Innovative use of data sources: a cross-sectional study of data linkage and artificial intelligence practices across European countries

Haneef, Romana; Delnord, Marie; Vernay, Michel; Bauchet, Emmanuelle; Gaidelyte, Rita; Oyen, Herman Van; Or, Zeynep; Pérez‐Gómez, Beatriz; Palmieri, Luigi; Achterberg, Peter; Tijhuis, Marja; Zaletel, Marjan; Mathis-Edenhofer, Stefan; Májek, Ondřej; Haaheim, Håkon; Tolonen, Hanna; Gallay, Anne

doi:10.1186/s13690-020-00436-9

Cited by 22 publications

(18 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Many countries have already invested in the linkage including both deterministic and probabilistic linkages and linking their traditional health administrative data with other types of data and has increased interoperability [ 2 ]. The capacity to use data linkage and artificial intelligence (AI) to estimate and predict health indicators varies across European countries [ 3 ]. However, the estimation of health indicators from linked administrative data is challenging due to several reasons such as variability in data sources and data collection methods, interoperability issues (legal, organizational, semantic and technical levels), availability of a large number of variables, lack of skills and capacity to link and analyze big data [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

Methodological guidelines to estimate population-based health indicators using linked data and/or machine learning techniques

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background The capacity to use data linkage and artificial intelligence to estimate and predict health indicators varies across European countries. However, the estimation of health indicators from linked administrative data is challenging due to several reasons such as variability in data sources and data collection methods resulting in reduced interoperability at various levels and timeliness, availability of a large number of variables, lack of skills and capacity to link and analyze big data. The main objective of this study is to develop the methodological guidelines calculating population-based health indicators to guide European countries using linked data and/or machine learning (ML) techniques with new methods. Method We have performed the following step-wise approach systematically to develop the methodological guidelines: i. Scientific literature review, ii. Identification of inspiring examples from European countries, and iii. Developing the checklist of guidelines contents. Results We have developed the methodological guidelines, which provide a systematic approach for studies using linked data and/or ML-techniques to produce population-based health indicators. These guidelines include a detailed checklist of the following items: rationale and objective of the study (i.e., research question), study design, linked data sources, study population/sample size, study outcomes, data preparation, data analysis (i.e., statistical techniques, sensitivity analysis and potential issues during data analysis) and study limitations. Conclusions This is the first study to develop the methodological guidelines for studies focused on population health using linked data and/or machine learning techniques. These guidelines would support researchers to adopt and develop a systematic approach for high-quality research methods. There is a need for high-quality research methodologies using more linked data and ML-techniques to develop a structured cross-disciplinary approach for improving the population health information and thereby the population health.

show abstract

Section: Introductionmentioning

confidence: 99%

Methodological guidelines to estimate population-based health indicators using linked data and/or machine learning techniques

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In InfAct, the following health information tools and innovations were developed, piloted and made available to the Health Information Portal, for use in DIPoH: A roadmap of innovative use of data sources, identifying best practices for using health information and methodological guidelines, which could systematically guide EU MS and associated countries (AC) for using linked data and machine learning techniques to estimate health indicators for public health research [ 16 – 18 ]. The development of new composite indicators to improve the monitoring of NCD: the “En-risk” an interactive application tool, which uses European non-health databases of industrial pollution and its association with mortality for public health surveillance, and the ratio between hospital admissions and deaths to explore the geographical variability of morbidity and mortality in a country [ 11 ].…”

Section: Resultsmentioning

confidence: 99%

The InfAct proposal for a sustainable European health information infrastructure on population health: the Distributed Infrastructure on Population Health (DIPoH)

