Extracting a stroke phenotype risk factor from Veteran Health Administration clinical reports: an information content analysis
نویسندگان
چکیده
BACKGROUND In the United States, 795,000 people suffer strokes each year; 10-15 % of these strokes can be attributed to stenosis caused by plaque in the carotid artery, a major stroke phenotype risk factor. Studies comparing treatments for the management of asymptomatic carotid stenosis are challenging for at least two reasons: 1) administrative billing codes (i.e., Current Procedural Terminology (CPT) codes) that identify carotid images do not denote which neurovascular arteries are affected and 2) the majority of the image reports are negative for carotid stenosis. Studies that rely on manual chart abstraction can be labor-intensive, expensive, and time-consuming. Natural Language Processing (NLP) can expedite the process of manual chart abstraction by automatically filtering reports with no/insignificant carotid stenosis findings and flagging reports with significant carotid stenosis findings; thus, potentially reducing effort, costs, and time. METHODS In this pilot study, we conducted an information content analysis of carotid stenosis mentions in terms of their report location (Sections), report formats (structures) and linguistic descriptions (expressions) from Veteran Health Administration free-text reports. We assessed an NLP algorithm, pyConText's, ability to discern reports with significant carotid stenosis findings from reports with no/insignificant carotid stenosis findings given these three document composition factors for two report types: radiology (RAD) and text integration utility (TIU) notes. RESULTS We observed that most carotid mentions are recorded in prose using categorical expressions, within the Findings and Impression sections for RAD reports and within neither of these designated sections for TIU notes. For RAD reports, pyConText performed with high sensitivity (88 %), specificity (84 %), and negative predictive value (95 %) and reasonable positive predictive value (70 %). For TIU notes, pyConText performed with high specificity (87 %) and negative predictive value (92 %), reasonable sensitivity (73 %), and moderate positive predictive value (58 %). pyConText performed with the highest sensitivity processing the full report rather than the Findings or Impressions independently. CONCLUSION We conclude that pyConText can reduce chart review efforts by filtering reports with no/insignificant carotid stenosis findings and flagging reports with significant carotid stenosis findings from the Veteran Health Administration electronic health record, and hence has utility for expediting a comparative effectiveness study of treatment strategies for stroke prevention.
منابع مشابه
Hybrid Method of Logistic Regression and Data Envelopment Analysis for Event Prediction: A Case Study (Stroke Disease)
Abstract Predictive analytics is an area of statistics that deals with extracting information from data and using it to predict trends and behavior patterns. Many mathematical modeling has been developed and used for prediction, and in some cases, they have been found to be very strong and reliable. This paper studies different mathematical and statistical approaches for events prediction. The ...
متن کاملThe frequency of post-stroke depression in an outpatient elderly population
Abstract Background: The purpose of the present study is to determine the frequency and severity of depression in post-stroke patients. Methods: Based on a cross-sectional research design, 30 recent stroke outpatients were assessed with DSM-IV interview for depression and two self-rating depression scales, CES-D and BDI. Sex differences in depression, the relationship between depression and th...
متن کاملHeritability for Stroke: Essential for Taking Family History
There are many well-established factors that influence the risk of stroke including blood pressure, diabetes, low socioeconomic status and smoking, however, the shared genetic resource in members of a family effect on stroke predisposition. Genome-wide association studies (GWAS) have demonstrated evidence of a shared genetic source in stroke risk. This review considered the influence of family...
متن کاملPrevalence of Knee OA in Karate Community in Indonesia
Background. Osteoarthritis (OA) ranks fifth in the most disabling conditions. Karate is an unarmed combat sport that uses hands and feet to deliver and block blows. The karate movements, such as high load and frequent flexion and extension of the knee, make the athletes susceptible to knee injuries and progress to knee OA (KOA). Objectives. The study aims to address the prevalence and risk fac...
متن کاملStill the Great Debate – “Fair Balance” in Direct-to-Consumer Prescription Drug Advertising; Comment on “Trouble Spots in Online Direct-to-Consumer Prescription Drug Promotion: A Content Analysis of FDA Warning Letters”
The above titled paper examined the Food and Drug Administration’s (FDA’s) warning letters and notice of violations (NOV) over a 10-year period. Findings from this content analysis reinforced what has been the primary issue for prescription direct-to-consumer advertising (DTCA) since its beginning, the fair balance of risk and benefit information. As opposed to another analysis in 2026 about th...
متن کامل