Gökhan Ertaylan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Gökhan Ertaylan has a total of 249 co-authors. Here are the top co-authors by number of shared publications:
- Murih Pusparum
Environmental Intelligence, Flemish Institute for Technological Research (VITO), Mol, Belgium
10 shared publications - Olivier Thas
Data Science Institute, I-BioStat, Hasselt University, Hasselt, Belgium
6 shared publications - Antonio del Sol
Computational Biology Group, CIC bioGUNE-BRTA (Basque Research and Technology Alliance), Bizkaia Technology Park, Derio, Spain
3 shared publications - Dirk Valkenborg
Data Science Institute, Hasselt University, Hasselt, Belgium
3 shared publications - Dries Heylen
Affiliations Environmental intelligence Unit, Flemish Institute for Technological Research (VITO), Mol, Belgium, Theory lab, Data Science Institute (DSI), CENSTAT, Hasselt University, Diepenbeek, Belgium
3 shared publications - Ilja C. W. Arts
Maastricht University
3 shared publications
Latest Publications
- Open Access
Pharmacolibrary: Interoperable executable models for PK, PD and PGx derived from published evidence
Published pharmacological knowledge is distributed across heterogeneous scientific literature, databases, and computational models, making systematic reuse, comparison, and reproducibility difficult. We present Pharmacolibrary v26.11, a source-traceable resource that connects pharmacokinetic (PK), pharmacodynamic (PD), and pharmacogenomic (PGx) knowledge with executable models, simulations, and interactive visualizations. A multi-agent workflow combines LLM-assisted literature retrieval and extraction with deterministic validation, ontology mapping, provenance tracking, automated model generation, and rule-based review. The system transforms published evidence and extracted parameters into executable models across Modelica, FMI, SBML, MATLAB, and CellML and provides browser-based simulations for research and education. Preliminary evaluation indicates that decomposing literature extraction into multiple stages improves parameter recovery compared with single-pass extraction and that locally deployed open-weight models can provide performance that is at least comparable with frontier commercial LLMs. Pharmacolibrary provides a foundation for scalable, auditable curation of pharmacological knowledge and for connecting published evidence to reusable computational models across research, simulation, and education.
Open AccessPharmacolibrary: Interoperable executable models for PK, PD and PGx derived from published evidence
Published pharmacological knowledge is distributed across heterogeneous scientific literature, databases, and computational models, making systematic reuse, comparison, and reproducibility difficult. We present Pharmacolibrary v26.11, a source-traceable resource that connects pharmacokinetic (PK), pharmacodynamic (PD), and pharmacogenomic (PGx) knowledge with executable models, simulations, and interactive visualizations. A multi-agent workflow combines LLM-assisted literature retrieval and extraction with deterministic validation, ontology mapping, provenance tracking, automated model generation, and rule-based review. The system transforms published evidence and extracted parameters into executable models across Modelica, FMI, SBML, MATLAB, and CellML and provides browser-based simulations for research and education. Preliminary evaluation indicates that decomposing literature extraction into multiple stages improves parameter recovery compared with single-pass extraction and that locally deployed open-weight models can provide performance that is at least comparable with frontier commercial LLMs. Pharmacolibrary provides a foundation for scalable, auditable curation of pharmacological knowledge and for connecting published evidence to reusable computational models across research, simulation, and education.
- 5 October 2026
- Published by Elsevier in Drug Discovery Today
- Vol. 31 (6)
Regulatory sandboxes for drug development: from uncertainty to structured evidence generation
- 5 October 2026
- Published by Elsevier in Drug Discovery Today
- Vol. 31 (6)
Regulatory sandboxes for drug development: from uncertainty to structured evidence generation
- Open Access
- 2 October 2026
- Published by Wiley in Clinical Pharmacology & Therapeutics
Toward the Use of Real‐World Data for Regulatory and HTA Decision‐Making: Experiences and Recommendations from Six EU ‐Funded Projects
Real‐world data are increasingly important for regulatory and health technology assessment decision‐making, yet their effective use across Europe remains limited by technical, methodological, regulatory, and societal challenges. Drawing on the experiences of six Horizon Europe projects in the MetReal cluster, this review summarizes common barriers and emerging solutions for the use of real‐world data in regulatory decision‐making. Key challenges include complex and lengthy data access procedures, fragmented governance frameworks, variable data quality and completeness, limited interoperability, methodological difficulties in analyzing heterogeneous datasets, and infrastructure constraints within secure data environments. The article highlights opportunities to address these barriers through improved metadata, harmonization, federated analytics, synthetic data sandboxes, sustainable funding, and stronger collaboration between researchers, regulators, health technology assessment bodies, data holders, and citizens. These recommendations aim to strengthen Europe's health data ecosystem and support more robust, efficient, and trusted evidence generation for public health and patient benefit.
