Remove obstacles to sharing health data with researchers outside of the European Union

Essential data variables for a minimum dataset for head and neck cancer trials and clinical research: HNCIG consensus recommendations and database

The Head and Neck Cancer International Group (HNCIG) has undertaken an international modified Delphi process to reach consensus on the essential data variables to be included in a minimum database for HNC research. Endorsed by 19 research organisations representing 34 countries, these recommendations provide the framework to facilitate and harmonise data collection and sharing for HNC research. These variables have also been incorporated into a ready to use downloadable HNCIG minimum database, available from the HNCIG website.

Best practices for multimodal clinical data management and integration: An atopic dermatitis research case

BACKGROUND

In clinical research on multifactorial diseases such as atopic dermatitis, data-driven medical research has become more widely used as means to clarify diverse pathological conditions and to realize precision medicine. However, modern clinical data, characterized as large-scale, multimodal, and multi-center, causes difficulties in data integration and management, which limits productivity in clinical data science.

METHODS

We designed a generic data management flow to collect, cleanse, and integrate data to handle different types of data generated at multiple institutions by 10 types of clinical studies. We developed MeDIA (Medical Data Integration Assistant), a software to browse the data in an integrated manner and extract subsets for analysis.

RESULTS

MeDIA integrates and visualizes data and information on research participants obtained from multiple studies. It then provides a sophisticated interface that supports data management and helps data scientists retrieve the data sets they need. Furthermore, the system promotes the use of unified terms such as identifiers or sampling dates to reduce the cost of pre-processing by data analysts. We also propose best practices in clinical data management flow, which we learned from the development and implementation of MeDIA.

CONCLUSIONS

The MeDIA system solves the problem of multimodal clinical data integration, from complex text data such as medical records to big data such as omics data from a large number of patients. The system and the proposed best practices can be applied not only to allergic diseases but also to other diseases to promote data-driven medical research.

Enriching Data Science and Health Care Education: Application and Impact of Synthetic Data Sets Through the Health Gym Project

Large-scale medical data sets are vital for hands-on education in health data science but are often inaccessible due to privacy concerns. Addressing this gap, we developed the Health Gym project, a free and open-source platform designed to generate synthetic health data sets applicable to various areas of data science education, including machine learning, data visualization, and traditional statistical models. Initially, we generated 3 synthetic data sets for sepsis, acute hypotension, and antiretroviral therapy for HIV infection. This paper discusses the educational applications of Health Gym's synthetic data sets. We illustrate this through their use in postgraduate health data science courses delivered by the University of New South Wales, Australia, and a Datathon event, involving academics, students, clinicians, and local health district professionals. We also include adaptable worked examples using our synthetic data sets, designed to enrich hands-on tutorial and workshop experiences. Although we highlight the potential of these data sets in advancing data science education and health care artificial intelligence, we also emphasize the need for continued research into the inherent limitations of synthetic data.

An innovative technological infrastructure for managing SARS-CoV-2 data across different cohorts in compliance with General Data Protection Regulation

Background

The ORCHESTRA project, funded by the European Commission, aims to create a pan-European cohort built on existing and new large-scale population cohorts to help rapidly advance the knowledge related to the prevention of the SARS-CoV-2 infection and the management of COVID-19 and its long-term sequelae. The integration and analysis of the very heterogeneous health data pose the challenge of building an innovative technological infrastructure as the foundation of a dedicated framework for data management that should address the regulatory requirements such as the General Data Protection Regulation (GDPR).

Methods

The three participating Supercomputing European Centres (CINECA - Italy, CINES - France and HLRS - Germany) designed and deployed a dedicated infrastructure to fulfil the functional requirements for data management to ensure sensitive biomedical data confidentiality/privacy, integrity, and security. Besides the technological issues, many methodological aspects have been considered: Berlin Institute of Health (BIH), Charité provided its expertise both for data protection, information security, and data harmonisation/standardisation.

Results

The resulting infrastructure is based on a multi-layer approach that integrates several security measures to ensure data protection. A centralised Data Collection Platform has been established in the Italian National Hub while, for the use cases in which data sharing is not possible due to privacy restrictions, a distributed approach for Federated Analysis has been considered. A Data Portal is available as a centralised point of access for non-sensitive data and results, according to findability, accessibility, interoperability, and reusability (FAIR) data principles. This technological infrastructure has been used to support significative data exchange between population cohorts and to publish important scientific results related to SARS-CoV-2.

