Download PDF
CC BY 4.0 · J Neurol Surg B Skull Base
DOI: 10.1055/s-0044-1786738
Original Article

Concept Recognition and Characterization of Patients Undergoing Resection of Vestibular Schwannoma Using Natural Language Processing

Simon C. Williams 
1   Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
2   Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
,
Kawsar Noor
3   Department of Computer Science, Institute for Health Informatics, University College London, London, United Kingdom
4   Department of Biostatistics and Health Informatics, NIHR Biomedical Research Centre, University College London Hospitals NHS Foundation Trust, London, United Kingdom
,
Siddharth Sinha
1   Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
2   Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
,
Richard J.B. Dobson
3   Department of Computer Science, Institute for Health Informatics, University College London, London, United Kingdom
4   Department of Biostatistics and Health Informatics, NIHR Biomedical Research Centre, University College London Hospitals NHS Foundation Trust, London, United Kingdom
5   Department of Informatics, NIHR Biomedical Research Centre, South London and Maudsley NHS Foundation Trust and King's College London, London, United Kingdom
6   Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom
,
Thomas Searle
5   Department of Informatics, NIHR Biomedical Research Centre, South London and Maudsley NHS Foundation Trust and King's College London, London, United Kingdom
,
Jonathan P. Funnell
1   Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
2   Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
,
John G. Hanrahan
1   Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
2   Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
,
William R. Muirhead
1   Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
2   Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
,
Neil Kitchen
2   Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
,
Hala Kanona
2   Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
7   Ear Nose and Throat Department, The Royal National ENT and Eastman Dental Hospital, University College London Hospitals, London, United Kingdom
,
Sherif Khalil
2   Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
7   Ear Nose and Throat Department, The Royal National ENT and Eastman Dental Hospital, University College London Hospitals, London, United Kingdom
,
Shakeel R. Saeed
2   Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
7   Ear Nose and Throat Department, The Royal National ENT and Eastman Dental Hospital, University College London Hospitals, London, United Kingdom
8   University College London Ear Institute, London, United Kingdom
,
Hani J. Marcus‡   *
1   Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
2   Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
,
Patrick Grover‡   *
2   Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
› Author Affiliations Funding S.C.W., J.P.F., J.G.H., W.R.M., and H.J.M. are supported by the Wellcome (203145Z/16/Z) EPSRC (NS/A000050/1) Centre for Interventional and Surgical Sciences, University College London. S.C.W. was supported by the Margaret Spittle Research Fellowship Grant. H.J.M. is also funded by the NIHR Biomedical Research Centre at University College London. J.G.H. is funded by an NIHR Academic Clinical Fellowship. This research was funded in whole, or in part, by the Wellcome Trust [203145Z/16/Z].
› Further Information
Also available at
   Permissions and Reprints

Abstract

Background Natural language processing (NLP), a subset of artificial intelligence (AI), aims to decipher unstructured human language. This study showcases NLP's application in surgical health care, focusing on vestibular schwannoma (VS). By employing an NLP platform, we identify prevalent text concepts in VS patients' electronic health care records (EHRs), creating concept panels covering symptomatology, comorbidities, and management. Through a case study, we illustrate NLP's potential in predicting postoperative cerebrospinal fluid (CSF) leaks.

Methods An NLP model analyzed EHRs of surgically managed VS patients from 2008 to 2018 in a single center. The model underwent unsupervised (trained on one million documents from EHR) and supervised (300 documents annotated in duplicate) learning phases, extracting text concepts and generating concept panels related to symptoms, comorbidities, and management. Statistical analysis correlated concept occurrences with postoperative complications, notably CSF leaks.

Results Analysis included 292 patients' records, yielding 6,901 unique concepts and 360,929 occurrences. Concept panels highlighted key associations with postoperative CSF leaks, including “antibiotics,” “sepsis,” and “intensive care unit admission.” The NLP model demonstrated high accuracy (precision 0.92, recall 0.96, macro F1 0.93).