- 2 October 2026
- Published by Wiley in Clinical Pharmacology & Therapeutics
Open AccessToward the Use of Real‐World Data for Regulatory and HTA Decision‐Making: Experiences and Recommendations from Six EU ‐Funded Projects
Real‐world data are increasingly important for regulatory and health technology assessment decision‐making, yet their effective use across Europe remains limited by technical, methodological, regulatory, and societal challenges. Drawing on the experiences of six Horizon Europe projects in the MetReal cluster, this review summarizes common barriers and emerging solutions for the use of real‐world data in regulatory decision‐making. Key challenges include complex and lengthy data access procedures, fragmented governance frameworks, variable data quality and completeness, limited interoperability, methodological difficulties in analyzing heterogeneous datasets, and infrastructure constraints within secure data environments. The article highlights opportunities to address these barriers through improved metadata, harmonization, federated analytics, synthetic data sandboxes, sustainable funding, and stronger collaboration between researchers, regulators, health technology assessment bodies, data holders, and citizens. These recommendations aim to strengthen Europe's health data ecosystem and support more robust, efficient, and trusted evidence generation for public health and patient benefit.
- Open Access
- 18 September 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Patient Care Advocate for Selectively Proactive Information Support During Clinical Consultations: Conceptual Framework (Preprint)
UNSTRUCTURED During consultations, clinicians must make decisions while relevant patient history, preferences, medical evidence, and outputs from a growing range of decision-support technologies remain dispersed across sources and difficult to integrate when needed. The challenge is not only information availability, but identifying what is relevant to the evolving discussion and introducing it at the appropriate moment without creating unnecessary distraction. This Viewpoint introduces PCAdvocate as a patient-oriented information-support role and proposes a design pattern governed by the principle of selective proactivity. To realize this principle, we define five core capabilities of PCAdvocate as its functional requirements–consultation awareness, longitudinal patient-context access, information-need detection, targeted information seeking, and relevance judgment and calibrated information delivery–and integrate them into a functional framework showing how they work together. We then illustrate this against existing clinical technologies, finding individual capabilities are variably supported across technology classes, but none integrates all five within a system. Finally, we illustrate how the framework could be operationalized through system configuration and use-case scenario, and outline strategies for evaluating future PCAdvocate systems.
- 18 September 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessPatient Care Advocate for Selectively Proactive Information Support During Clinical Consultations: Conceptual Framework (Preprint)
UNSTRUCTURED During consultations, clinicians must make decisions while relevant patient history, preferences, medical evidence, and outputs from a growing range of decision-support technologies remain dispersed across sources and difficult to integrate when needed. The challenge is not only information availability, but identifying what is relevant to the evolving discussion and introducing it at the appropriate moment without creating unnecessary distraction. This Viewpoint introduces PCAdvocate as a patient-oriented information-support role and proposes a design pattern governed by the principle of selective proactivity. To realize this principle, we define five core capabilities of PCAdvocate as its functional requirements–consultation awareness, longitudinal patient-context access, information-need detection, targeted information seeking, and relevance judgment and calibrated information delivery–and integrate them into a functional framework showing how they work together. We then illustrate this against existing clinical technologies, finding individual capabilities are variably supported across technology classes, but none integrates all five within a system. Finally, we illustrate how the framework could be operationalized through system configuration and use-case scenario, and outline strategies for evaluating future PCAdvocate systems.