Conclusions

Considering the increasing demand for data usage in accordance with the requirements of the GDPR regulations, the experience gained in the project and the infrastructure released for the ORCHESTRA project can act as a model to manage future public health threats. Other projects could benefit from the results achieved by ORCHESTRA by building upon the available standardisation of variables, design of the architecture, and process used for GDPR compliance.

Relay learning: a physically secure framework for clinical multi-site deep learning

Big data serves as the cornerstone for constructing real-world deep learning systems across various domains. In medicine and healthcare, a single clinical site lacks sufficient data, thus necessitating the involvement of multiple sites. Unfortunately, concerns regarding data security and privacy hinder the sharing and reuse of data across sites. Existing approaches to multi-site clinical learning heavily depend on the security of the network firewall and system implementation. To address this issue, we propose Relay Learning, a secure deep-learning framework that physically isolates clinical data from external intruders while still leveraging the benefits of multi-site big data. We demonstrate the efficacy of Relay Learning in three medical tasks of different diseases and anatomical structures, including structure segmentation of retina fundus, mediastinum tumors diagnosis, and brain midline localization. We evaluate Relay Learning by comparing its performance to alternative solutions through multi-site validation and external validation. Incorporating a total of 41,038 medical images from 21 medical hosts, including 7 external hosts, with non-uniform distributions, we observe significant performance improvements with Relay Learning across all three tasks. Specifically, it achieves an average performance increase of 44.4%, 24.2%, and 36.7% for retinal fundus segmentation, mediastinum tumor diagnosis, and brain midline localization, respectively. Remarkably, Relay Learning even outperforms central learning on external test sets. In the meanwhile, Relay Learning keeps data sovereignty locally without cross-site network connections. We anticipate that Relay Learning will revolutionize clinical multi-site collaboration and reshape the landscape of healthcare in the future.

A systematic review of data sources for artificial intelligence applications in pediatric brain tumors in Europe: implications for bias and generalizability

Introduction

Europe works to improve cancer management through the use of artificialintelligence (AI), and there is a need to accelerate the development of AI applications for childhood cancer. However, the current strategies used for algorithm development in childhood cancer may have bias and limited generalizability. This study reviewed existing publications on AI tools for pediatric brain tumors, Europe's most common type of childhood solid tumor, to examine the data sources for developing AI tools.

Methods

We performed a bibliometric analysis of the publications on AI tools for pediatric brain tumors, and we examined the type of data used, data sources, and geographic location of cohorts to evaluate the generalizability of the algorithms.

Results

We screened 10503 publications, and we selected 45. A total of 34/45 publications developing AI tools focused on glial tumors, while 35/45 used MRI as a source of information to predict the classification and prognosis. The median number of patients for algorithm development was 89 for single-center studies and 120 for multicenter studies. A total of 17/45 publications used pediatric datasets from the UK.

Discussion

Since the development of AI tools for pediatric brain tumors is still in its infancy, there is a need to support data exchange and collaboration between centers to increase the number of patients used for algorithm training and improve their generalizability. To this end, there is a need for increased data exchange and collaboration between centers and to explore the applicability of decentralized privacy-preserving technologies consistent with the General Data Protection Regulation (GDPR). This is particularly important in light of using the European Health Data Space and international collaborations.

Overcoming ethical and legal obstacles to data linkage in health research: stakeholder perspectives

Introduction

Data linkage for health research purposes enables the answering of countless new research questions, is said to be cost effective and less intrusive than other means of data collection. Nevertheless, health researchers are currently dealing with a complicated, fragmented, and inconsistent regulatory landscape with regard to the processing of data, and progress in health research is hindered.

Aim

We designed a qualitative study to assess what different stakeholders perceive as ethical and legal obstacles to data linkage for health research purposes, and how these obstacles could be overcome.

Methods

Two focus groups and eighteen semi-structured in-depth interviews were held to collect opinions and insights of various stakeholders. An inductive thematic analysis approach was used to identify overarching themes.

