COMORBIDITY MECHANISMS UTILIZED IN HEALTHCARE

Project Information

COMMUTE

Grant agreement ID: 101136957

DOI

10.3030/101136957

EC signature date 23 November 2023

Start date 1 December 2023

End date 30 November 2027

Funded under

• Health

Total cost

€ 7 280 986,25

EU contribution

€ 7 280 986,25

Coordinated by

FRAUNHOFER GESELLSCHAFT ZUR FORDERUNG DER ANGEWANDTEN FORSCHUNG EV
Germany

Periodic Reporting for period 1 - COMMUTE (COMORBIDITY MECHANISMS UTILIZED IN HEALTHCARE)

Reporting period: 2023-12-01 to 2025-05-31

Summary of the context and overall objectives of the project

The coronavirus disease pandemic is an experiment involving all humankind: almost everyone has been or will be infected with severe acute respiratory syndrome coronavirus 2. This makes it well suited to study effects of infection on diverse individuals. There is growing evidence that viruses may contribute to neurodegenerative diseases, raising concerns about a wave of dementia due to coronavirus disease.
In COMMUTE, we focus on mechanisms underlying the comorbidity between coronavirus disease and neurodegenerative diseases, particularly Alzheimer’s disease and Parkinsonism.
COMMUTE combines two approaches: a hypotheses-free, data-driven approach using big data and artificial intelligence and machine learning to test whether infection with severe acute respiratory syndrome coronavirus 2 increases the risk of neurodegenerative diseases, and a hypothesis-driven, knowledge-based approach leveraging existing scientific knowledge on mechanisms linking coronavirus disease and neurodegeneration. Both approaches will inform each other through collaboration between computational and experimental biology.
The first goal of COMMUTE is to understand the comorbidity between coronavirus disease and neurodegenerative diseases causally. The second goal is to translate actionable insights into personalized health applications.
On the artificial intelligence and machine learning side, the outcome will be qualified biomarkers and predictive features for an artificial intelligence-powered recommender system that supports individualized risk assessment and recommendations. On the biomedical side, COMMUTE will use cell-based assays to test the drugability of candidate mechanisms and targets for drug repurposing in collaboration with REMEDI4ALL, a large European Union drug repurposing platform.
COMMUTE fosters ongoing exchange between partners and end users so their needs and concerns are reflected in outcomes. A Legal and Ethical Advisory Board has been established; experts will meet regularly to discuss and advise.
Engaging users (patients, healthcare professionals, and institutions) through annual workshops is crucial. Insights from these workshops will be compiled into recommendations published at the project’s conclusion.
Throughout the project, COMMUTE will analyze legal and ethical requirements, including consent under the General Data Protection Regulation for patients with neurodegenerative diseases and the interplay of medical regulatory frameworks with the emerging legal framework for artificial intelligence in the European Union. Attention to legal and ethical developments and patient engagement are vital for success.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

COMMUTE has made strong progress toward its technical and scientific objectives. Overall management was coordinated effectively, aligning activities with objectives and milestones. The consortium completed contractual obligations, including funder reporting and finalizing the Consortium and Grant Agreement.
A comprehensive Data Management Plan was developed to outline data handling procedures adhering to Findable, Accessible, Interoperable, and Reusable principles, strengthening data governance. A Dissemination and Communication Plan was submitted to engage stakeholders, including patient organizations and research institutions.
Data handling and knowledge graphs were described. The team examined data models and ontologies to standardize clinical dataset features, leading to a comorbidity-centric knowledge graph with 2,800 curated relations and a natural language processing-enhanced hypothesis graph with 4,700 edges. An enrichment server was created to enable algorithmic use of these knowledge graphs for analyses such as gene set enrichment.
To create biomarker-based artificial intelligence and machine learning models to identify patients at risk of neurodegenerative diseases, the team accessed multiple databases and curated relevant variables. The project also began uncovering molecular mechanisms linking coronavirus disease and neurodegenerative diseases, identifying public databases for further investigation.
Knowledge-based hypotheses for comorbidity mechanisms were generated through literature review, yielding testable hypotheses and experimental models. Collaboration with artificial intelligence and machine learning initiatives identified critical molecular drivers of coronavirus disease and neurodegenerative disease comorbidities through advanced network analysis.
Legal and ethical considerations were addressed through workshops with consortium members and stakeholders, providing recommendations for implementation. Data governance was strengthened through a Data Protection Impact Assessment, and a centralized helpdesk was set up for legal queries.
In the first 18 months, COMMUTE advanced understanding of the interplay between coronavirus disease and neurodegenerative diseases while developing robust data management frameworks and ensuring ethical compliance.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

COMMUTE has generated results with potential impact on scientific understanding and practical applications concerning coronavirus disease and neurodegenerative diseases. Key achievements include comprehensive analyses through knowledge graphs elucidating comorbidities, and advanced artificial intelligence and machine learning models for identifying at-risk patients. These innovations deepen understanding of molecular mechanisms linking coronavirus disease and neurodegenerative diseases and pave the way for improved diagnostic and therapeutic strategies.

Logo of COMMUTE