Rule-based approach for detecting dirty data in discharge summaries

Rabia, Lydia; Amarouche, Idir Amine; Bey, Kadda Beghdad

doi:10.1109/isps.2018.8379015

Cited by 2 publications

(9 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We identified 23 articles describing dedicated DQA programs implemented between 2013 and 2021, some of which have been deployed in real-world settings to assess EHR data quality (n = 14) [64][65][66][67][68][69][70][71][72][73][74][75][76][77], and a few experimental prototypes (n = 9) [48,[78][79][80][81][82][83][84][85], as shown in Table 1. Most of the DQA programs reported are affiliated with institutions in the USA (n = 12) and other countries, such as the UK, Canada, Germany, Belgium, the Netherlands, and Kenya.…”

Section: Study Summary and Contextmentioning

confidence: 99%

“…Most of the DQA programs reported are affiliated with institutions in the USA (n = 12) and other countries, such as the UK, Canada, Germany, Belgium, the Netherlands, and Kenya. These DQA programs were designed for various use cases, such as validating if data captured in particular EHRs conform to local system specifications [67,[72][73][74]76] or if they agree with data collected in other EHRs or other health information systems [64,75]. Also, some of the reported DQA programs focus on preparing datasets for research studies [48,66,79,83] and validating that data from contributing sites conform to research network or data warehouse specifications [65,[68][69][70][71]77].…”

Section: Study Summary and Contextmentioning

confidence: 99%

“…Also, given the increasingly task-dependent requirement of many DQA activities, some programs allow data consumers to specify the DQ-Dimensions they want to investigate dynamically at runtime [69,73]. These definitions can be expressed in different formats, including natural language (text), ontologies [52], taxonomies [39,74,83], queries [77,87], and other computational structures. Terms used to describe DQ-Dimension may also have multiple connotations.…”

Section: Dq-taskmentioning

confidence: 99%

“…Examples of such trade-offs could include focusing on data elements necessary for intended use cases [72,76,91], those prevalent in the previous records [61] and literature reviews [61,84], or having more weight regarding their contributions to the overall quality of a dataset [92]. A DQ-Task may also be limited to DQ-Dimensions that are feasible to investigate, [74,75,79,83], accuracy [69,84], timeliness [75], out of range [73,83], representation completeness [78,79], domain completeness [78,79], domain constraints [78,79], syntax accuracy [69], duplicate [83], domain consistency [79], precision [74], violations of logical order [83], redundancy [84], readability [84].…”

Section: Dq-taskmentioning

confidence: 99%

“…Data elements determined at runtime [73,78,81,84] pre-defined data elements, e.g. growth measurements [48], discharge summaries [74],…”

Section: Data-element An Individual Unit Of An Observationmentioning

confidence: 99%

See 4 more Smart Citations

Automating Electronic Health Record Data Quality Assessment

2023

View full text Add to dashboard Cite

Information systems such as Electronic Health Record (EHR) systems are susceptible to data quality (DQ) issues. Given the growing importance of EHR data, there is an increasing demand for strategies and tools to help ensure that available data are fit for use. However, developing reliable data quality assessment (DQA) tools necessary for guiding and evaluating improvement efforts has remained a fundamental challenge. This review examines the state of research on operationalising EHR DQA, mainly automated tooling, and highlights necessary considerations for future implementations. We reviewed 1841 articles from PubMed, Web of Science, and Scopus published between 2011 and 2021. 23 DQA programs deployed in real-world settings to assess EHR data quality (n = 14), and a few experimental prototypes (n = 9), were identified. Many of these programs investigate completeness (n = 15) and value conformance (n = 12) quality dimensions and are backed by knowledge items gathered from domain experts (n = 9), literature reviews and existing DQ measurements (n = 3). A few DQA programs also explore the feasibility of using data-driven techniques to assess EHR data quality automatically. Overall, the automation of EHR DQA is gaining traction, but current efforts are fragmented and not backed by relevant theory. Existing programs also vary in scope, type of data supported, and how measurements are sourced. There is a need to standardise programs for assessing EHR data quality, as current evidence suggests their quality may be unknown.

show abstract