Publication date: Available online 28 March 2018
Source:Academic Radiology
Author(s): W. Katherine Tan, Saeed Hassanpour, Patrick J. Heagerty, Sean D. Rundell, Pradeep Suri, Hannu T. Huhdanpaa, Kathryn James, David S. Carrell, Curtis P. Langlotz, Nancy L. Organ, Eric N. Meier, Karen J. Sherman, David F. Kallmes, Patrick H. Luetmer, Brent Griffith, David R. Nerenz, Jeffrey G. Jarvik
Rationale and ObjectivesTo evaluate a natural language processing (NLP) system built with open-source tools for identification of lumbar spine imaging findings related to low back pain on magnetic resonance and x-ray radiology reports from four health systems.Materials and MethodsWe used a limited data set (de-identified except for dates) sampled from lumbar spine imaging reports of a prospectively assembled cohort of adults. From N = 178,333 reports, we randomly selected N = 871 to form a reference-standard dataset, consisting of N = 413 x-ray reports and N = 458 MR reports. Using standardized criteria, four spine experts annotated the presence of 26 findings, where 71 reports were annotated by all four experts and 800 were each annotated by two experts. We calculated inter-rater agreement and finding prevalence from annotated data. We randomly split the annotated data into development (80%) and testing (20%) sets. We developed an NLP system from both rule-based and machine-learned models. We validated the system using accuracy metrics such as sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).ResultsThe multirater annotated dataset achieved inter-rater agreement of Cohen's kappa > 0.60 (substantial agreement) for 25 of 26 findings, with finding prevalence ranging from 3% to 89%. In the testing sample, rule-based and machine-learned predictions both had comparable average specificity (0.97 and 0.95, respectively). The machine-learned approach had a higher average sensitivity (0.94, compared to 0.83 for rules-based), and a higher overall AUC (0.98, compared to 0.90 for rules-based).ConclusionsOur NLP system performed well in identifying the 26 lumbar spine findings, as benchmarked by reference-standard annotation by medical experts. Machine-learned models provided substantial gains in model sensitivity with slight loss of specificity, and overall higher AUC.
from Imaging via alkiviadis.1961 on Inoreader https://ift.tt/2GVojdK
Εγγραφή σε:
Σχόλια ανάρτησης (Atom)
Δημοφιλείς αναρτήσεις
-
Objectives Adult sagittal posture is established during childhood and adolescence. A flattened or hypercurved spine is associated with poore...
-
Objective Outpatient parenteral antimicrobial therapy (OPAT) provides opportunities for improved cost savings, but in the UK, implementation...
-
Abstract Purpose Overcoming the flaws of current data management conditions in head and neck oncology could enable integrated informatio...
-
CBN News Cancer Took Most of His Tongue, but This Pastor Is Still Singing ... CBN News A youth pastor in San Diego, California is not ...
-
Family: Know the drill New Straits Times Online One of my sons had this so often that his tonsils were removed. ... However, for som...
-
The E3 ubiquitin ligase F-box and WD repeat domain containing 7 (FBW7α) functions as a putative tumor suppressor in non-small cell lung canc...
-
In this study, the changes in pH, organic acid content, acidity, and salinity of kimchi prepared at 0 days, stored 1–8 weeks at 4 and 10°C, ...
-
When you make pizza this good you are allowed to brag about it. Come try a square of the best pizza in Erie. Ohhh yeah, we have ice cream no...
-
The March for Science reflects the growing gap between slow, steady, vital scientific gains and quick-fire, opportunist US politics, says D...
Δεν υπάρχουν σχόλια:
Δημοσίευση σχολίου