitation+medicine&rft.au=Zhang%2C+Liang&rft.au=Tashiro%2C+Syoichi&rft.au=Mukaino%2C+Masahiko&rft.au=Yamada%2C+Shin&rft.date=2023-09-11&rft.issn=1651-2081&rft.eissn=1651-2081&rft.volume=55&rft.spage=jrm13373&rft_id=info:doi/10.2340%2Fjrm.v55.13373&rft.externalDBID=n%2Fa&rft.externalDocID=10_2340_jrm_v55_13373 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1651-2081&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1651-2081&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1651-2081&client=summon |