Jens Declerck

Jens Declerck

Auto-generated profile, based on publicly available information

Jens Declerck

Department of Public Health and Primary Care, Unit of Medical Informatics and Statistics, Ghent University, Ghent, Belgium

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 March 2024 in JMIR Medical Informatics
Verified
Journal Article
Open access
JDJens Declerck
Jens Declerck
DKDipak Kalra
Dipak Kalra
RSRobert Vander Stichele
Robert Vander Stichele
PCPascal Coorevits
Pascal Coorevits
Background: Health care has not reached the full potential of the secondary use of health data because of—among other issues—concerns about the quality of the data being used. The shift toward digital health has led to an increase in the volume of health data. However, this increase in quantity has not been matched by a proportional improvement in the quality of health data. Objective: This review aims to offer a comprehensive overview of the existing frameworks for data quality dimensions and assessment methods for the secondary use of health data. In addition, it aims to consolidate the results into a unified framework. Methods: A review of reviews was conducted including reviews describing frameworks of data quality dimensions and their assessment methods, specifically from a secondary use perspective. Reviews were excluded if they were not related to the health care ecosystem, lacked relevant information related to our research objective, and were published in languages other than English. Results: A total of 22 reviews were included, comprising 22 frameworks, with 23 different terms for dimensions, and 62 definitions of dimensions. All dimensions were mapped toward the data quality framework of the European Institute for Innovation through Health Data. In total, 8 reviews mentioned 38 different assessment methods, pertaining to 31 definitions of the dimensions. Conclusions: The findings in this review revealed a lack of consensus in the literature regarding the terminology, definitions, and assessment methods for data quality dimensions. This creates ambiguity and difficulties in developing specific assessment methods. This study goes a step further by assigning all observed definitions to a consolidated framework of 9 data quality dimensions.

12 November 2025 in JMIR Medical Informatics
Verified
Journal Article
Open access
JDJens Declerck
Jens Declerck
ÖKÖmer Durukan Kılıç
Ömer Durukan Kılıç
EEEnsar Emir Erol
Ensar Emir Erol
SMShervin Mehryar
Shervin Mehryar
DKDipak Kalra
Dipak Kalra
RCRemzi Celebi
Remzi Celebi
Background: Integrated health data are foundational for secondary use, research, and policymaking. However, data quality issues—such as missing values and inconsistencies—are common due to the heterogeneity of health data sources. Existing frameworks often use static, 1-time assessments, which limit their ability to address quality issues across evolving data pipelines. Objective: This study evaluates the AIDAVA (artificial intelligence–powered data curation and validation) data quality framework, which introduces dynamic, life cycle–based validation of health data using knowledge graph technologies and SHACL (Shapes Constraint Language)–based rules. The framework is assessed for its ability to detect and manage data quality issues—specifically, completeness and consistency—during integration. Methods: Using the MIMIC-III (Medical Information Mart for Intensive Care-III) dataset, we simulated real-world data quality challenges by introducing structured noise, including missing values and logical inconsistencies. The data was transformed into source knowledge graphs and integrated into a unified personal health knowledge graph. SHACL validation rules were applied iteratively during the integration process, and data quality was assessed under varying noise levels and integration orders. Results: The AIDAVA framework effectively detected completeness and consistency issues across all scenarios. Completeness was shown to influence the interpretability of consistency scores, and domain-specific attributes (eg, diagnoses and procedures) were more sensitive to integration order and data gaps. Conclusions: AIDAVA supports dynamic, rule-based validation throughout the data life cycle. By addressing both dimension-specific vulnerabilities and cross-dimensional effects, it lays the groundwork for scalable, high-quality health data integration. Future work should explore deployment in live clinical settings and expand to additional quality dimensions.

