nach oben

Current Reviews in Musculoskeletal Medicine

Erschienen in:

10.11.2021 | The Use of Technology in Orthopaedic Surgery—Intraoperative and Post Operative Management (C Krueger and S Bini, Section Editors)

Natural Language Processing and Its Use in Orthopaedic Research

verfasst von: John M. Wyatt, Gregory J. Booth, Ashton H. Goldman

Erschienen in: Current Reviews in Musculoskeletal Medicine | Ausgabe 6/2021

Einloggen, um Zugang zu erhalten

Abstract

Purpose of Review

This review aims to demonstrate how natural language processing is used in orthopaedic research.

Recent Findings

Natural language processing is a form of artificial intelligence that involves encoding human-generated text or speech into a form which can be interpreted by computers to perform a variety of tasks. Natural language processing gathers, processes, and organizes large amounts of free-text data more efficiently than humans. In orthopaedics, it has been utilized for retrospective chart review, automated reporting of electronic health record data, analyzing operative notes and radiology reports, and patient reviews of physicians and practices.

Summary

Although still in its infancy, natural language processing promises to be a valuable tool in the future of orthopaedic research. It will not eliminate the need for the essential human component of questioning involved in research, but natural language processing can improve the quality, efficiency, and thoroughness of research, thus improving patient care.

Nadkarni PM, Ohno-Machado L, Chapman WW. Natural language processing: an introduction. J Am Med Inform Assoc. 2011;18(5):544–51.CrossRef

Blei DM, Ng AY, Jordan MI. Latent dirichlet allocation. J Mach Learn Res. 2003;3:993–1022.

Thirukumaran CP, Zaman A, Rubery PT, Calabria C, Li Y, Ricciardi BF, Bakhsh WR, Kautz H. Natural language processing for the identification of surgical site infections in orthopaedics. J Bone Joint Surg Am. 2019;101(24):2167–74.CrossRef

Karhade AV, Bongers MER, Groot OQ, Cha TD, Doorly TP, Fogel HA, Hershman SH, Tobert DG, Schoenfeld AJ, Kang JD, Harris MB, Bono CM, Schwab JH. Can natural language processing provide accurate, automated reporting of wound infection requiring reoperation after lumbar discectomy? Spine J. 2020;20(10):1602–9.CrossRef

Shah RF, Bini S, Vail T. Data for registry and quality review can be retrospectively collected using natural language processing from unstructured charts of arthroplasty patients. Bone Joint J. 2020;102-B(7_Supple_B):99–104.CrossRef

6.•

Borjali A, Magnéli M, Shin D, Malchau H, Muratoglu OK, Varadarajan KM. Natural language processing with deep learning for medical adverse event detection from free-text medical narratives: a case study of detecting total hip replacement dislocation. Comput Biol Med. 2021;129:104140. Most retrospective reviews, and thus most research in the field of orthopaedic surgery, heavily rely on chart mining with ICD and CPT code searches to supply their data set. Borjali et al specifically compared to NLP algorithms to manual chart review searching via ICD and CPT codes. They found NLP searches of free-text notes were far more accurate in identifying the desired condition than manual search of ICD and CPT codes. This will allow researches to have larger and more thorough data sets/populations in their future research endeavors and therefore strengthening their studiesCrossRef

Sagheb E, Ramazanian T, Tafti AP, Fu S, Kremers WK, Berry DJ, Lewallen DG, Sohn S, Maradit Kremers H. Use of natural language processing algorithms to identify common data elements in operative notes for knee arthroplasty. J Arthroplast. 2021;36(3):922–6.CrossRef

Karhade AV, Bongers MER, Groot OQ, Kazarian ER, Cha TD, Fogel HA, Hershman SH, Tobert DG, Schoenfeld AJ, Bono CM, Kang JD, Harris MB, Schwab JH. Natural language processing for automated detection of incidental durotomy. Spine J. 2020;20(5):695–700.CrossRef

Fu S, Wyles CC, Osmon DR, Carvour ML, Sagheb E, Ramazanian T, Kremers WK, Lewallen DG, Berry DJ, Sohn S, Kremers HM. Automated detection of periprosthetic joint infections and data elements using natural language processing. J Arthroplast. 2021;36(2):688–92.CrossRef

10.•

Wyles CC, Tibbo ME, Fu S, Wang Y, Sohn S, Kremers WK, et al. Use of natural language processing algorithms to identify common data elements in operative notes for total hip arthroplasty. J Bone Joint Surg Am. 2019;101(21):1931–8. Wyles et al. demonstrated NLP was accurate in detecting multiple desired variables from operative reports. They also took the next step and externally validated their algorithms by testing on a separate set of operative notes from physicians at outside facilities with similar accurate results. This displays the ability of well-designed NLP algorithms to accurately detect and categorize information from many differing sources allowing efficient gathering of extremely large data sets. The research could then be more generalizable to a larger population groupCrossRef