- Open Access
Modeling Joint Reference Regions for Omics Biomarkers in UK Biobank Proteomics
Conventional univariate reference intervals (UniRIs) are widely used to identify abnormal biomarker values, but they evaluate each biomarker independently and do not account for coordinated deviations between biomarkers. We developed and evaluated a joint reference region (JRR) framework for plasma proteomics data using the Olink proteomics dataset generated by the UK Biobank Pharma Proteomics Project, covering approximately 3,000 plasma proteins. JRRs were estimated for selected protein pairs in a healthy reference subset, while UniRIs were estimated separately for individual proteins using the nonparametric method. Both approaches were then evaluated in ICD-defined disease subsets. Biomarker discovery revealed sparse and heterogeneous disease–protein associations, with some proteins recurring across multiple phenotypes and others showing more disease-specific patterns. The added value of JRRs varied across diseases and protein pairs. Across evaluated protein pairs, 56.5% showed higher sensitivity under the JRR framework than the UniRI of the first protein, and 47.3% showed higher sensitivity than the UniRI of the second protein. At the disease level, the median proportion of protein pairs with improved JRR sensitivity was 0.57. JRRs were most informative when univariate detection was limited but a subset of diseased observations was flagged only by the joint region. These findings suggest that JRRs provide a complementary approach to UniRIs by capturing abnormal joint biomarker configurations in high-dimensional proteomics data.
Open AccessModeling Joint Reference Regions for Omics Biomarkers in UK Biobank Proteomics
Conventional univariate reference intervals (UniRIs) are widely used to identify abnormal biomarker values, but they evaluate each biomarker independently and do not account for coordinated deviations between biomarkers. We developed and evaluated a joint reference region (JRR) framework for plasma proteomics data using the Olink proteomics dataset generated by the UK Biobank Pharma Proteomics Project, covering approximately 3,000 plasma proteins. JRRs were estimated for selected protein pairs in a healthy reference subset, while UniRIs were estimated separately for individual proteins using the nonparametric method. Both approaches were then evaluated in ICD-defined disease subsets. Biomarker discovery revealed sparse and heterogeneous disease–protein associations, with some proteins recurring across multiple phenotypes and others showing more disease-specific patterns. The added value of JRRs varied across diseases and protein pairs. Across evaluated protein pairs, 56.5% showed higher sensitivity under the JRR framework than the UniRI of the first protein, and 47.3% showed higher sensitivity than the UniRI of the second protein. At the disease level, the median proportion of protein pairs with improved JRR sensitivity was 0.57. JRRs were most informative when univariate detection was limited but a subset of diseased observations was flagged only by the joint region. These findings suggest that JRRs provide a complementary approach to UniRIs by capturing abnormal joint biomarker configurations in high-dimensional proteomics data.
- Open Access
- 19 August 2026
- Published by Oxford University Press (OUP) in Journal of the American Medical Informatics Association
- Vol. 33 (10) , 1921-1933
SMART: structured, meaningful, auditable, responsible, and transparent documentation for clinical AI
Objective: Clinical AI systems and models increasingly need traceable documentation that makes intended use, performance evidence, transparency, and lifecycle status explicit, yet existing model cards, datasheets, reporting guidelines, and other documentation approaches do not consistently bring together structured clinical fields, vocabulary-linked cohort descriptions, structured performance reporting, and governed documentation history. We introduce Structured, Meaningful, Auditable, Responsible, and Transparent (SMART), a framework that adapts the model card concept into structured, lifecycle-aware documentation with OMOP integration, role-based lifecycle governance, and a blockchain-backed audit trail for verifying documentation integrity and lifecycle history. Materials and Methods: Following a design-science-informed approach, we analyzed documentation requirements, reviewed existing approaches, implemented SMART through open-source packages and smart contracts, and evaluated it using example SMART model cards, an illustrative COPD exacerbation risk-prediction documentation case study, and blockchain-governed lifecycle experiments. Results: The design process resulted in the SMART framework in which documentation provisions are reflected across Schema, Lifecycle, and Chain (ie, Blockchain) components. Evaluation showed that, in multi-party settings, documentation history remains independently verifiable because lifecycle actions are role-attributed and linked to content hashes; median testnet gas use ranged from 352 722 to 852 399 gas across the evaluated lifecycle operations. Discussion: SMART positions clinical AI documentation as a shared infrastructure for preliminary model assessment, making role attribution, lifecycle state, and documentation changes more transparent and traceable over time. Conclusion: By providing an implementable framework, SMART illustrates how clinical AI documentation can be structured, clinically contextualized, auditable, responsible, transparent, and lifecycle-aware.