30 May 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
JDJens Declerck
Jens Declerck
JLJoanne Lee
Joanne Lee
ASAnando Sen
Anando Sen
VSVolker Straub
Volker Straub
OOOostenbrink Oostenbrink
Oostenbrink Oostenbrink
VSVolker Straub
Volker Straub
Background: Pediatric clinical research, especially in rare diseases, faces persistent challenges including the identification and recruitment of eligible patients, assessing protocol feasibility, and ensuring efficient trial execution. These issues are compounded by small, age-stratified populations and fragmented clinical data. Real-world data (RWD), especially when drawn from electronic health records (EHRs), present an opportunity to support innovative trial designs, such as real-world comparator arms and postmarketing surveillance. However, realizing this potential depends on the routine availability of structured, reusable clinical data. Objective: This proof-of-concept study aimed to assess the availability and structure of routine clinical data in European pediatric hospitals, focusing on data elements relevant for use in comparator arms and postmarketing surveillance studies. The study focused on 2 disease areas—neurofibromatosis (NF) and atopic dermatitis (AD)—as examples of rare and common conditions in children, respectively. Methods: An inventory of 113 high-value clinical data items was developed based on expert analysis of clinical protocols for NF, AD, and safety studies. These items were included in a structured web-based survey disseminated through the connect4children (c4c) National Hub network, reaching sites across. Europe. Respondents were asked to indicate how each data item is collected and stored: in structured/coded EHR fields, as free text, in external systems, or on paper. Results: Survey responses from 24 hospitals across 11 European countries revealed considerable variability in how data are captured and stored. While many general clinical and drug safety data elements—such as demographics, vital signs, and medication use—were often collected in structured formats, disease-specific and contextual variables were frequently captured as free text or not documented in a standardized way. For example, structured data capture was more prevalent for basic demographic and safety-related variables, whereas only a minority of sites recorded key disease-specific clinical details in a structured form. Lifestyle and family history data were among the least consistently documented. These gaps in structured data entry reduce the immediate reusability of EHR data for secondary research purposes. Conclusions: This study highlights gaps in the structured documentation of pediatric clinical data across European sites. While the routine collection of many variables is promising, the lack of structured and coded formats poses a barrier to reusing these data for observational studies or comparator arms. As a first step toward the broader integration of RWD into pediatric research, this study demonstrates the feasibility of assessing EHR data availability and sets the stage for future scaling across more diseases and sites.

20 December 2024 in JMIR Medical Informatics
Verified
Journal Article
Open access
JDJens Declerck
Jens Declerck
BVBert Vandenberk
Bert Vandenberk
MDMieke Deschepper
Mieke Deschepper
KCKirsten Colpaert
Kirsten Colpaert
LCLieselot Cool
Lieselot Cool
PCPascal Coorevits
Pascal Coorevits
Background: Data quality is fundamental to maintaining the trust and reliability of health data for both primary and secondary purposes. However, before the secondary use of health data, it is essential to assess the quality at the source and to develop systematic methods for the assessment of important data quality dimensions. Objective: This case study aims to offer a dual aim—to assess the data quality of height and weight measurements across 7 Belgian hospitals, focusing on the dimensions of completeness and consistency, and to outline the obstacles these hospitals face in sharing and improving data quality standards. Methods: Focusing on data quality dimensions completeness and consistency, this study examined height and weight data collected from 2021 to 2022 within 3 distinct departments—surgical, geriatrics, and pediatrics—in each of the 7 hospitals. Results: Variability was observed in the completeness scores for height across hospitals and departments, especially within surgical and geriatric wards. In contrast, weight data uniformly achieved high completeness scores. Notably, the consistency of height and weight data recording was uniformly high across all departments. Conclusions: A collective collaboration among Belgian hospitals, transcending network affiliations, was formed to conduct this data quality assessment. This study demonstrates the potential for improving data quality across health care organizations by sharing knowledge and good practices, establishing a foundation for future, similar research.

