Natural language processing and machine learning algorithm to identify brain MRI reports with acute ischemic stroke

PloS One
Chulho KimLeslie Lenert

Abstract

This project assessed performance of natural language processing (NLP) and machine learning (ML) algorithms for classification of brain MRI radiology reports into acute ischemic stroke (AIS) and non-AIS phenotypes. All brain MRI reports from a single academic institution over a two year period were randomly divided into 2 groups for ML: training (70%) and testing (30%). Using "quanteda" NLP package, all text data were parsed into tokens to create the data frequency matrix. Ten-fold cross-validation was applied for bias correction of the training set. Labeling for AIS was performed manually, identifying clinical notes. We applied binary logistic regression, naïve Bayesian classification, single decision tree, and support vector machine for the binary classifiers, and we assessed performance of the algorithms by F1-measure. We also assessed how n-grams or term frequency-inverse document frequency weighting affected the performance of the algorithms. Of all 3,204 brain MRI documents, 432 (14.3%) were labeled as AIS. AIS documents were longer in character length than those of non-AIS (median [interquartile range]; 551 [377-681] vs. 309 [164-396]). Of all ML algorithms, single decision tree had the highest F1-measure (93.2) and accu...Continue Reading

References

Nov 4, 2000·Radiology·P W SchaeferR G Gonzalez
Feb 2, 2008·Stroke; a Journal of Cerebral Circulation·Dawn KleindorferJoseph P Broderick
Dec 6, 2011·Journal of the American College of Radiology : JACR·Ronilda Lacson, Ramin Khorasani
Apr 2, 2013·Journal of the American Medical Informatics Association : JAMIA·Adam WrightDean F Sittig
May 9, 2013·Stroke; a Journal of Cerebral Circulation·Ralph L SaccoUNKNOWN Council on Nutrition, Physical Activity and Metabolism
May 31, 2014·Journal of Digital Imaging·Yihua ZhouFranz J Wippold
Jul 17, 2014·JAMA : the Journal of the American Medical Association·Silvia KotonJosef Coresh
Oct 22, 2014·Journal of the American Medical Informatics Association : JAMIA·Christian M RochefortDavid L Buckeridge
Oct 21, 2015·Artificial Intelligence in Medicine·Saeed Hassanpour, Curtis P Langlotz
Jan 14, 2016·Radiographics : a Review Publication of the Radiological Society of North America, Inc·Tianrun CaiDimitrios Mitsouras
Jan 15, 2016·Academic Emergency Medicine : Official Journal of the Society for Academic Emergency Medicine·Kabir YadavJames M Chamberlain
Jan 31, 2016·Academic Emergency Medicine : Official Journal of the Society for Academic Emergency Medicine·Son DoanUNKNOWN Pediatric Emergency Medicine Kawasaki Disease Research Group
Nov 9, 2016·Applied Clinical Informatics·Robert W GrundmeierUNKNOWN Pediatric Emergency Care Applied Research Network
Nov 9, 2016·Breast Cancer Research and Treatment·Adam YalaKevin S Hughes
Jul 2, 2017·Stroke; a Journal of Cerebral Circulation·Isabel FragataPatrícia Canhão
Sep 18, 2017·Journal of Stroke and Cerebrovascular Diseases : the Official Journal of National Stroke Association·Mandip S DhamoonBaiju R Shah
Oct 22, 2017·European Journal of Radiology·Pedro Vilela, Howard A Rowley
Oct 12, 2017·Biomedical Engineering Letters·Salim LahmiriAmir Shmuel

❮ Previous
Next ❯

Citations

Oct 27, 2020·Journal of Gastroenterology and Hepatology·Dennis ShungAndrew Taylor
Dec 15, 2020·Brain and Behavior·Xiao-Guang ZhangYun-Hua Yue
Jun 5, 2021·BMC Medical Informatics and Decision Making·Arlene CaseyBeatrice Alex
Nov 20, 2021·Journal of the American Heart Association·Sheng-Feng SungJiann-Shing Jeng

❮ Previous
Next ❯

Methods Mentioned

BETA
imaging techniques

Software Mentioned

word2vec
rpart
quanteda
GloVe
quanteda R package
R
e1071

Related Concepts

Related Feeds

Brain Ischemia

Brain ischemia is a condition in which there is insufficient blood flow to the brain to meet metabolic demand. Discover the latest research on brain ischemia here.

Acute Stroke

A stroke occurs when blood supply to the brain is interrupted depriving the brain of oxygen and nutrients. This feed focuses cerebrovascular accidents including ischemic and paralytic stroke.