Results

This study showed that the ambiguity regarding the 'correct' interpretation of the law, the fragmentation of policies governing the processing of personal health data, and the demandingness of legal requirements are experienced as causes for the impediment of data linkage for research purposes by the participating stakeholders. To remove or reduce these obstacles authoritative interpretations of the laws and regulations governing data linkage should be issued. The participants furthermore encouraged the harmonisation of data linkage policies, as well as promoting trust and transparency and the enhancement of technical and organisational measures. Lastly, there is a demand for legislative and regulatory modifications amongst the participants.

Conclusions

To overcome the obstacles in data linkage for scientific research purposes, perhaps we should shift the focus from adapting the current laws and regulations governing data linkage, or even designing completely new laws, towards creating a more thorough understanding of the law and making better use of the flexibilities within the existing legislation. Important steps in achieving this shift could be clarification of the legal provisions governing data linkage by issuing authoritative interpretations, as well as the strengthening of ethical-legal oversight bodies.

Overcoming personal information protection challenges involving real-world data to support public health efforts in China

In the information age, real-world data-based evidence can help extrapolate and supplement data from randomized controlled trials, which can benefit clinical trials and drug development and improve public health decision-making. However, the legitimate use of real-world data in China is limited due to concerns over patient confidentiality. The use of personal information is a core element of data governance in public health. In China's public health data governance, practical problems exist, such as balancing personal information protection and public value conflict. In 2021, China adopted the Personal Information Protection Law (PIPL) to provide a consistent legal framework for protecting personal information, including sensitive medical health data. Despite the PIPL offering critical legal safeguards for processing health data, further clarification is needed regarding specific issues, including the meaning of "separate consent," cross-border data transfer requirements, and exceptions for scientific research. A shift in the law and regulatory framework is necessary to advance public health research further and realize the potential benefits of combining real-world evidence and digital health while respecting privacy in the technological and demographic change era.

Accessibility of covariance information creates vulnerability in Federated Learning frameworks

MOTIVATION

Federated Learning (FL) is gaining traction in various fields as it enables integrative data analysis without sharing sensitive data, such as in healthcare. However, the risk of data leakage caused by malicious attacks must be considered. In this study, we introduce a novel attack algorithm that relies on being able to compute sample means, sample covariances, and construct known linearly independent vectors on the data owner side.

RESULTS

We show that these basic functionalities, which are available in several established FL frameworks, are sufficient to reconstruct privacy-protected data. Additionally, the attack algorithm is robust to defense strategies that involve adding random noise. We demonstrate the limitations of existing frameworks and propose potential defense strategies analyzing the implications of using differential privacy. The novel insights presented in this study will aid in the improvement of FL frameworks.

AVAILABILITY AND IMPLEMENTATION

The code examples are provided at GitHub (https://github.com/manuhuth/Data-Leakage-From-Covariances.git). The CNSIM1 dataset, which we used in the manuscript, is available within the DSData R package (https://github.com/datashield/DSData/tree/main/data).

Avoiding Liability and Other Legal Land Mines in the Evolving Genomics Landscape

This article reviews evolving legal implications for clinicians and researchers as genomics is used more widely in both the clinic and in translational research, reflecting rapid changes in scientific knowledge as well as the surrounding cultural and political environment. Professionals will face new and changing duties to make or act upon a genetic diagnosis, address direct-to-consumer genetic testing in patient care, consider the health implications of results for patients' family members, and recontact patients when test results change over time. Professional duties in reproductive genetic testing will need to be recalibrated in response to disruptive changes to reproductive rights in the United States. We also review the debate over who controls the flow of genetic information and who is responsible for its protection, considering the globally influential European Union General Data Protection Regulation and the rapidly evolving data privacy law landscape of the United States.

Generating synthetic clinical data that capture class imbalanced distributions with generative adversarial networks: Example using antiretroviral therapy for HIV

OBJECTIVE

Clinical data's confidential nature often limits the development of machine learning models in healthcare. Generative adversarial networks (GANs) can synthesise realistic datasets, but suffer from mode collapse, resulting in low diversity and bias towards majority demographics and common clinical practices. This work proposes an extension to the classic GAN framework that includes a variational autoencoder (VAE) and an external memory mechanism to overcome these limitations and generate synthetic data accurately describing imbalanced class distributions commonly found in clinical variables.