Conclusion Our NLP model effectively extracted concepts from VS patients' EHRs, facilitating personalized concept panels with diverse applications. NLP shows promise in surgical settings, aiding in early diagnosis, complication prediction, and patient care. Further validation of NLP's predictive capabilities is warranted.

Keywords

artificial intelligence - vestibular schwannoma - machine learning - Natural Language Processing - retrosigmoid - translabyrinthine

Data Availability

Due to GDPR (General Data Protection Regulation) restrictions, any patient-sensitive data are not available for dissemination. Raw concept occurrence data are available on reasonable request.


Code Availability

CogStack and related models are Open Source and available online.


Authors Contributions

S.C.W.: conceptualization, data curation, formal analysis, methodology, project administration, data analysis, writing—original draft preparation; K.N.: data curation, formal analysis, methodology, writing—reviewing and editing; S.S.: data curation, formal analysis, writing—reviewing and editing; R.J.B.D.: data curation, formal analysis, writing—reviewing and editing; J.P.F.: conceptualization, methodology, data curation, writing—reviewing and editing; J.G.H.: methodology, data curation, writing—reviewing and editing; W.R.M.: methodology, data curation, project administration, writing—reviewing and editing; N.K.: data curation, project administration, writing—reviewing and editing; H.K.: data curation, project administration, writing—reviewing and editing; S.K.: data curation, project administration, writing—reviewing and editing; S.R.S.: data curation, project administration, writing—reviewing and editing; H.J.M.: conceptualization, methodology, data curation, project administration, writing—reviewing and editing; P.G.: conceptualization, methodology, data curation, project administration, writing—reviewing and editing.


* Equal contribution and joint senior authorship.




Publication History

Received: 04 November 2023

Accepted: 31 March 2024

Article published online:
11 May 2024

© 2024. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/)