- 19 August 2026
- Published by Oxford University Press (OUP) in Journal of the American Medical Informatics Association
- Vol. 33 (10) , 1921-1933
Open AccessSMART: structured, meaningful, auditable, responsible, and transparent documentation for clinical AI
Objective: Clinical AI systems and models increasingly need traceable documentation that makes intended use, performance evidence, transparency, and lifecycle status explicit, yet existing model cards, datasheets, reporting guidelines, and other documentation approaches do not consistently bring together structured clinical fields, vocabulary-linked cohort descriptions, structured performance reporting, and governed documentation history. We introduce Structured, Meaningful, Auditable, Responsible, and Transparent (SMART), a framework that adapts the model card concept into structured, lifecycle-aware documentation with OMOP integration, role-based lifecycle governance, and a blockchain-backed audit trail for verifying documentation integrity and lifecycle history. Materials and Methods: Following a design-science-informed approach, we analyzed documentation requirements, reviewed existing approaches, implemented SMART through open-source packages and smart contracts, and evaluated it using example SMART model cards, an illustrative COPD exacerbation risk-prediction documentation case study, and blockchain-governed lifecycle experiments. Results: The design process resulted in the SMART framework in which documentation provisions are reflected across Schema, Lifecycle, and Chain (ie, Blockchain) components. Evaluation showed that, in multi-party settings, documentation history remains independently verifiable because lifecycle actions are role-attributed and linked to content hashes; median testnet gas use ranged from 352 722 to 852 399 gas across the evaluated lifecycle operations. Discussion: SMART positions clinical AI documentation as a shared infrastructure for preliminary model assessment, making role attribution, lifecycle state, and documentation changes more transparent and traceable over time. Conclusion: By providing an implementable framework, SMART illustrates how clinical AI documentation can be structured, clinically contextualized, auditable, responsible, transparent, and lifecycle-aware.
- Open Access
- 21 August 2025
- Published by Springer Nature in npj Digital Medicine
- Vol. 8 (1) , 1-13
From ageing clocks to human digital twins in personalising healthcare through biological age analysis
Age is the most important risk factor for the majority human diseases, leading to the exploration of innovative approaches, including the development of predictors to estimate biological age (BA). These predictors offer promising insights into the ageing process and age-related diseases. With real-time, multi-modal data streams and continuous patient monitoring, these BA can also inform the construction of ‘human digital twins’, quantifying how age-related changes impact health trajectories. This study highlights the significance of BA within a deeply phenotyped longitudinal cohort, using omics-based approaches alongside gold-standard clinical risk predictors. BA and health traits predictions were computed from 29 epigenetics, 4 clinical-biochemistry, 2 proteomics, and 3 metabolomics clocks. The study reveals that ageing is different between individuals but relatively stable within individuals. We suggest that BA should be considered crucial biomarkers complementing routine clinical tests. Regular updates of BA predictions within digital twin frameworks can also help guiding individualised treatment plans.
- 21 August 2025
- Published by Springer Nature in npj Digital Medicine
- Vol. 8 (1) , 1-13
Open AccessFrom ageing clocks to human digital twins in personalising healthcare through biological age analysis
Age is the most important risk factor for the majority human diseases, leading to the exploration of innovative approaches, including the development of predictors to estimate biological age (BA). These predictors offer promising insights into the ageing process and age-related diseases. With real-time, multi-modal data streams and continuous patient monitoring, these BA can also inform the construction of ‘human digital twins’, quantifying how age-related changes impact health trajectories. This study highlights the significance of BA within a deeply phenotyped longitudinal cohort, using omics-based approaches alongside gold-standard clinical risk predictors. BA and health traits predictions were computed from 29 epigenetics, 4 clinical-biochemistry, 2 proteomics, and 3 metabolomics clocks. The study reveals that ageing is different between individuals but relatively stable within individuals. We suggest that BA should be considered crucial biomarkers complementing routine clinical tests. Regular updates of BA predictions within digital twin frameworks can also help guiding individualised treatment plans.