METHODS

The proposed method generated a synthetic dataset related to antiretroviral therapy for human immunodeficiency virus (ART for HIV). We evaluated it based on five metrics: (1) accurately representing imbalanced class distribution; (2) the realism of the individual variables; (3) the realism among variables; (4) patient disclosure risk; and (5) the utility of the generated dataset for developing downstream machine learning models.

RESULTS

The proposed method overcomes the issue of mode collapse and generates a synthetic dataset that accurately describes imbalanced class distributions commonly found in clinical variables. The generated data has a patient disclosure risk of 0.095%, lower than the 9% threshold stated by Health Canada and the European Medicines Agency, making it suitable for distribution to the research community with high security. The generated data also has high utility, indicating the potential of the proposed method to enable the development of downstream machine learning algorithms for healthcare applications using synthetic data.

CONCLUSION

Our proposed extension to the classic GAN framework, which includes a VAE and an external memory mechanism, represents a promising approach towards generating synthetic data that accurately describe imbalanced class distributions commonly found in clinical variables. This method overcomes the limitations of GANs and creates more realistic datasets with higher patient cohort diversity, facilitating the development of downstream machine learning algorithms for healthcare applications.

A comparison of synthetic data generation and federated analysis for enabling international evaluations of cardiovascular health

Sharing health data for research purposes across international jurisdictions has been a challenge due to privacy concerns. Two privacy enhancing technologies that can enable such sharing are synthetic data generation (SDG) and federated analysis, but their relative strengths and weaknesses have not been evaluated thus far. In this study we compared SDG with federated analysis to enable such international comparative studies. The objective of the analysis was to assess country-level differences in the role of sex on cardiovascular health (CVH) using a pooled dataset of Canadian and Austrian individuals. The Canadian data was synthesized and sent to the Austrian team for analysis. The utility of the pooled (synthetic Canadian + real Austrian) dataset was evaluated by comparing the regression results from the two approaches. The privacy of the Canadian synthetic data was assessed using a membership disclosure test which showed an F1 score of 0.001, indicating low privacy risk. The outcome variable of interest was CVH, calculated through a modified CANHEART index. The main and interaction effect parameter estimates of the federated and pooled analyses were consistent and directionally the same. It took approximately one month to set up the synthetic data generation platform and generate the synthetic data, whereas it took over 1.5 years to set up the federated analysis system. Synthetic data generation can be an efficient and effective tool for enabling multi-jurisdictional studies while addressing privacy concerns.

Synthetic Data Generation by Artificial Intelligence to Accelerate Research and Precision Medicine in Hematology

PURPOSE

Synthetic data are artificial data generated without including any real patient information by an algorithm trained to learn the characteristics of a real source data set and became widely used to accelerate research in life sciences. We aimed to (1) apply generative artificial intelligence to build synthetic data in different hematologic neoplasms; (2) develop a synthetic validation framework to assess data fidelity and privacy preservability; and (3) test the capability of synthetic data to accelerate clinical/translational research in hematology.

METHODS

A conditional generative adversarial network architecture was implemented to generate synthetic data. Use cases were myelodysplastic syndromes (MDS) and AML: 7,133 patients were included. A fully explainable validation framework was created to assess fidelity and privacy preservability of synthetic data.

RESULTS

We generated MDS/AML synthetic cohorts (including information on clinical features, genomics, treatment, and outcomes) with high fidelity and privacy performances. This technology allowed resolution of lack/incomplete information and data augmentation. We then assessed the potential value of synthetic data on accelerating research in hematology. Starting from 944 patients with MDS available since 2014, we generated a 300% augmented synthetic cohort and anticipated the development of molecular classification and molecular scoring system obtained many years later from 2,043 to 2,957 real patients, respectively. Moreover, starting from 187 MDS treated with luspatercept into a clinical trial, we generated a synthetic cohort that recapitulated all the clinical end points of the study. Finally, we developed a website to enable clinicians generating high-quality synthetic data from an existing biobank of real patients.

CONCLUSION

Synthetic data mimic real clinical-genomic features and outcomes, and anonymize patient information. The implementation of this technology allows to increase the scientific use and value of real data, thus accelerating precision medicine in hematology and the conduction of clinical trials.