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background In Europe, data on population health is fragmented, difficult to access, project-based and prone to health information inequalities in terms of availability, accessibility and especially in quality between and within countries. This situation is further exacerbated and exposed by the recent COVID-19 pandemic. The Joint Action on Health Information (InfAct) that builds on previous works of the BRIDGE Health project, carried out collaborative action to set up a sustainable infrastructure for health information in the European Union (EU). The aim of this paper is to present InfAct’s proposal for a sustainable research infrastructure, the Distributed Infrastructure on Population Health (DIPoH), which includes the setup of a Health Information Portal on population health to be maintained beyond InfAct’s time span. Methods The strategy for the proposal was based on three components: scientific initiatives and proposals to improve Health Information Systems (HIS), exploration of technical acceptability and feasibility, and finally obtaining high-level political support.. The technical exploration (Technical Dialogues—TD) was assumed by technical experts proposed by the countries, and political guidance was provided by the Assembly of Members (AoM), which gathered representatives from Ministries of Health and Science of EU/EEA countries. The results from the AoM and the TD were integrated in the sustainability plan compiling all the major outputs of InfAct. Results The InfAct sustainability plan was organized in three main sections: a proposal of a new research infrastructure on population health (the DIPoH), new health information tools and innovative proposals for HIS, and a comprehensive capacity building programme. These activities were carried out in InfAct and are being further developed in the Population Health Information Research Infrastructure (PHIRI). PHIRI is a practical rollout of DIPoH facilitating and generating the best available evidence for research on health and wellbeing of populations as impacted by COVID-19. Conclusions The sustainability plan received wide support from Member States and was recognized to have an added value at EU level. Nevertheless, there were several aspects which still need to be considered for the near future such as: (i) a commitment of stable financial and political support by Member States (MSs), (ii) the availability of resources at regional, national and European level to deal with innovations, and (iii) a more direct involvement from EU and international institutions such as the European Centre for Disease Prevention and Control (ECDC), the World Health Organization (WHO) and the Organisation for Economic Cooperation and Development OECD for providing support and sustainable contributions.

show abstract

“…Studies of rare conditions, more than any other disease, need structures for data integration between academia and clinical institutions in order to collect a sufficient number of patients from which patterns can emerge to underpin valid research questions. Success in such a collaborative multi-center approach relies on proper phenotyping with standardized disease classification, unified and reliable data capture, merging of data, analyses processes, and storage methods ( 145 , 146 ). In addition to this, the quality of machine learning outputs and bioinformatics methods strictly depends on the quality and consistency of input data.…”

Section: From Genetic Discoveries To Improved Patient Management In Rare Bone Diseasesmentioning

confidence: 99%

A Roadmap to Gene Discoveries and Novel Therapies in Monogenic Low and High Bone Mass Disorders

et al. 2021

View full text Add to dashboard Cite

Genetic disorders of the skeleton encompass a diverse group of bone diseases differing in clinical characteristics, severity, incidence and molecular etiology. Of particular interest are the monogenic rare bone mass disorders, with the underlying genetic defect contributing to either low or high bone mass phenotype. Extensive, deep phenotyping coupled with high-throughput, cost-effective genotyping is crucial in the characterization and diagnosis of affected individuals. Massive parallel sequencing efforts have been instrumental in the discovery of novel causal genes that merit functional validation using in vitro and ex vivo cell-based techniques, and in vivo models, mainly mice and zebrafish. These translational models also serve as an excellent platform for therapeutic discovery, bridging the gap between basic science research and the clinic. Altogether, genetic studies of monogenic rare bone mass disorders have broadened our knowledge on molecular signaling pathways coordinating bone development and metabolism, disease inheritance patterns, development of new and improved bone biomarkers, and identification of novel drug targets. In this comprehensive review we describe approaches to further enhance the innovative processes taking discoveries from clinic to bench, and then back to clinic in rare bone mass disorders. We highlight the importance of cross laboratory collaboration to perform functional validation in multiple model systems after identification of a novel disease gene. We describe the monogenic forms of rare low and high rare bone mass disorders known to date, provide a roadmap to unravel the genetic determinants of monogenic rare bone mass disorders using proper phenotyping and genotyping methods, and describe different genetic validation approaches paving the way for future treatments.

show abstract

Innovative use of data sources: a cross-sectional study of data linkage and artificial intelligence practices across European countries

Cited by 22 publications

References 27 publications

Methodological guidelines to estimate population-based health indicators using linked data and/or machine learning techniques

Methodological guidelines to estimate population-based health indicators using linked data and/or machine learning techniques

The InfAct proposal for a sustainable European health information infrastructure on population health: the Distributed Infrastructure on Population Health (DIPoH)

A Roadmap to Gene Discoveries and Novel Therapies in Monogenic Low and High Bone Mass Disorders

Contact Info

Product

Resources

About