1 September 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
JDJens Declerck
Jens Declerck
DKDipak Kalra
Dipak Kalra
AAAntti Airola
Antti Airola
AYAhmed Youssef
Ahmed Youssef
Christos ChatzichristosChristos Chatzichristos
Christos Chatzichristos
CMChristophe Maes
Christophe Maes
Synthetic data generation (SDG) structured health data is increasingly promoted as a solution to longstanding barriers in health data access. It is offering the promise of privacy-preserving data reuse for research, innovation, and policy. Despite rapid technical advances, the adoption of synthetic health data in real-world settings remains limited. Shaped by challenges around data quality, representativeness, infrastructure readiness, trust, and legal uncertainty, this viewpoint draws on experiences from 7 European research initiatives within the HealthData4EU cluster to reflect on how SDG is being operationalized in practice. It synthesizes cross-project insights to highlight recurring methodological and governance tensions and to examine their implications for trust and responsible use. The analysis argues that trustworthy SDG cannot be achieved through technical optimization alone but requires alignment between evaluation practices, upstream data stewardship, regulatory clarity, and sustained stakeholder engagement. Addressing these conditions is essential for moving synthetic data from experimental pilots toward a credible and sustainable component of European health research ecosystems.

6 July 2026 in Journal of Medical Internet Research
Verified
Journal Article
Open access
JDJens Declerck
Jens Declerck
NENiina Eklund
Niina Eklund
CSCarlos Sáez
Carlos Sáez
PRPeter Rijnbeek
Peter Rijnbeek
EBEnrique Bernal-Delgado
Enrique Bernal-Delgado
DKDipak Kalra
Dipak Kalra
Background: The secondary use of health data is accelerating across Europe driven by growing demand for data-enabled research, innovation, and policymaking. The European Health Data Space (EHDS) establishes a regulatory framework to support this ecosystem, including Article 78, which mandates a data quality and utility labeling mechanism for datasets intended for reuse. Implementing this framework requires that data holders, data users, and health data access bodies possess sufficient skills, training, and organizational capacity to assess, document, and communicate data quality. However, little empirical evidence exists on whether European health data stakeholders currently possess these capabilities or how their needs differ across the 3 EHDS-defined roles. Objective: This study aimed to identify current skill gaps, training needs, and organizational readiness related to health data quality among European health data stakeholders within the context of the EHDS. Methods: A cross-sectional online survey was conducted between March 2024 and April 2024 using convenience sampling through the QUANTUM (Quality, Utility, and Maturity Measured; Developing a Data Quality and Utility Label for the European Health Data Space) consortium network, professional mailing lists, and health data communities. The survey targeted individuals involved in the secondary use of health data who identified as data holders, data users, or health data access bodies. The survey assessed 5 domains: stakeholder roles and data interaction, individual skills and experience, perceived challenges and skill gaps, organizational support and tools, and learning needs and preferences. Overall, 64 responses were collected from participants representing 44 institutions across 18 European countries. Results: Overall, 82.8% (53/64; 95% CI 71.8%-90.1%) of respondents interacted with health data at least weekly, and 84.4% (54/64; 95% CI 73.6%-91.3%) rated data quality as moderately to absolutely critical for their work. Despite this, 87.5% (56/64; 95% CI 77.2%-93.8%) reported that poor data quality limited their effectiveness, with missing or inconsistent data identified as the most prevalent challenge. While 79.7% (51/64; 95% CI 67.4%-88.3%) reported prior experience with data quality tasks, key skill gaps were identified in applying data quality metrics, auditing and reporting, and metadata management. At the organizational level, only 15.6% (10/64; 95% CI 8.7%-26.6%) reported clearly defined data quality roles, and 68.8% (44/64; 95% CI 56.6%-78.8%) lacked a dedicated data quality manager or team. Conclusions: This study provides an empirical assessment of data quality skills and organizational readiness across the 3 EHDS-defined stakeholder groups. The findings highlight that practical experience alone does not ensure data quality competence and that structural deficits, particularly unclear roles and limited governance, constrain effective data quality management. The results offer a role-specific, evidence-based road map for capacity-building efforts essential to the successful implementation of the EHDS Article 78 data quality and utility labeling framework. This evidence underscores the urgent need for coordinated capacity building to ensure successful EHDS data quality implementation.