How to build up big team science: a practical guide for large-scale collaborations

The past decade has witnessed a proliferation of big team science (BTS), endeavours where a comparatively large number of researchers pool their intellectual and/or material resources in pursuit of a common goal. Despite this burgeoning interest, there exists little guidance on how to create, manage and participate in these collaborations. In this paper, we integrate insights from a multi-disciplinary set of BTS initiatives to provide a how-to guide for BTS. We first discuss initial considerations for launching a BTS project, such as building the team, identifying leadership, governance, tools and open science approaches. We then turn to issues related to running and completing a BTS project, such as study design, ethical approvals and issues related to data collection, management and analysis. Finally, we address topics that present special challenges for BTS, including authorship decisions, collaborative writing and team decision-making.

The necessity revealed by COVID-19 pandemic: Paradigm shift of Iran's healthcare system

Background

COVID-19 pandemic has resulted in drastic changes around the world, revealing vulnerable aspects of healthcare systems. This study aimed to explore how Iranian healthcare system experienced the paradigm shift during the pandemic and determine the aspects that need improvement during the pandemic era.

Method

This qualitative study was conducted in 2021. A framework analysis approach was used to analyze the content of the 19 semi-structured interviews with the healthcare system experts from Shiraz University of Medical Sciences (SUMS). The interviews' audio files changed into transcript after each session and data was saturated at the 19 interview. To increase the trustworthiness of the study, Guba and Lincoln's criteria including credibility, transferability, dependability, and confirmability were used. Goldsmith's five-step framework analysis was used applying MAX QDA version 10 software.

Result

Eight main themes and 20 subthemes were explored. The main themes included "strengthening the electronic health infrastructure," "research for evidence-based decision making," "dedicated financing to the pandemic," "prevention of disruption in the effective provision of services and medicines," "enriching the authority of the Ministry of Health by focusing on interactions," "recruiting, managing and empowering health human resources with attention to financial and non-financial incentives," "reforming educational approaches in training students in medical universities," as well as "lessons learned from neglected aspects."

Conclusion

To be ready to respond to a possible future pandemic and for a paradigm shift, bold steps must be taken to make fundamental changes in various aspects of the healthcare system including e-health development, evidence-based decision making, dedicated budgets for pandemics, reinforcement of interactions at the national and international level, as well as sufficient attention to healthcare workers from all financial, non-financial and educational aspects.

Health data privacy through homomorphic encryption and distributed ledger computing: an ethical-legal qualitative expert assessment study

BACKGROUND

Increasingly, hospitals and research institutes are developing technical solutions for sharing patient data in a privacy preserving manner. Two of these technical solutions are homomorphic encryption and distributed ledger technology. Homomorphic encryption allows computations to be performed on data without this data ever being decrypted. Therefore, homomorphic encryption represents a potential solution for conducting feasibility studies on cohorts of sensitive patient data stored in distributed locations. Distributed ledger technology provides a permanent record on all transfers and processing of patient data, allowing data custodians to audit access. A significant portion of the current literature has examined how these technologies might comply with data protection and research ethics frameworks. In the Swiss context, these instruments include the Federal Act on Data Protection and the Human Research Act. There are also institutional frameworks that govern the processing of health related and genetic data at different universities and hospitals. Given Switzerland's geographical proximity to European Union (EU) member states, the General Data Protection Regulation (GDPR) may impose additional obligations.

METHODS

To conduct this assessment, we carried out a series of qualitative interviews with key stakeholders at Swiss hospitals and research institutions. These included legal and clinical data management staff, as well as clinical and research ethics experts. These interviews were carried out with two series of vignettes that focused on data discovery using homomorphic encryption and data erasure from a distributed ledger platform.

RESULTS

For our first set of vignettes, interviewees were prepared to allow data discovery requests if patients had provided general consent or ethics committee approval, depending on the types of data made available. Our interviewees highlighted the importance of protecting against the risk of reidentification given different types of data. For our second set, there was disagreement amongst interviewees on whether they would delete patient data locally, or delete data linked to a ledger with cryptographic hashes. Our interviewees were also willing to delete data locally or on the ledger, subject to local legislation.

CONCLUSION

Our findings can help guide the deployment of these technologies, as well as determine ethics and legal requirements for such technologies.

