Accuracy of ICD-9-CM Codes for Identifying Cardiovascular and Stroke Risk Factors

By E. Birman-Deych, A. Waterman, Yan Yan, D. Nilasena, M. Radford, B. Gage. 2005

736 citations recorded by the source corpus.

Subfields: Epidemiology, General Health Professions, Health Information Management

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Epidemiology

1. Jacob Eisenstein
2. Jimeng Sun
3. Harlan M. Krumholz
4. Jon D. Duke

In General Health Professions

1. Harlan M. Krumholz

In Health Information Management

1. Jimeng Sun
2. Joshua Charles Denny

Citations in the corpus

• Natural Language Processing for EHR-Based Computational Phenotyping (2018, neutral): “to accurately infer phenotypes [10], [11].”
• Explainable Prediction of Medical Codes from Clinical Text (2018, background): “These features combine to make the prediction of ICD codes from clinical notes an especially difficult task, for computers and human coders alike (Birman-Deych et al., 2005).”
• Diagnoses and Timing of 30-Day Readmissions after Hospitalization For Heart Failure, Acute Myocardial Infarction, or Pneumonia (2013, positive): “However, administrative codes have been shown to be accurate for cardiovascular and pulmonary diagnoses.(47-49) Finally, CMS claims data contain relatively limited information on patient social factors potentially associated with readmission patterns,(50) and we did not develop proxy measures to tes”
• Identifying and Mitigating Biases in EHR Laboratory Tests (2014, neutral): “ICD-9 codes are notoriously non-specific to patient disease state and are often not recorded for all patient ailments [11] [12].”
• Detection of drug‐drug interactions through data mining studies using clinical sources, scientific literature and social media (2018, neutral): “There are some examples that showed that coded data may be insufficient to describe some steps in pharmacovigilance procedures and that the combination with narrative data can yield better results, such as building patient cohorts [55, 56].”
• Extracting and integrating data from entire electronic health records for detecting colorectal cancer cases. (2011, background): “For disease case detection, a number of studies have shown that coded data such as International Classification of Disease (ICD) codes were not sufficient or accurate enough [16-18].”