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 

  • References

  • 1 Locke S, Bashall A, Al-Adely S, Moore J, Wilson A, Kitchen GB. Natural language processing in medicine: a review. Trends in Anaesthesia and Critical Care 2021; 38: 4-9
    CrossrefPubMedGoogle Scholar
  • 2 Wang J, Deng H, Liu B. et al. Systematic evaluation of research progress on natural language processing in medicine over the past 20 years: bibliometric study on PubMed. J Med Internet Res 2020; 22 (01) e16816
    CrossrefPubMedGoogle Scholar
  • 3 Hashimoto DA, Rosman G, Rus D, Meireles OR. Artificial intelligence in surgery: promises and perils. Ann Surg 2018; 268 (01) 70-76
    CrossrefPubMedGoogle Scholar
  • 4 Nadkarni PM, Ohno-Machado L, Chapman WW. Natural language processing: an introduction. J Am Med Inform Assoc 2011; 18 (05) 544-551
    CrossrefPubMedGoogle Scholar
  • 5 Evans DGR, Moran A, King A, Saeed S, Gurusinghe N, Ramsden R. Incidence of vestibular schwannoma and neurofibromatosis 2 in the North West of England over a 10-year period: higher incidence than previously thought. Otol Neurotol 2005; 26 (01) 93-97
    CrossrefPubMedGoogle Scholar
  • 6 Teppo H, Heikkinen J, Laitakari K, Alho OP. Diagnostic delays in vestibular schwannoma. J Laryngol Otol 2009; 123 (03) 289-293
    CrossrefPubMedGoogle Scholar
  • 7 Mellia JA, Basta MN, Toyoda Y. et al. Natural language processing in surgery: a systematic review and meta-analysis. Ann Surg 2021; 273 (05) 900-908
    CrossrefPubMedGoogle Scholar
  • 8 Funnell JP, Noor K, Khan DZ. et al. Characterization of patients with idiopathic normal pressure hydrocephalus using natural language processing within an electronic healthcare record system. J Neurosurg 2022; 1-9
    CrossrefPubMedGoogle Scholar
  • 9 Hernandez-Boussard T, Bozkurt S, Ioannidis JPA, Shah NH. MINIMAR (MINimum Information for Medical AI Reporting): developing reporting standards for artificial intelligence in health care. J Am Med Inform Assoc 2020; 27 (12) 2011-2015
    CrossrefPubMedGoogle Scholar
  • 10 McCulloch P, Altman DG, Campbell WB. et al; Balliol Collaboration. No surgical innovation without evaluation: the IDEAL recommendations. Lancet 2009; 374 (9695) 1105-1112
    CrossrefPubMedGoogle Scholar
  • 11 Noor K, Roguski L, Handy A. et al. Deployment of a free-text analytics platform at a UK National Health Service Research Hospital: CogStack at University College London Hospitals. arXiv:210806835. August 15, 2021. Accessed May 8, 2022 at: http://arxiv.org/abs/2108.06835
    PubMedGoogle Scholar
  • 12 Searle T, Kraljevic Z, Bendayan R, Bean D, Dobson R. MedCATTrainer: a biomedical free text annotation interface with active learning and research use case specific customisation. arXiv:190707322. July 16, 2019. Accessed May 8, 2022 at: http://arxiv.org/abs/1907.07322
    PubMedGoogle Scholar
  • 13 Thomsen J, Tos M. Acoustic neuromas. Diagnostic delay, growth rate and possible non-surgical treatment. Acta Otolaryngol Suppl 1988; 452 (452) 26-33
    CrossrefPubMedGoogle Scholar
  • 14 Strickland BA, Rennert R, Zada G. et al. Surgical outcomes following vestibular schwannoma resection in patients over the age of sixty-five. J Neurol Surg B Skull Base 2022; 84 (02) 129-135
    PubMedGoogle Scholar
  • 15 Gurgel RK, Dogru S, Amdur RL, Monfared A. Facial nerve outcomes after surgery for large vestibular schwannomas: do surgical approach and extent of resection matter?. Neurosurg Focus 2012; 33 (03) E16
    CrossrefPubMedGoogle Scholar
  • 16 McMorran J, Crowther D, McMorran S. 20 years of GPnotebook: from a medical student project to a national resource. Br J Gen Pract 2014; 64 (619) 92-93
    CrossrefPubMedGoogle Scholar
  • 17 Irving J, Patel R, Oliver D. et al. Using natural language processing on electronic health records to enhance detection and prediction of psychosis risk. Schizophr Bull 2021; 47 (02) 405-414
    CrossrefPubMedGoogle Scholar
  • 18 Campillo-Gimenez B, Garcelon N, Jarno P, Chapplain JM, Cuggia M. Full-text automated detection of surgical site infections secondary to neurosurgery in Rennes, France. Stud Health Technol Inform 2013; 192: 572-575
    PubMedGoogle Scholar
  • 19 Lo Barco T, Kuchenbuch M, Garcelon N, Neuraz A, Nabbout R. Improving early diagnosis of rare diseases using natural language processing in unstructured medical records: an illustration from Dravet syndrome. Orphanet J Rare Dis 2021; 16 (01) 309
