1
|
Okoniewski MJ, Wiegand A, Schmid DC, Bolliger C, Bovino C, Belluco M, Wüst T, Byrde O, Maffioletti S, Rinn B. Leonhard Med, a trusted research environment for processing sensitive research data. J Integr Bioinform 2024; 0:jib-2024-0021. [PMID: 39092509 DOI: 10.1515/jib-2024-0021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2024] [Accepted: 06/26/2024] [Indexed: 08/04/2024] Open
Abstract
This paper provides an overview of the development and operation of the Leonhard Med Trusted Research Environment (TRE) at ETH Zurich. Leonhard Med gives scientific researchers the ability to securely work on sensitive research data. We give an overview of the user perspective, the legal framework for processing sensitive data, design history, current status, and operations. Leonhard Med is an efficient, highly secure Trusted Research Environment for data processing, hosted at ETH Zurich and operated by the Scientific IT Services (SIS) of ETH. It provides a full stack of security controls that allow researchers to store, access, manage, and process sensitive data according to Swiss legislation and ETH Zurich Data Protection policies. In addition, Leonhard Med fulfills the BioMedIT Information Security Policies and is compatible with international data protection laws and therefore can be utilized within the scope of national and international collaboration research projects. Initially designed as a "bare-metal" High-Performance Computing (HPC) platform to achieve maximum performance, Leonhard Med was later re-designed as a virtualized, private cloud platform to offer more flexibility to its customers. Sensitive data can be analyzed in secure, segregated spaces called tenants. Technical and Organizational Measures (TOMs) are in place to assure the confidentiality, integrity, and availability of sensitive data. At the same time, Leonhard Med ensures broad access to cutting-edge research software, especially for the analysis of human -omics data and other personalized health applications.
Collapse
Affiliation(s)
- Michal J Okoniewski
- SIS Scientific IT Services, ETH Zurich, Binzmühlestrasse 130, 8092 Zurich, Switzerland, https://sis.id.ethz.ch/
| | - Anna Wiegand
- SIS Scientific IT Services, ETH Zurich, Binzmühlestrasse 130, 8092 Zurich, Switzerland, https://sis.id.ethz.ch/
| | - Diana Coman Schmid
- SIS Scientific IT Services, ETH Zurich, Binzmühlestrasse 130, 8092 Zurich, Switzerland, https://sis.id.ethz.ch/
| | - Christian Bolliger
- SIS Scientific IT Services, ETH Zurich, Binzmühlestrasse 130, 8092 Zurich, Switzerland, https://sis.id.ethz.ch/
| | - Cristian Bovino
- SIS Scientific IT Services, ETH Zurich, Binzmühlestrasse 130, 8092 Zurich, Switzerland, https://sis.id.ethz.ch/
| | - Mattia Belluco
- SIS Scientific IT Services, ETH Zurich, Binzmühlestrasse 130, 8092 Zurich, Switzerland, https://sis.id.ethz.ch/
| | - Thomas Wüst
- SIS Scientific IT Services, ETH Zurich, Binzmühlestrasse 130, 8092 Zurich, Switzerland, https://sis.id.ethz.ch/
| | - Olivier Byrde
- SIS Scientific IT Services, ETH Zurich, Binzmühlestrasse 130, 8092 Zurich, Switzerland, https://sis.id.ethz.ch/
| | - Sergio Maffioletti
- SIS Scientific IT Services, ETH Zurich, Binzmühlestrasse 130, 8092 Zurich, Switzerland, https://sis.id.ethz.ch/
| | - Bernd Rinn
- SIS Scientific IT Services, ETH Zurich, Binzmühlestrasse 130, 8092 Zurich, Switzerland, https://sis.id.ethz.ch/
| |
Collapse
|
2
|
Kolobkov D, Mishra Sharma S, Medvedev A, Lebedev M, Kosaretskiy E, Vakhitov R. Efficacy of federated learning on genomic data: a study on the UK Biobank and the 1000 Genomes Project. Front Big Data 2024; 7:1266031. [PMID: 38487517 PMCID: PMC10937521 DOI: 10.3389/fdata.2024.1266031] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2023] [Accepted: 01/31/2024] [Indexed: 03/17/2024] Open
Abstract
Combining training data from multiple sources increases sample size and reduces confounding, leading to more accurate and less biased machine learning models. In healthcare, however, direct pooling of data is often not allowed by data custodians who are accountable for minimizing the exposure of sensitive information. Federated learning offers a promising solution to this problem by training a model in a decentralized manner thus reducing the risks of data leakage. Although there is increasing utilization of federated learning on clinical data, its efficacy on individual-level genomic data has not been studied. This study lays the groundwork for the adoption of federated learning for genomic data by investigating its applicability in two scenarios: phenotype prediction on the UK Biobank data and ancestry prediction on the 1000 Genomes Project data. We show that federated models trained on data split into independent nodes achieve performance close to centralized models, even in the presence of significant inter-node heterogeneity. Additionally, we investigate how federated model accuracy is affected by communication frequency and suggest approaches to reduce computational complexity or communication costs.
