Integrating Natural Language Processing and Machine Learning Algorithms to Categorize Oncologic Response in Radiology Reports

Journal of Digital Imaging
Po-Hao ChenTessa Cook

Abstract

A significant volume of medical data remains unstructured. Natural language processing (NLP) and machine learning (ML) techniques have shown to successfully extract insights from radiology reports. However, the codependent effects of NLP and ML in this context have not been well-studied. Between April 1, 2015 and November 1, 2016, 9418 cross-sectional abdomen/pelvis CT and MR examinations containing our internal structured reporting element for cancer were separated into four categories: Progression, Stable Disease, Improvement, or No Cancer. We combined each of three NLP techniques with five ML algorithms to predict the assigned label using the unstructured report text and compared the performance of each combination. The three NLP algorithms included term frequency-inverse document frequency (TF-IDF), term frequency weighting (TF), and 16-bit feature hashing. The ML algorithms included logistic regression (LR), random decision forest (RDF), one-vs-all support vector machine (SVM), one-vs-all Bayes point machine (BPM), and fully connected neural network (NN). The best-performing NLP model consisted of tokenized unigrams and bigrams with TF-IDF. Increasing N-gram length yielded little to no added benefit for most ML algorithms....Continue Reading

References

Feb 3, 2005·Journal of the American Medical Informatics Association : JAMIA·George Hripcsak, Adam S Rothschild
Nov 1, 2011·Journal of Digital Imaging·Paras LakhaniCurtis P Langlotz
Dec 11, 2014·IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society·Xiao LiuJiajun Bu
Jul 2, 2015·Journal of the American College of Radiology : JACR·Hanna M ZafarMitchell D Schnall
Sep 12, 2015·Journal of Digital Imaging·Saeed Hassanpour, Curtis P Langlotz
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 18, 2016·Journal of Biomedical Informatics·Mohammad Amin MoridGuilherme Del Fiol
Apr 29, 2016·JAMA Oncology·Wen-Wai YimSharon W Kwan
Aug 12, 2016·BMC Medical Genomics·Jian WangYuanyuan Sun

❮ Previous
Next ❯

Citations

Dec 6, 2018·Journal of the American Medical Informatics Association : JAMIA·Ronilda LacsonRamin Khorasani
Aug 7, 2020·JCO Clinical Cancer Informatics·Kenneth L KehlDeborah Schrag
Apr 8, 2020·Journal of Digital Imaging·Priya DeshpandeSamuel G Armato
Oct 12, 2018·Radiographics : a Review Publication of the Radiological Society of North America, Inc·Alexander J Towbin
Dec 6, 2018·European Radiology Experimental·Daniel Pinto Dos Santos, Bettina Baeßler
Jul 18, 2018·Der Radiologe·F JungmannB Kämpgen
May 15, 2021·JCO Clinical Cancer Informatics·Matthew S AlkaitisDavid Sontag
May 21, 2021·Skeletal Radiology·Matthew D LiConnie Y Chang
Jun 5, 2021·BMC Medical Informatics and Decision Making·Arlene CaseyBeatrice Alex
Jun 18, 2021·Radiology. Artificial Intelligence·Hesham Elhalawani, Raymond Mak
Aug 14, 2021·Radiographics : a Review Publication of the Radiological Society of North America, Inc·Krishna JuluruPierre Elnajjar

❮ Previous
Next ❯

Related Concepts

Related Feeds

Cancer Imaging

Imaging techniques, including CT and MR, have become essential to tumor detection, diagnosis, and monitoring. Here is the latest research on cancer imaging.