- Open Access
- 12 June 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (6) , e0326024
Cohort profile: The Belgian I AM frontier prospective cohort study for comprehensive health outcome exploration
Objectives: The I AM Frontier cohort was set up to support proof-of-concepts aimed at personalized prevention and health promotion. The study was designed to identify patterns, markers and processes involved in the spectrum between health and early disease onset, with the aim of generating actionable insights in a clinical setting. Study design: A prospective cohort study. The study was approved by the ethics committee of the Antwerp University Hospital (RegN°: B300201938600). Methods: Data collection in the I AM Frontier study spanned 12 months as a longitudinal small-scale cohort study (n = 30) conducted in the Antwerp region of Flanders, Belgium. Participants were employees of the company hosting the study, who did not have a clinical diagnosis and were between 45–60 years old. Results: Even though no severe health problems were recorded at baseline, participants reported several physical complaints. There was a clear difference in longitudinal variation between clinical and research grade omics types, which might have affected their respective ability to detect intermediate molecular changes that were be linked to phenotype changes. Conclusion: By integrating findings from the IAF cohort into a large-scale cohort on personalized prevention, and incorporating new technologies for microsample data collection and participant engagement, we can develop more precise and individualized health recommendations.
- 12 June 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (6) , e0326024
Open AccessCohort profile: The Belgian I AM frontier prospective cohort study for comprehensive health outcome exploration
Objectives: The I AM Frontier cohort was set up to support proof-of-concepts aimed at personalized prevention and health promotion. The study was designed to identify patterns, markers and processes involved in the spectrum between health and early disease onset, with the aim of generating actionable insights in a clinical setting. Study design: A prospective cohort study. The study was approved by the ethics committee of the Antwerp University Hospital (RegN°: B300201938600). Methods: Data collection in the I AM Frontier study spanned 12 months as a longitudinal small-scale cohort study (n = 30) conducted in the Antwerp region of Flanders, Belgium. Participants were employees of the company hosting the study, who did not have a clinical diagnosis and were between 45–60 years old. Results: Even though no severe health problems were recorded at baseline, participants reported several physical complaints. There was a clear difference in longitudinal variation between clinical and research grade omics types, which might have affected their respective ability to detect intermediate molecular changes that were be linked to phenotype changes. Conclusion: By integrating findings from the IAF cohort into a large-scale cohort on personalized prevention, and incorporating new technologies for microsample data collection and participant engagement, we can develop more precise and individualized health recommendations.
- Open Access
- 25 March 2025
- Published by Springer Nature in Archives of Public Health
- Vol. 83 (1) , 1-15
Language as a barrier to colorectal cancer screening in Flanders: an ecological study
Background: Despite its potential with regard to the prevention and early detection of colorectal cancer (CRC), participation in the organized CRC screening programme of the Belgian region of Flanders is suboptimal. The role of language discordance as a determinant of screening participation in Europe is poorly understood, despite being identified as a potential barrier in qualitative and non-European studies. Methods: In an ecological study analysing data on the level of Flemish municipalities (n = 300) from 2016 to 2021, we investigated whether the proportion of non-Dutch speakers at home is correlated with the response rate to CRC screening programme invitations and/or the total CRC screening coverage using multiple linear regression. We also performed Kruskal-Wallis tests and Dunn’s tests to examine municipal differences in screening based on their adjacency to the regions of Brussels and Wallonia. Results: After adjusting for confounders, the proportion of secondary school pupils that primarily speak a language other than Dutch at home was associated with a lower screening response rate (β = -0.327, 95% CI -0.359; -0.296)) and lower total screening coverage (β = -0.195, 95% CI -0.219; -0.171). Response rates and coverage were higher in municipalities at least two municipalities away from the border with Wallonia, Brussels or France. Our findings suggest that a high proportion of French speakers is particularly indicative of linguistic barriers to screening in Flemish municipalities (β = -0.358, 95% CI -0.397; -0.319 for response rate and β = -0.213, 95% CI -0.238; -0.188 for total coverage). Conclusion: Our study highlights the need to consider potential linguistic challenges when optimizing CRC screening policies.