Collapse
Affiliation(s)
- Dmitry Kolobkov
- GENXT, Hinxton, United Kingdom
- Laboratory of Ecological Genetics, Vavilov Institute of General Genetics, Moscow, Russia
| | - Satyarth Mishra Sharma
- GENXT, Hinxton, United Kingdom
- Center for Artificial Intelligence Technology, Skolkovo Institute of Science and Technology, Moscow, Russia
| | - Aleksandr Medvedev
- GENXT, Hinxton, United Kingdom
- Center for Artificial Intelligence Technology, Skolkovo Institute of Science and Technology, Moscow, Russia
| | | | | | | |
Collapse
|
3
|
Iskrov G, Raycheva R, Kostadinov K, Gillner S, Blankart CR, Gross ES, Gumus G, Mitova E, Stefanov S, Stefanov G, Stefanov R. Are the European reference networks for rare diseases ready to embrace machine learning? A mixed-methods study. Orphanet J Rare Dis 2024; 19:25. [PMID: 38273306 PMCID: PMC10809751 DOI: 10.1186/s13023-024-03047-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Accepted: 01/19/2024] [Indexed: 01/27/2024] Open
Abstract
BACKGROUND The delay in diagnosis for rare disease (RD) patients is often longer than for patients with common diseases. Machine learning (ML) technologies have the potential to speed up and increase the precision of diagnosis in this population group. We aim to explore the expectations and experiences of the members of the European Reference Networks (ERNs) for RDs with those technologies and their potential for application. METHODS We used a mixed-methods approach with an online survey followed by a focus group discussion. Our study targeted primarily medical professionals but also other individuals affiliated with any of the 24 ERNs. RESULTS The online survey yielded 423 responses from ERN members. Participants reported a limited degree of knowledge of and experience with ML technologies. They considered improved diagnostic accuracy the most important potential benefit, closely followed by the synthesis of clinical information, and indicated the lack of training in these new technologies, which hinders adoption and implementation in routine care. Most respondents supported the option that ML should be an optional but recommended part of the diagnostic process for RDs. Most ERN members saw the use of ML limited to specialised units only in the next 5 years, where those technologies should be funded by public sources. Focus group discussions concluded that the potential of ML technologies is substantial and confirmed that the technologies will have an important impact on healthcare and RDs in particular. As ML technologies are not the core competency of health care professionals, participants deemed a close collaboration with developers necessary to ensure that results are valid and reliable. However, based on our results, we call for more research to understand other stakeholders' opinions and expectations, including the views of patient organisations. CONCLUSIONS We found enthusiasm to implement and apply ML technologies, especially diagnostic tools in the field of RDs, despite the perceived lack of experience. Early dialogue and collaboration between health care professionals, developers, industry, policymakers, and patient associations seem to be crucial to building trust, improving performance, and ultimately increasing the willingness to accept diagnostics based on ML technologies.
Collapse
Affiliation(s)
- Georgi Iskrov
- Institute for Rare Diseases, 22 Maestro G. Atanasov St., 4017, Plovdiv, Bulgaria.
