Identification of documented medication non-adherence in physician notes.
Authors:
- Jonathan Seth EinbinderJEJonathan Seth Einbinder
- 6 November 2008
- journal article
- Vol. 2008, 732-6
Abstract
Medication non-adherence is common and the physicians awareness of it may be an important factor in clinical decision making. Few sources of data on physician awareness of medication non-adherence are available. We have designed an algorithm to identify documentation of medication non-adherence in the text of physician notes. The algorithm recognizes eight semantic classes of documentation of medication non-adherence. We evaluated the algorithm against manual ratings of 200 randomly selected notes of hypertensive patients. The algorithm detected 89% of the notes with documented medication non-adherence with specificity of 84.7% and positive predictive value of 80.2%. In a larger dataset of 1,000 documents, notes that documented medication non-adherence were more likely to report significantly elevated systolic (15.3% vs. 9.0%; p = 0.002) and diastolic (4.1% vs. 1.9%; p = 0.03) blood pressure. This novel clinically validated tool expands the range of information on medication non-adherence available to researchers.Keywords
This publication has 17 references indexed in Scilit:
- Effect of Board Certification on Antihypertensive Treatment Intensification in Patients With Diabetes MellitusCirculation, 2008
- Automation of a problem list using natural language processingBMC Medical Informatics and Decision Making, 2005
- MediClass: A System for Detecting and Classifying Encounter-based Clinical Events in Any Electronic Medical RecordJournal of the American Medical Informatics Association, 2005
- Clinical Outcomes and Adherence to Medications Measured by Claims Data in Patients With DiabetesDiabetes Care, 2004
- Automated Encoding of Clinical Documents Based on Natural Language ProcessingJournal of the American Medical Informatics Association, 2004
- Variations in Patients’ Adherence to Medical RecommendationsMedical Care, 2004
- medSynDiKATe—a natural language system for the extraction of medical information from findings reportsInternational Journal of Medical Informatics, 2002
- Physician-Related Barriers to the Effective Management of Uncontrolled HypertensionArchives of internal medicine (1960), 2002
- Clinical InertiaAnnals of Internal Medicine, 2001
- The assessment of refill compliance using pharmacy records: Methods, validity, and applicationsJournal of Clinical Epidemiology, 1997