Dataset Information

A Data Element-Function Conceptual Model for Data Quality Checks.

ABSTRACT:

Introduction

In aggregate, existing data quality (DQ) checks are currently represented in heterogeneous formats, making it difficult to compare, categorize, and index checks. This study contributes a data element-function conceptual model to facilitate the categorization and indexing of DQ checks and explores the feasibility of leveraging natural language processing (NLP) for scalable acquisition of knowledge of common data elements and functions from DQ checks narratives.

Methods

The model defines a "data element", the primary focus of the check, and a "function", the qualitative or quantitative measure over a data element. We applied NLP techniques to extract both from 172 checks for Observational Health Data Sciences and Informatics (OHDSI) and 3,434 checks for Kaiser Permanente's Center for Effectiveness and Safety Research (CESR).

Results

The model was able to classify all checks. A total of 751 unique data elements and 24 unique functions were extracted. The top five frequent data element-function pairings for OHDSI were Person-Count (55 checks), Insurance-Distribution (17), Medication-Count (16), Condition-Count (14), and Observations-Count (13); for CESR, they were Medication-Variable Type (175), Medication-Missing (172), Medication-Existence (152), Medication-Count (127), and Socioeconomic Factors-Variable Type (114).

Conclusions

This study shows the efficacy of the data element-function conceptual model for classifying DQ checks, demonstrates early promise of NLP-assisted knowledge acquisition, and reveals the great heterogeneity in the focus in DQ checks, confirming variation in intrinsic checks and use-case specific "fitness-for-use" checks.

SUBMITTER: Rogers JR

PROVIDER: S-EPMC6484368 | biostudies-literature | 2019 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Data Element-Function Conceptual Model for Data Quality Checks.

Rogers James R JR Callahan Tiffany J TJ Kang Tian T Bauck Alan A Khare Ritu R Brown Jeffrey S JS Kahn Michael G MG Weng Chunhua C

EGEMS (Washington, DC) 20190423 1

<h4>Introduction</h4>In aggregate, existing data quality (DQ) checks are currently represented in heterogeneous formats, making it difficult to compare, categorize, and index checks. This study contributes a data element-function conceptual model to facilitate the categorization and indexing of DQ checks and explores the feasibility of leveraging natural language processing (NLP) for scalable acquisition of knowledge of common data elements and functions from DQ checks narratives.<h4>Methods</h4 ...[more]

PMID: 31065558

Similar Datasets

Project description:Background:Hypertrophic cardiomyopathy (HCM) is a primary myocardial disorder defined by left ventricular hypertrophy that cannot be explained by another cardiac or systemic disease. There is a general lack of knowledge about patients' perspectives on the symptoms and day-to-day limitations they experience as a result of HCM. We therefore sought an in-depth understanding of patients' experiences of obstructive (oHCM) and nonobstructive (nHCM) forms of the disease, including symptoms and their quality of life impacts, and to develop a conceptual model to capture them.Methods:Development of the HCM conceptual model involved a web-based survey to capture patients' insights, a targeted literature review (which included relevant guidelines and patient advocacy websites), one-to-one interviews with clinical experts, and one-to-one qualitative concept elicitation interviews with patients. Key symptoms and their impacts most important to patients' experiences were identified and used to develop a conceptual model of the patient experience with HCM.Results:The HCM symptoms reported by patient interviewees (n?=?27) were largely consistent with findings from the patient web survey (n?=?444), literature review, and interviews with three expert clinicians. The symptoms most commonly reported in patient interviews included tiredness (89%), shortness of breath (89%), shortness of breath with physical activity (89%), and dizziness/light-headedness (89%). Other symptoms commonly reported included chest pain (angina) (70%), chest pain (angina) with physical exertion (70%), and palpitations (fluttering or rapid heartbeat) (81%). The most commonly reported impacts of HCM symptoms on patients' lives included limitations to physical activities (78%), emotional impacts, including feeling anxious or depressed (78%), and impacts on work (63%). Symptoms and impacts were similar for both oHCM and nHCM.Conclusions:A conceptual model was developed, which identifies the core symptoms that patients with oHCM and nHCM reported as most frequent and most important: shortness of breath, palpitations, fatigue/tiredness, dizziness/light-headedness, and chest pain, as well as the impacts those symptoms have on patients' lives. This HCM conceptual model reflecting patients' experiences and perspectives was used in the development of a patient-reported outcomes instrument for use in clinical trials and it may also help inform the clinical management of HCM.

Dataset Information

A Data Element-Function Conceptual Model for Data Quality Checks.

Introduction

Methods

Results

Conclusions

Publications

A Data Element-Function Conceptual Model for Data Quality Checks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure