OpenLB
Open Library of Bioscience
Advanced Search
Neurology
Nov 27, 2023;101 (22): 1010-1018.

Improving Neurology Clinical Care With Natural Language Processing Tools.

Wendong Ge, Hunter J Rice, Irfan S Sheikh, M Brandon Westover, Allison L Weathers, Lyell K Jones, Lidia Moura
Author Information
  1. Wendong Ge: From the Department of Neurology (W.G., H.J.R., I.S.S., L.M.), Massachusetts General Hospital, Boston; Department of Neurology (M.B.W.), Beth Israel Deaconess Medical Center, Boston, MA; Information Technology Division (A.L.W.), Cleveland Clinic, OH; Department of Neurology (L.K.J.), Mayo Clinic, Rochester, MN; and Department of Neurology (L.M.), Harvard Medical School, Boston, MA.
  2. Hunter J Rice: From the Department of Neurology (W.G., H.J.R., I.S.S., L.M.), Massachusetts General Hospital, Boston; Department of Neurology (M.B.W.), Beth Israel Deaconess Medical Center, Boston, MA; Information Technology Division (A.L.W.), Cleveland Clinic, OH; Department of Neurology (L.K.J.), Mayo Clinic, Rochester, MN; and Department of Neurology (L.M.), Harvard Medical School, Boston, MA. ORCID
  3. Irfan S Sheikh: From the Department of Neurology (W.G., H.J.R., I.S.S., L.M.), Massachusetts General Hospital, Boston; Department of Neurology (M.B.W.), Beth Israel Deaconess Medical Center, Boston, MA; Information Technology Division (A.L.W.), Cleveland Clinic, OH; Department of Neurology (L.K.J.), Mayo Clinic, Rochester, MN; and Department of Neurology (L.M.), Harvard Medical School, Boston, MA.
  4. M Brandon Westover: From the Department of Neurology (W.G., H.J.R., I.S.S., L.M.), Massachusetts General Hospital, Boston; Department of Neurology (M.B.W.), Beth Israel Deaconess Medical Center, Boston, MA; Information Technology Division (A.L.W.), Cleveland Clinic, OH; Department of Neurology (L.K.J.), Mayo Clinic, Rochester, MN; and Department of Neurology (L.M.), Harvard Medical School, Boston, MA. ORCID
  5. Allison L Weathers: From the Department of Neurology (W.G., H.J.R., I.S.S., L.M.), Massachusetts General Hospital, Boston; Department of Neurology (M.B.W.), Beth Israel Deaconess Medical Center, Boston, MA; Information Technology Division (A.L.W.), Cleveland Clinic, OH; Department of Neurology (L.K.J.), Mayo Clinic, Rochester, MN; and Department of Neurology (L.M.), Harvard Medical School, Boston, MA.
  6. Lyell K Jones: From the Department of Neurology (W.G., H.J.R., I.S.S., L.M.), Massachusetts General Hospital, Boston; Department of Neurology (M.B.W.), Beth Israel Deaconess Medical Center, Boston, MA; Information Technology Division (A.L.W.), Cleveland Clinic, OH; Department of Neurology (L.K.J.), Mayo Clinic, Rochester, MN; and Department of Neurology (L.M.), Harvard Medical School, Boston, MA. ORCID
  7. Lidia Moura: From the Department of Neurology (W.G., H.J.R., I.S.S., L.M.), Massachusetts General Hospital, Boston; Department of Neurology (M.B.W.), Beth Israel Deaconess Medical Center, Boston, MA; Information Technology Division (A.L.W.), Cleveland Clinic, OH; Department of Neurology (L.K.J.), Mayo Clinic, Rochester, MN; and Department of Neurology (L.M.), Harvard Medical School, Boston, MA. lidia.moura@mgh.harvard.edu. ORCID
PMID: 37816638 DOI: 10.1212/WNL.0000000000207853

Abstract

The integration of natural language processing (NLP) tools into neurology workflows has the potential to significantly enhance clinical care. However, it is important to address the limitations and risks associated with integrating this new technology. Recent advances in transformer-based NLP algorithms (e.g., GPT, BERT) could augment neurology clinical care by summarizing patient health information, suggesting care options, and assisting research involving large datasets. However, these NLP platforms have potential risks including fabricated facts and data security and substantial barriers for implementation. Although these risks and barriers need to be considered, the benefits for providers, patients, and communities are substantial. With these systems achieving greater functionality and the pace of medical need increasing, integrating these tools into clinical care may prove not only beneficial but necessary. Further investigation is needed to design implementation strategies, mitigate risks, and overcome barriers.

References

  1. J Am Med Inform Assoc. 2022 Apr 13;29(5):873-881 [PMID: 35190834]
  2. J Am Med Inform Assoc. 2011 Dec;18 Suppl 1:i150-6 [PMID: 21946240]
  3. JMIR Cancer. 2021 Nov 29;7(4):e27850 [PMID: 34847056]
  4. Am J Med. 2020 Feb;133(2):160-164 [PMID: 31520624]
  5. BMC Med Inform Decis Mak. 2023 Jan 10;23(1):5 [PMID: 36627624]
  6. J Neuroophthalmol. 2022 Mar 1;42(1):62-67 [PMID: 33770009]
  7. N Engl J Med. 2023 May 25;388(21):1981-1990 [PMID: 37224199]
  8. JAMA Intern Med. 2018 Nov 1;178(11):1544-1547 [PMID: 30128552]
  9. Addiction. 2022 Apr;117(4):925-933 [PMID: 34729829]
  10. Neurol Clin Pract. 2016 Oct;6(5):379-380 [PMID: 29443277]
  11. Patterns (N Y). 2021 Oct 08;2(10):100347 [PMID: 34693373]
  12. NPJ Digit Med. 2022 Dec 3;5(1):177 [PMID: 36463327]
  13. Front Digit Health. 2022 Dec 08;4:1065581 [PMID: 36569804]
  14. BMC Med Inform Decis Mak. 2022 Dec 22;22(1):338 [PMID: 36550485]
  15. JAMA. 2019 Nov 12;322(18):1765-1766 [PMID: 31584609]

MeSH Term

Humans
Natural Language Processing
Algorithms
Journal Article
Article has an altmetric score of 28

Word Cloud

Created with Highcharts 10.0.0carerisksNLPclinicalbarrierstoolsneurologypotentialHoweverintegratingsubstantialimplementationneedintegrationnaturallanguageprocessingworkflowssignificantlyenhanceimportantaddresslimitationsassociatednewtechnologyRecentadvancestransformer-basedalgorithmsegGPTBERTaugmentsummarizingpatienthealthinformationsuggestingoptionsassistingresearchinvolvinglargedatasetsplatformsincludingfabricatedfactsdatasecurityAlthoughconsideredbenefitsproviderspatientscommunitiessystemsachievinggreaterfunctionalitypacemedicalincreasingmayprovebeneficialnecessaryinvestigationneededdesignstrategiesmitigateovercomeImprovingNeurologyClinicalCareNaturalLanguageProcessingTools

Similar Articles

Cited By