Literature DB >> 35534660

Natural Language Processing of Radiology Reports to Detect Complications of Ischemic Stroke.

Matthew I Miller1, Agni Orfanoudaki2, Michael Cronin1, Hanife Saglam3, Ivy So Yeon Kim4, Oluwafemi Balogun4,5, Maria Tzalidi6, Kyriakos Vasilopoulos6, Georgia Fanaropoulou6, Nina M Fanaropoulou7, Jack Kalin1, Meghan Hutch8,9, Brenton R Prescott4, Benjamin Brush10, Emelia J Benjamin1,5, Min Shin11, Asim Mian12, David M Greer1,4, Stelios M Smirnakis9,13,14, Charlene J Ong15,16,17,18,19.   

Abstract

BACKGROUND: Abstraction of critical data from unstructured radiologic reports using natural language processing (NLP) is a powerful tool to automate the detection of important clinical features and enhance research efforts. We present a set of NLP approaches to identify critical findings in patients with acute ischemic stroke from radiology reports of computed tomography (CT) and magnetic resonance imaging (MRI).
METHODS: We trained machine learning classifiers to identify categorical outcomes of edema, midline shift (MLS), hemorrhagic transformation, and parenchymal hematoma, as well as rule-based systems (RBS) to identify intraventricular hemorrhage (IVH) and continuous MLS measurements within CT/MRI reports. Using a derivation cohort of 2289 reports from 550 individuals with acute middle cerebral artery territory ischemic strokes, we externally validated our models on reports from a separate institution as well as from patients with ischemic strokes in any vascular territory.
RESULTS: In all data sets, a deep neural network with pretrained biomedical word embeddings (BioClinicalBERT) achieved the highest discrimination performance for binary prediction of edema (area under precision recall curve [AUPRC] > 0.94), MLS (AUPRC > 0.98), hemorrhagic conversion (AUPRC > 0.89), and parenchymal hematoma (AUPRC > 0.76). BioClinicalBERT outperformed lasso regression (p < 0.001) for all outcomes except parenchymal hematoma (p = 0.755). Tailored RBS for IVH and continuous MLS outperformed BioClinicalBERT (p < 0.001) and linear regression, respectively (p < 0.001).
CONCLUSIONS: Our study demonstrates robust performance and external validity of a core NLP tool kit for identifying both categorical and continuous outcomes of ischemic stroke from unstructured radiographic text data. Medically tailored NLP methods have multiple important big data applications, including scalable electronic phenotyping, augmentation of clinical risk prediction models, and facilitation of automatic alert systems in the hospital setting.
© 2022. Springer Science+Business Media, LLC, part of Springer Nature and Neurocritical Care Society.

Entities:  

Keywords:  Critical care; Diagnostic imaging; Natural language processing; Stroke

Mesh:

Year:  2022        PMID: 35534660     DOI: 10.1007/s12028-022-01513-3

Source DB:  PubMed          Journal:  Neurocrit Care        ISSN: 1541-6933            Impact factor:   3.532


  37 in total

1.  Coding neuroradiology reports for the Northern Manhattan Stroke Study: a comparison of natural language processing and manual review.

Authors:  J S Elkins; C Friedman; B Boden-Albala; R L Sacco; G Hripcsak
Journal:  Comput Biomed Res       Date:  2000-02

2.  A Roadmap for Foundational Research on Artificial Intelligence in Medical Imaging: From the 2018 NIH/RSNA/ACR/The Academy Workshop.

Authors:  Curtis P Langlotz; Bibb Allen; Bradley J Erickson; Jayashree Kalpathy-Cramer; Keith Bigelow; Tessa S Cook; Adam E Flanders; Matthew P Lungren; David S Mendelson; Jeffrey D Rudie; Ge Wang; Krishna Kandarpa
Journal:  Radiology       Date:  2019-04-16       Impact factor: 11.105

3.  Deep Learning-A Technology With the Potential to Transform Health Care.

Authors:  Geoffrey Hinton
Journal:  JAMA       Date:  2018-09-18       Impact factor: 56.272

Review 4.  Natural Language Processing in Radiology: A Systematic Review.

Authors:  Ewoud Pons; Loes M M Braun; M G Myriam Hunink; Jan A Kors
Journal:  Radiology       Date:  2016-05       Impact factor: 11.105

5.  Assessment of the Predictive Validity of Etiologic Stroke Classification.

Authors:  E Murat Arsava; Johanna Helenius; Ross Avery; Mine H Sorgun; Gyeong-Moon Kim; Octavio M Pontes-Neto; Kwang Yeol Park; Jonathan Rosand; Mark Vangel; Hakan Ay
Journal:  JAMA Neurol       Date:  2017-04-01       Impact factor: 18.302

Review 6.  Neurocritical Care: Bench to Bedside (Eds. Claude Hemphill, Michael James) Integrating and Using Big Data in Neurocritical Care.

Authors:  Brandon Foreman
Journal:  Neurotherapeutics       Date:  2020-04       Impact factor: 7.620

7.  Analysis of Stroke Detection during the COVID-19 Pandemic Using Natural Language Processing of Radiology Reports.

Authors:  M D Li; M Lang; F Deng; K Chang; K Buch; S Rincon; W A Mehan; T M Leslie-Mazwi; J Kalpathy-Cramer
Journal:  AJNR Am J Neuroradiol       Date:  2020-12-17       Impact factor: 3.825

8.  Machine learning and natural language processing methods to identify ischemic stroke, acuity and location from radiology reports.

Authors:  Charlene Jennifer Ong; Agni Orfanoudaki; Rebecca Zhang; Francois Pierre M Caprasse; Meghan Hutch; Liang Ma; Darian Fard; Oluwafemi Balogun; Matthew I Miller; Margaret Minnig; Hanife Saglam; Brenton Prescott; David M Greer; Stelios Smirnakis; Dimitris Bertsimas
Journal:  PLoS One       Date:  2020-06-19       Impact factor: 3.240

9.  Improving Prehospital Stroke Diagnosis Using Natural Language Processing of Paramedic Reports.

Authors:  Anoop Mayampurath; Zahra Parnianpour; Christopher T Richards; William J Meurer; Jungwha Lee; Bruce Ankenman; Ohad Perry; Scott J Mendelson; Jane L Holl; Shyam Prabhakaran
Journal:  Stroke       Date:  2021-06-24       Impact factor: 10.170

View more
  1 in total

1.  Navigating the Ocean of Big Data in Neurocritical Care.

Authors:  Rajat Dhar; Geert Meyfroidt
Journal:  Neurocrit Care       Date:  2022-08       Impact factor: 3.532

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.