Literature DB >> 31784992

Prospective validation of a machine learning model that uses provider notes to identify candidates for resective epilepsy surgery.

Benjamin D Wissel1, Hansel M Greiner2,3, Tracy A Glauser2,3, Katherine D Holland-Bouley2,3, Francesco T Mangano2,4, Daniel Santel1, Robert Faist1, Nanhua Zhang2,5, John P Pestian1,2, Rhonda D Szczesniak2,5, Judith W Dexheimer1,2,6.   

Abstract

OBJECTIVE: Delay to resective epilepsy surgery results in avoidable disease burden and increased risk of mortality. The objective was to prospectively validate a natural language processing (NLP) application that uses provider notes to assign epilepsy surgery candidacy scores.
METHODS: The application was trained on notes from (1) patients with a diagnosis of epilepsy and a history of resective epilepsy surgery and (2) patients who were seizure-free without surgery. The testing set included all patients with unknown surgical candidacy status and an upcoming neurology visit. Training and testing sets were updated weekly for 1 year. One- to three-word phrases contained in patients' notes were used as features. Patients prospectively identified by the application as candidates for surgery were manually reviewed by two epileptologists. Performance metrics were defined by comparing NLP-derived surgical candidacy scores with surgical candidacy status from expert chart review.
RESULTS: The training set was updated weekly and included notes from a mean of 519 ± 67 patients. The area under the receiver operating characteristic curve (AUC) from 10-fold cross-validation was 0.90 ± 0.04 (range = 0.83-0.96) and improved by 0.002 per week (P < .001) as new patients were added to the training set. Of the 6395 patients who visited the neurology clinic, 4211 (67%) were evaluated by the model. The prospective AUC on this test set was 0.79 (95% confidence interval [CI] = 0.62-0.96). Using the optimal surgical candidacy score threshold, sensitivity was 0.80 (95% CI = 0.29-0.99), specificity was 0.77 (95% CI = 0.64-0.88), positive predictive value was 0.25 (95% CI = 0.07-0.52), and negative predictive value was 0.98 (95% CI = 0.87-1.00). The number needed to screen was 5.6. SIGNIFICANCE: An electronic health record-integrated NLP application can accurately assign surgical candidacy scores to patients in a clinical setting. Wiley Periodicals, Inc.
© 2019 International League Against Epilepsy.

Entities:  

Keywords:  clinical decision support; epilepsy surgery; machine learning; natural language processing

Mesh:

Year:  2019        PMID: 31784992      PMCID: PMC6980264          DOI: 10.1111/epi.16398

Source DB:  PubMed          Journal:  Epilepsia        ISSN: 0013-9580            Impact factor:   5.864


  38 in total

1.  Predictors for being offered epilepsy surgery: 5-year experience of a tertiary referral centre.

Authors:  Chiara Fois; Stjepana Kovac; Aytakin Khalil; Gülnur Tekgöl Uzuner; Beate Diehl; Tim Wehner; John S Duncan; Matthew C Walker
Journal:  J Neurol Neurosurg Psychiatry       Date:  2015-05-02       Impact factor: 10.154

2.  Neurologists' knowledge of and attitudes toward epilepsy surgery: a national survey.

Authors:  Jodie I Roberts; Chantelle Hrazdil; Samuel Wiebe; Khara Sauro; Michelle Vautour; Natalie Wiebe; Nathalie Jetté
Journal:  Neurology       Date:  2014-12-10       Impact factor: 9.910

3.  Investigation of bias in an epilepsy machine learning algorithm trained on physician notes.

Authors:  Benjamin D Wissel; Hansel M Greiner; Tracy A Glauser; Francesco T Mangano; Daniel Santel; John P Pestian; Rhonda D Szczesniak; Judith W Dexheimer
Journal:  Epilepsia       Date:  2019-08-23       Impact factor: 5.864

4.  Surgical outcomes for intractable epilepsy in children with epileptic spasms.

Authors:  Brian D Moseley; Katherine Nickels; Elaine C Wirrell
Journal:  J Child Neurol       Date:  2011-11-28       Impact factor: 1.987

5.  Referral to evaluation for epilepsy surgery: Reluctance by epileptologists and patients.

Authors:  Mirja Steinbrenner; Alexander B Kowski; Martin Holtkamp
Journal:  Epilepsia       Date:  2019-01-17       Impact factor: 5.864

Review 6.  Practice parameter: temporal lobe and localized neocortical resections for epilepsy: report of the Quality Standards Subcommittee of the American Academy of Neurology, in association with the American Epilepsy Society and the American Association of Neurological Surgeons.

