Development and validation of data quality rules in administrative health data using association rule mining

Abstract

Background: Data quality assessment presents a challenge for research using coded administrative health data. The objective of this study is to develop and validate a set of coding association rules for coded diagnostic data. Methods: We used the Canadian re-abstracted hospital discharge abstract data coded in International Classification of Disease, 10th revision (ICD-10) codes. Association rule mining was conducted on the re-abstracted data in four age groups (0-4, 20-44, 45-64; ≥ 65) to extract ICD-10 coding association rules at the three-digit (category of diagnosis) and four-digit levels (category of diagnosis with etiology, anatomy, or severity). The rules were reviewed by a panel of 5 physicians and 2 classification specialists using a modified Delphi rating process. We proposed and defined the variance and bias to assess data quality using the rules. Results: After the rule mining process and the panel review, 388 rules at the three-digit level and 275 rules at the four-digit level were developed. Half of the rules were from the age group of ≥65. Rules captured meaningful agespecific clinical associations, with rules at the age group of ≥65 being more complex and comprehensive than other age groups. The variance and bias can identify rules with high bias and variance in Alberta data and provides directions for quality improvement. Conclusions: A set of ICD-10 data quality rules were developed and validated by a clinical and classification expert panel. The rules can be used as a tool to assess ICD-coded data, enabling the monitoring and comparison of data quality across institutions, provinces, and countries.

Definitions and Prevalence of Multimorbidity in Large Database Studies: A Scoping Review

“…While patient record review has been suggested as the best method to derive multimorbidity prevalence as it is not reliant on coding and data entry [ 15 , 16 ], large studies lack access to individual patient notes or direct accounts of patients’ conditions. Errors in coding subsequently implicate the accuracy of research using data from large databases [ 14 ].…”

“…Compared to smaller databases, standards of governance are generally required to ensure diagnoses are reliably coded in large datasets. Some challenges in using larger databases include the accuracy of the coding system used, and the reliability of coding as hospital records may be coded by non-physicians and may not reflect the actual codes from the physicians' perspectives [14,15]. This is confounded by the impracticability to go through individual patient notes or obtain a direct account of the patient's conditions.…”

CODE-EHR best practice framework for the use of structured electronic healthcare records in clinical research

“…14 Data quality rules can be used to assess coded data and allow comparisons across institutions and countries. 15 Reporting of methods used for data pre-processing and data linkage. This includes the methods used to assess the quality of linkage and the results of any data pre-processing and linkage (with provision of false positive and false negative rates, comparisons of linked and unlinked data, and any sensitivity analyses).…”

LRFM- based association rule mining for dentistry services patterns identification (Case study: a dental center in Iran)

“…Finally, they tried to analyze the rules and compare them with the physician's decisions. (Peng et al, 2020) used association rules in a hospital discharge abstract data in order to investigate whether the coding system in the case study hospital could be improved or not. Results showed that the rules extracted could de ne different codes and helped the coding system to be more structured.…”