Challenges and Opportunities for Global Genomic Surveillance Strategies in the COVID-19 Era

Global SARS-CoV-2 genomic surveillance efforts have provided critical data on the ongoing evolution of the virus to inform best practices in clinical care and public health throughout the pandemic. Impactful genomic surveillance strategies generally follow a multi-disciplinary pipeline involving clinical sample collection, viral genotyping, metadata linkage, data reporting, and public health responses. Unfortunately, current limitations in each of these steps have compromised the overall effectiveness of these strategies. Biases from convenience-based sampling methods can obfuscate the true distribution of circulating variants. The lack of standardization in genotyping strategies and bioinformatic expertise can create bottlenecks in data processing and complicate interpretation. Limitations and inconsistencies in clinical and demographic data collection and sharing can slow the compilation and limit the utility of comprehensive datasets. This likewise can complicate data reporting, restricting the availability of timely data. Finally, gaps and delays in the implementation of genomic surveillance data in the public health sphere can prevent officials from formulating effective mitigation strategies to prevent outbreaks. In this review, we outline current SARS-CoV-2 global genomic surveillance methods and assess roadblocks at each step of the pipeline to identify potential solutions. Evaluating the current obstacles that impede effective surveillance can improve both global coordination efforts and pandemic preparedness for future outbreaks.

The human genetic epidemiology of COVID-19

Human genetics can inform the biology and epidemiology of coronavirus disease 2019 (COVID-19) by pinpointing causal mechanisms that explain why some individuals become more severely affected by the disease upon infection by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus. Large-scale genetic association studies, encompassing both rare and common genetic variants, have used different study designs and multiple disease phenotype definitions to identify several genomic regions associated with COVID-19. Along with a multitude of follow-up studies, these findings have increased our understanding of disease aetiology and provided routes for management of COVID-19. Important emergent opportunities include the clinical translatability of genetic risk prediction, the repurposing of existing drugs, exploration of variable host effects of different viral strains, study of inter-individual variability in vaccination response and understanding the long-term consequences of SARS-CoV-2 infection. Beyond the current pandemic, these transferrable opportunities are likely to affect the study of many infectious diseases.

Barriers to Use Artificial Intelligence Methodologies in Health Technology Assessment in Central and East European Countries

The aim of this paper is to identify the barriers that are specifically relevant to the use of Artificial Intelligence (AI)-based evidence in Central and Eastern European (CEE) Health Technology Assessment (HTA) systems. The study relied on two main parallel sources to identify barriers to use AI methodologies in HTA in CEE, including a scoping literature review and iterative focus group meetings with HTx team members. Most of the other selected articles discussed AI from a clinical perspective (n = 25), and the rest are from regulatory perspective (n = 13), and transfer of knowledge point of view (n = 3). Clinical areas studied are quite diverse—from pediatric, diabetes, diagnostic radiology, gynecology, oncology, surgery, psychiatry, cardiology, infection diseases, and oncology. Out of all 38 articles, 25 (66%) describe the AI method and the rest are more focused on the utilization barriers of different health care services and programs. The potential barriers could be classified as data related, methodological, technological, regulatory and policy related, and human factor related. Some of the barriers are quite similar, especially concerning the technologies. Studies focusing on the AI usage for HTA decision making are scarce. AI and augmented decision making tools are a novel science, and we are in the process of adapting it to existing needs. HTA as a process requires multiple steps, multiple evaluations which rely on heterogenous data. Therefore, the observed range of barriers come as a no surprise, and experts in the field need to give their opinion on the most important barriers in order to develop recommendations to overcome them and to disseminate the practical application of these tools.

Exchange of Human Data Across International Boundaries

There is a need to share personal data across jurisdictional boundaries. However, the laws regulating such transfers are not harmonized, and sometimes even conflict, causing challenges and occasional data stalls. This review describes the legal landscape for transfer of human data across international boundaries. The European Union's data protection legislation is used as the starting point for illustrating the legislation of countries across the world, how these diverge, and one's options for exchanging human data internationally in a legally compliant manner. Expected final online publication date for the Annual Review of Biomedical Data Science, Volume 5 is August 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Will the European Health Data Space change data sharing rules?

Questions of consent and public interest research loom large.