    CrossrefPubMedGoogle Scholar
  • 20 Cosgriff CV, Celi LA. Deep learning for risk assessment: all about automatic feature extraction. Br J Anaesth 2020; 124 (02) 131-133
    CrossrefPubMedGoogle Scholar
  • 21 Lee CK, Hofer I, Gabel E, Baldi P, Cannesson M. Development and validation of a deep neural network model for prediction of postoperative in-hospital mortality. Anesthesiology 2018; 129 (04) 649-662
    CrossrefPubMedGoogle Scholar
  • 22 Gadot R, Anand A, Lovin BD, Sweeney AD, Patel AJ. Predicting surgical decision-making in vestibular schwannoma using tree-based machine learning. Neurosurg Focus 2022; 52 (04) E8
    CrossrefPubMedGoogle Scholar
  • 23 Tang OY, Bajaj AI, Zhao K. et al. Association of patient frailty with vestibular schwannoma resection outcomes and machine learning development of a vestibular schwannoma risk stratification score. Neurosurgery 2022; 91 (02) 312-321
    CrossrefPubMedGoogle Scholar
  • 24 Mangus BD, Rivas A, Yoo MJ. et al. Management of cerebrospinal fluid leaks after vestibular schwannoma surgery. Otol Neurotol 2011; 32 (09) 1525-1529
    CrossrefPubMedGoogle Scholar
  • 25 Chern A, Hunter JB, Bennett ML. Cost analysis of cerebrospinal fluid leaks and cerebrospinal fluid leak prevention in patients undergoing cerebellopontine angle surgery. Otol Neurotol 2017; 38 (01) 147-151
    CrossrefPubMedGoogle Scholar
  • 26 Kraljevic Z, Bean D, Shek A. et al. Foresight–generative pretrained transformer (GPT) for modelling of patient timelines using EHRs. January 24, 2023 DOI: 10.48550/arXiv.2212.08072
    CrossrefPubMedGoogle Scholar
  • 27 Layard Horsfall H, Palmisciano P, Khan DZ. et al. Attitudes of the surgical team toward artificial intelligence in neurosurgery: international 2-stage cross-sectional survey. World Neurosurg 2021; 146: e724-e730
    CrossrefPubMedGoogle Scholar
  • 28 Palmisciano P, Jamjoom AAB, Taylor D, Stoyanov D, Marcus HJ. Attitudes of patients and their relatives toward artificial intelligence in neurosurgery. World Neurosurg 2020; 138: e627-e633
    CrossrefPubMedGoogle Scholar
  • 29 Lee CC, Lee WK, Wu CC. et al. Applying artificial intelligence to longitudinal imaging analysis of vestibular schwannoma following radiosurgery. Sci Rep 2021; 11 (01) 3106
    CrossrefPubMedGoogle Scholar
  • 30 Lee WK, Wu CC, Lee CC. et al. Combining analysis of multi-parametric MR images into a convolutional neural network: precise target delineation for vestibular schwannoma treatment planning. Artif Intell Med 2020; 107: 101911
    CrossrefPubMedGoogle Scholar
  • 31 Koechli C, Vu E, Sager P. et al. Convolutional neural networks to detect vestibular schwannomas on single MRI slices: a feasibility study. Cancers (Basel) 2022; 14 (09) 2069
    CrossrefPubMedGoogle Scholar
  • 32 Cass ND, Lindquist NR, Zhu Q, Li H, Oguz I, Tawfik KO. Machine learning for automated calculation of vestibular schwannoma volumes. Otol Neurotol 2022; 43 (10) 1252-1256
    CrossrefPubMedGoogle Scholar
  • 33 Shapey J, Wang G, Dorent R. et al. An artificial intelligence framework for automatic segmentation and volumetry of vestibular schwannomas from contrast-enhanced T1-weighted and high-resolution T2-weighted MRI. J Neurosurg 2019; 134 (01) 171-179
    CrossrefPubMedGoogle Scholar
  • 34 Shapey J, Kujawa A, Dorent R. et al. Artificial intelligence opportunities for vestibular schwannoma management using image segmentation and clinical decision tools. World Neurosurg 2021; 149: 269-270
    CrossrefPubMedGoogle Scholar
  • 35 Decision making on vestibular schwannoma treatment: predictions based on machine-learning analysis | Scientific Reports. Accessed March 27, 2023 at: https://www.nature.com/articles/s41598-021-97819-x
    PubMedGoogle Scholar
  • 36 Cha D, Shin SH, Kim SH, Choi JY, Moon IS. Machine learning approach for prediction of hearing preservation in vestibular schwannoma surgery. Sci Rep 2020; 10 (01) 7136
    CrossrefPubMedGoogle Scholar
  • 37 Tvardik N, Kergourlay I, Bittar A, Segond F, Darmoni S, Metzger MH. Accuracy of using natural language processing methods for identifying healthcare-associated infections. Int J Med Inform 2018; 117: 96-102
    CrossrefPubMedGoogle Scholar
  • 38 Wissel BD, Greiner HM, Glauser TA. et al. Prospective validation of a machine learning model that uses provider notes to identify candidates for resective epilepsy surgery. Epilepsia 2020; 61 (01) 39-48
    CrossrefPubMedGoogle Scholar