Authors:  J Engel; S Wiebe; J French; M Sperling; P Williamson; D Spencer; R Gumnit; C Zahn; E Westbrook; B Enos
Journal:  Neurology       Date:  2003-02-25       Impact factor: 9.910

7.  How long does it take for partial epilepsy to become intractable?

Authors:  A T Berg; J Langfitt; S Shinnar; B G Vickrey; M R Sperling; T Walczak; C Bazil; S V Pacia; S S Spencer
Journal:  Neurology       Date:  2003-01-28       Impact factor: 9.910

8.  Surgery for Drug-Resistant Epilepsy in Children.

Authors:  Rekha Dwivedi; Bhargavi Ramanujam; P Sarat Chandra; Savita Sapra; Sheffali Gulati; Mani Kalaivani; Ajay Garg; Chandra S Bal; Madhavi Tripathi; Sada N Dwivedi; Rajesh Sagar; Chitra Sarkar; Manjari Tripathi
Journal:  N Engl J Med       Date:  2017-10-26       Impact factor: 91.245

9.  How accurate is ICD coding for epilepsy?

Authors:  Nathalie Jetté; Aylin Y Reid; Hude Quan; Michael D Hill; Samuel Wiebe
Journal:  Epilepsia       Date:  2009-07-20       Impact factor: 5.864

10.  Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration.

Authors:  Karel G M Moons; Douglas G Altman; Johannes B Reitsma; John P A Ioannidis; Petra Macaskill; Ewout W Steyerberg; Andrew J Vickers; David F Ransohoff; Gary S Collins
Journal:  Ann Intern Med       Date:  2015-01-06       Impact factor: 25.391

View more
  8 in total

1.  Can Big Data guide prognosis and clinical decisions in epilepsy?

Authors:  Xiaojin Li; Licong Cui; Guo-Qiang Zhang; Samden D Lhatoo
Journal:  Epilepsia       Date:  2021-02-02       Impact factor: 5.864

2.  Natural Language Processing Applications in the Clinical Neurosciences: A Machine Learning Augmented Systematic Review.

Authors:  Quinlan D Buchlak; Nazanin Esmaili; Christine Bennett; Farrokh Farrokhi
Journal:  Acta Neurochir Suppl       Date:  2022

Review 3.  Machine Learning in Neuro-Oncology, Epilepsy, Alzheimer's Disease, and Schizophrenia.

Authors:  Mason English; Chitra Kumar; Bonnie Legg Ditterline; Doniel Drazin; Nicholas Dietz
Journal:  Acta Neurochir Suppl       Date:  2022

4.  Impaired Functional Homotopy and Topological Properties Within the Default Mode Network of Children With Generalized Tonic-Clonic Seizures: A Resting-State fMRI Study.

Authors:  Yongxin Li; Bing Qin; Qian Chen; Jiaxu Chen
Journal:  Front Neurosci       Date:  2022-06-02       Impact factor: 5.152

Review 5.  Automated Identification of Surgical Candidates and Estimation of Postoperative Seizure Freedom in Children - A Focused Review.

Authors:  Debopam Samanta; Jules C Beal; Zachary M Grinspan
Journal:  Semin Pediatr Neurol       Date:  2021-08-19       Impact factor: 3.042

Review 6.  Can antiepileptic efficacy and epilepsy variables be studied from electronic health records? A review of current approaches.

Authors:  Barbara M Decker; Chloé E Hill; Steven N Baldassano; Pouya Khankhanian
Journal:  Seizure       Date:  2021-01-13       Impact factor: 3.184

7.  Early identification of epilepsy surgery candidates: A multicenter, machine learning study.

Authors:  Benjamin D Wissel; Hansel M Greiner; Tracy A Glauser; John P Pestian; Andrew J Kemme; Daniel Santel; David M Ficker; Francesco T Mangano; Rhonda D Szczesniak; Judith W Dexheimer
Journal:  Acta Neurol Scand       Date:  2021-03-26       Impact factor: 3.915

8.  Natural language processing in clinical neuroscience and psychiatry: A review.

Authors:  Claudio Crema; Giuseppe Attardi; Daniele Sartiano; Alberto Redolfi
Journal:  Front Psychiatry       Date:  2022-09-14       Impact factor: 5.435

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.