[Paper Review] A Framework for Transparent Reporting of Data Quality Analysis Across the Clinical Electronic Health Record Data Lifecycle

M. Wassell, Kerryn Butler-Henderson+1 more|arXiv (Cornell University)|Mar 1, 2026

Scientific Computing and Data Management0 citations

TL;DR

The paper develops a framework to transparently report data quality assessments across the clinical EHR data lifecycle, clarifying provenance and enabling targeted DQ improvements for research and AI workflows.

ABSTRACT

Data quality (DQ) and transparency of secondary data are critical factors that delay the adoption of clinical AI models and affect clinician trust in them. Many DQ studies fail to clarify where, along the lifecycle, quality checks occur, leading to uncertainty about provenance and fitness for reuse. This study develops a framework for transparent reporting of DQ assessments across the clinical electronic health record (EHR) data lifecycle. The reporting framework was developed through iterative analysis to identify actors and phases of the clinical data lifecycle. The framework distinguishes between data-generating organizations and data-receiving organizations to allow users to map DQ parameters to stages across the data lifecycle. The framework defines 5 key lifecycle phases and multiple actors. When applied to the real-world dataset, the framework demonstrated applicability in revealing where DQ issues may originate. The framework provides a structured approach for reporting DQ assessments, which can enhance transparency regarding data fitness for reuse, supporting reliable clinical research, AI model development, and internal organisational governance. This work provides practical guidance for researchers to understand data provenance and for organisations to target DQ improvement efforts across the data lifecycle.

Motivation & Objective

• Clarify where data quality checks occur along the clinical EHR data lifecycle.
• Distinguish between data-generating and data-receiving organizations to map DQ parameters to lifecycle stages.
• Identify actors and lifecycle phases to provide a structured reporting framework for DQ assessments.
• Demonstrate applicability of the framework on a real-world dataset to reveal origins of DQ issues.
• Offer practical guidance to researchers and organizations for data provenance understanding and governance.

Proposed method

• Iterative analysis to identify actors and phases of the clinical data lifecycle.
• Define a five-phase lifecycle and multiple actors to map DQ parameters to stages.

Experimental results

Research questions

• RQ1 What are the key lifecycle phases and actors in clinical EHR data that influence data quality reporting?
• RQ2 How can DQ assessments be transparently reported to indicate provenance and fitness for reuse across the data lifecycle?
• RQ3 How does differentiating data-generating from data-receiving organizations aid in tracing DQ issues?
• RQ4 Can the framework reveal where DQ issues originate in real-world EHR datasets?

Key findings

• The framework identifies five lifecycle phases and multiple actors for DQ reporting.
• It distinguishes data-generating vs data-receiving organizations to map DQ parameters to lifecycle stages.
• Applied to a real-world dataset, the framework demonstrated its ability to reveal where DQ issues may originate.
• The approach provides a structured method for reporting DQ assessments to enhance transparency and governance.
• The framework supports reliable clinical research, AI model development, and internal organizational governance through improved provenance.
• The work offers practical guidance for researchers and organizations to target DQ improvements across the data lifecycle.