Measuring diagnoses: ICD code accuracy.

By K. O'Malley, Karon Cook, Matt D. Price, K. Wildes, John F. Hurdle, C. Ashton. 2005

1,124 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

In General Health Professions

In Health Information Management

Citations in the corpus

Natural Language Processing for EHR-Based Computational Phenotyping (2018, background): “For example, ICD-9 codes are mainly recorded for administrative purposes and are influenced by billing requirements and avoidance of liability [12, 13].”
Extracting research-quality phenotypes from electronic health records to support precision medicine (2015, background): “Common sources of inaccuracy include the amount and quality of information available, communication between patients and clinicians, professional knowledge and experience with the illness, unintentional errors (for example, misspecification, use of medical abbreviations), and, occasionally, intentio”
Word2Vec inversion and traditional text classifiers for phenotyping lupus (2017, background): “ICD-9 billing codes have been proven to be ineffective classifiers in the past [1–3].”
Do no harm: a roadmap for responsible machine learning for health care (2019, background): “They may poorly correspond to the actual diagnoses 6 and should not be relied on as ground truth.”
Validation of the national health insurance research database with ischemic stroke cases in Taiwan (2011, background): “Errors in assigning ICD-9 codes can be caused by ambiguous descriptions made by physicians or by a coder misunderstanding or miscoding a written diagnosis.(28) Incorrect coding of discharge diagnoses can also result when initial diagnoses based on clinical impressions are not updated during hospital”
Information security and privacy in healthcare: current state of research (2010, methodology): “can result from the amount and quality of information being gathered at admission, communication quality between patients and clinicians, clinical training and experience, transcription error, training and experience of coders, and incorrect bundling of codes (O’Malley et al., 2005).”
A Review of Challenges and Opportunities in Machine Learning for Health. (2018, background): “Or, in some cases, structured labels may unreliable 29 .”