- 25 March 2025
- Published by Springer Nature in Archives of Public Health
- Vol. 83 (1) , 1-15
Open AccessLanguage as a barrier to colorectal cancer screening in Flanders: an ecological study
Background: Despite its potential with regard to the prevention and early detection of colorectal cancer (CRC), participation in the organized CRC screening programme of the Belgian region of Flanders is suboptimal. The role of language discordance as a determinant of screening participation in Europe is poorly understood, despite being identified as a potential barrier in qualitative and non-European studies. Methods: In an ecological study analysing data on the level of Flemish municipalities (n = 300) from 2016 to 2021, we investigated whether the proportion of non-Dutch speakers at home is correlated with the response rate to CRC screening programme invitations and/or the total CRC screening coverage using multiple linear regression. We also performed Kruskal-Wallis tests and Dunn’s tests to examine municipal differences in screening based on their adjacency to the regions of Brussels and Wallonia. Results: After adjusting for confounders, the proportion of secondary school pupils that primarily speak a language other than Dutch at home was associated with a lower screening response rate (β = -0.327, 95% CI -0.359; -0.296)) and lower total screening coverage (β = -0.195, 95% CI -0.219; -0.171). Response rates and coverage were higher in municipalities at least two municipalities away from the border with Wallonia, Brussels or France. Our findings suggest that a high proportion of French speakers is particularly indicative of linguistic barriers to screening in Flemish municipalities (β = -0.358, 95% CI -0.397; -0.319 for response rate and β = -0.213, 95% CI -0.238; -0.188 for total coverage). Conclusion: Our study highlights the need to consider potential linguistic challenges when optimizing CRC screening policies.
- Open Access
- 22 November 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (1)
Synthetic plasma pool cohort correction for affinity-based proteomics datasets allows multiple study comparison
Proteomics stands as the crucial link between genomics and human diseases. Quantitative proteomics provides detailed insights into protein levels, enabling differentiation between distinct phenotypes. OLINK, a biotechnology company from Uppsala, Sweden, offers a targeted, affinity-based protein measurement method called Target 96, which has become prominent in the field of proteomics. The SCALLOP consortium, for instance, contains data from over 70.000 individuals across 45 independent cohort studies, all sampled by OLINK. However, when independent cohorts want to collaborate and quantitatively compare their target 96 protein values, it is currently advised to include 'identical biological bridging' samples in each sampling run to perform a reference sample normalization, correcting technical variations across measurements. Such a ‘biological bridging sample’ approach requires each of the involved cohorts to resend their biological bridging samples to OLINK to run them all together, which is logistically challenging, costly and time-consuming. Hence alternatives are searched and an evaluation of the current state of the art exposes the need for a more robust method that allows all OLINK Target 96 studies to compare proteomics data accurately and cost-efficiently. To meet these goals we developed the Synthetic Plasma Pool Cohort Correction, the ‘SPOC correction’ approach, based on the use of an OLINK-composed synthetic plasma sample. The method can easily be implemented in a federated data-sharing context which is illustrated on a sepsis use case.
- 22 November 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (1)
Open AccessSynthetic plasma pool cohort correction for affinity-based proteomics datasets allows multiple study comparison
Proteomics stands as the crucial link between genomics and human diseases. Quantitative proteomics provides detailed insights into protein levels, enabling differentiation between distinct phenotypes. OLINK, a biotechnology company from Uppsala, Sweden, offers a targeted, affinity-based protein measurement method called Target 96, which has become prominent in the field of proteomics. The SCALLOP consortium, for instance, contains data from over 70.000 individuals across 45 independent cohort studies, all sampled by OLINK. However, when independent cohorts want to collaborate and quantitatively compare their target 96 protein values, it is currently advised to include 'identical biological bridging' samples in each sampling run to perform a reference sample normalization, correcting technical variations across measurements. Such a ‘biological bridging sample’ approach requires each of the involved cohorts to resend their biological bridging samples to OLINK to run them all together, which is logistically challenging, costly and time-consuming. Hence alternatives are searched and an evaluation of the current state of the art exposes the need for a more robust method that allows all OLINK Target 96 studies to compare proteomics data accurately and cost-efficiently. To meet these goals we developed the Synthetic Plasma Pool Cohort Correction, the ‘SPOC correction’ approach, based on the use of an OLINK-composed synthetic plasma sample. The method can easily be implemented in a federated data-sharing context which is illustrated on a sepsis use case.