11.•

Tibbo ME, Wyles CC, Fu S, Sohn S, Lewallen DG, Berry DJ, et al. Use of natural language processing tools to identify and classify periprosthetic femur fractures. J Arthroplast. 2019;34(10):2216–9. This reference is important in two aspects. First, Tibbo et al. demonstrated extremely high accuracy in their initial algorithms searching/identifying periprosthetic fractures out of free-text radiology reports. It shows NLP has the ability to extract information from free text accurately, thoroughly, and efficiently. Second, it also demonstrates the ability of NLP to perform more complex data categorization accurately. It took the second step from simply identifying the fracture to classifying it according the Vancouver classification and did so with great accuracyCrossRef

12.

Tan WK, Hassanpour S, Heagerty PJ, Rundell SD, Suri P, Huhdanpaa HT, James K, Carrell DS, Langlotz CP, Organ NL, Meier EN, Sherman KJ, Kallmes DF, Luetmer PH, Griffith B, Nerenz DR, Jarvik JG. Comparison of natural language processing rules-based and machine-learning systems to identify lumbar spine imaging findings related to low back pain. Acad Radiol. 2018;25(11):1422–32.CrossRef

13.

Wang Y, Meehrabi S, Sohn S, Atkinson A, Amin S, Liu H. Automatic extraction of major osteoporotic fractures from radiology reports using natural language processing. International Conference on Healthcare Informatics Workshop (ICHI-W): IEEE; 2018. p. 64-5.

14.

Jungmann F, Kämpgen B, Hahn F, Wagner D, Mildenberger P, Düber C, Kloeckner R. Natural language processing of radiology reports to investigate the effects of the COVID-19 pandemic on the incidence and age distribution of fractures. Skelet Radiol. 2021;

15.

Patawut Bovonratwet MTSS, MD; Wasif Islam, BS; Michael P. Ast, MD. Natural language processing of patient-experience comments after primary total knee arthroplasty. J Arthroplast 2020;26(3):927-934.

16.•

Langerhuizen D, Brown L, Doornberg J, Ring D, Kerkhoffs G, Janssen S. Analysis of online reviews of orthopaedic surgeons and orthopaedic practices using natural language processing. J Am Acad Orthop Surg. 2021;29(8):337–44. In today’s growing trend of patient centered medicine, patient satisfaction is an increasingly important factor in practices. This article demonstrated NLP’s ability to synthesize free-text information on websites the general public accesses to find information. Tapping into this resource can allow physicians to tailor and focus on ideals and conditions patients consider important to improve their practiceCrossRef

17.

Greaves F, Ramirez-Cano D, Millett C, Darzi A, Donaldson L. Use of sentiment analysis for capturing patient experience from free-text comments posted online. J Med Internet Res. 2013;15(11):e239.CrossRef

18.

Sriram RD, Reddy SSK. Artificial intelligence and digital tools: future of diabetes care. Clin Geriatr Med. 2020;36(3):513–25.CrossRef

19.

Kreimeyer K, Foster M, Pandey A, Arya N, Halford G, Jones SF, Forshee R, Walderhaug M, Botsis T. Natural language processing systems for capturing and standardizing unstructured clinical information: a systematic review. J Biomed Inform. 2017;73:14–29.CrossRef

20.

Sheikhalishahi S, Miotto R, Dudley JT, Lavelli A, Rinaldi F, Osmani V. Natural language processing of clinical notes on chronic diseases: systematic review. JMIR Med Inform. 2019;7(2):e12239.CrossRef

21.

Gwo-Chin Lee M. More data please! The evolution of orthopaedic research: commentary on an artile by Cody C. Wyles, MD, et al.: “Use of natural language processing algoritms to identify common data elements in operative notes for total hip arthroplasy”. J Bone Joint Surg. 2019;101(21):e118.CrossRef

22.

Cote M, Lubowitz J, Brand J, Rossi M. Artificial intelligence, machine learning, and medicine. A little background goes a long way towards understanding. Arthrosc - J Arthrosc Relat Surg. 2021;37(6):1699–702.CrossRef

Titel: Natural Language Processing and Its Use in Orthopaedic Research
verfasst von: John M. Wyatt
Gregory J. Booth
Ashton H. Goldman
Publikationsdatum: 10.11.2021
Verlag: Springer US
Erschienen in: Current Reviews in Musculoskeletal Medicine / Ausgabe 6/2021
Elektronische ISSN: 1935-9748
DOI: https://doi.org/10.1007/s12178-021-09734-3

Update Orthopädie und Unfallchirurgie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Die Highlights vom Kongress des American College of Cardiology 2024

Springer Medizin

Natural Language Processing and Its Use in Orthopaedic Research