- Department of Social Medicine and Public Health, Faculty of Public Health, Medical University of Plovdiv, 15A Vasil Aprilov Blvd., 4002, Plovdiv, Bulgaria.
| | - Ralitsa Raycheva
- Institute for Rare Diseases, 22 Maestro G. Atanasov St., 4017, Plovdiv, Bulgaria
- Department of Social Medicine and Public Health, Faculty of Public Health, Medical University of Plovdiv, 15A Vasil Aprilov Blvd., 4002, Plovdiv, Bulgaria
| | - Kostadin Kostadinov
- Institute for Rare Diseases, 22 Maestro G. Atanasov St., 4017, Plovdiv, Bulgaria
- Department of Social Medicine and Public Health, Faculty of Public Health, Medical University of Plovdiv, 15A Vasil Aprilov Blvd., 4002, Plovdiv, Bulgaria
| | - Sandra Gillner
- KPM Center for Public Management, University of Bern, Freiburgstr. 3, 3010, Bern, Switzerland
- Swiss Institute for Translational and Entrepreneurial Medicine (Sitem-Insel), Freiburgstr. 3, 3010, Bern, Switzerland
| | - Carl Rudolf Blankart
- KPM Center for Public Management, University of Bern, Freiburgstr. 3, 3010, Bern, Switzerland
- Swiss Institute for Translational and Entrepreneurial Medicine (Sitem-Insel), Freiburgstr. 3, 3010, Bern, Switzerland
| | - Edith Sky Gross
- EURORDIS - Rare Diseases Europe, 96 Rue Didot, 75014, Paris, France
| | - Gulcin Gumus
- EURORDIS - Rare Diseases Europe, 96 Rue Didot, 75014, Paris, France
| | - Elena Mitova
- Institute for Rare Diseases, 22 Maestro G. Atanasov St., 4017, Plovdiv, Bulgaria
| | - Stefan Stefanov
- Institute for Rare Diseases, 22 Maestro G. Atanasov St., 4017, Plovdiv, Bulgaria
- Department of Epidemiology and Disaster Medicine, Faculty of Public Health, Medical University, 15A Vasil Aprilov Blvd., 4002, Plovdiv, Bulgaria
| | - Georgi Stefanov
- Institute for Rare Diseases, 22 Maestro G. Atanasov St., 4017, Plovdiv, Bulgaria
| | - Rumen Stefanov
- Institute for Rare Diseases, 22 Maestro G. Atanasov St., 4017, Plovdiv, Bulgaria
- Department of Social Medicine and Public Health, Faculty of Public Health, Medical University of Plovdiv, 15A Vasil Aprilov Blvd., 4002, Plovdiv, Bulgaria
| |
Collapse
|
4
|
Ritchie F, Tilbrook A, Cole C, Jefferson E, Krueger S, Mansouri-Benssassi E, Rogers S, Smith J. Machine learning models in trusted research environments - understanding operational risks. Int J Popul Data Sci 2023; 8:2165. [PMID: 38414545 PMCID: PMC10898318 DOI: 10.23889/ijpds.v8i1.2165] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/29/2024] Open
Abstract
Introduction Trusted research environments (TREs) provide secure access to very sensitive data for research. All TREs operate manual checks on outputs to ensure there is no residual disclosure risk. Machine learning (ML) models require very large amount of data; if this data is personal, the TRE is a well-established data management solution. However, ML models present novel disclosure risks, in both type and scale. Objectives As part of a series on ML disclosure risk in TREs, this article is intended to introduce TRE managers to the conceptual problems and work being done to address them. Methods We demonstrate how ML models present a qualitatively different type of disclosure risk, compared to traditional statistical outputs. These arise from both the nature and the scale of ML modelling. Results We show that there are a large number of unresolved issues, although there is progress in many areas. We show where areas of uncertainty remain, as well as remedial responses available to TREs. Conclusions At this stage, disclosure checking of ML models is very much a specialist activity. However, TRE managers need a basic awareness of the potential risk in ML models to enable them to make sensible decisions on using TREs for ML model development.
Collapse
Affiliation(s)
- Felix Ritchie
- Bristol Business School, University of the West of England, Coldharbour Lane, Bristol BS16 1QY
| | - Amy Tilbrook
- University of Edinburgh, South Bridge, Edinburgh EH8 9YL
| | - Christian Cole
- Division of Population Health and Genomics, Ninewells Hospital and Medical School, Dundee DD1 9SY
| | - Emily Jefferson
- Division of Population Health and Genomics, Ninewells Hospital and Medical School, Dundee DD1 9SY
| | - Susan Krueger
- Health Informatics Centre, Ninewells Hospital and Medical School, Dundee DD1 9SY
| | | | - Simon Rogers
- NHS National Services Scotland, Gyle Square, 1 South Gyle Crescent, Edinburgh EH12 9EB
| | - Jim Smith
- School of Computer Science and Creative Technologies, University of the West of England, Coldharbour Lane, Bristol BS16 1QY
| |
Collapse
|