ERAMET will provide an integrated approach for developers and regulators’ decision-making for paediatric and orphan drugs, centred on the drug development questions. This will constitute a transparent ecosystem for drug development and assessment, that will facilitate the adoption of modelling and simulation (M&S) methods and related data types (including real word data such as registries and electronic healthcare data). The overall objective of ERAMET is to provide and implement a framework for establishing the credibility of M&S methods and related results as sources of evidence within regulatory procedures. The ecosystem proposed by ERAMET will be based on three pillars: (1) A repository connecting questions, data and methods. (2) The development and validation of high-quality standards for data and analytical methods (including M&S and hybrid approaches). These will cover computational M&S, digital twins, AI, hybrid approaches, standard statistics and pharmacometrics, as analytical methods and alternative data types and sources such as RWD, eHealth data, registries, historical regulatory submissions, scientific and (non)clinical trials). (3) An AI-based platform that will automate and optimise the data collection, formatting and modelling and simulation analysis and implement the credibility assessment. As part of ERAMET, the ecosystem will be applied to five use-cases including paediatric extrapolation and characterisation of drug benefit/risk in 4 groups of rare diseases, namely ataxia, transfusion dependent haemoglobinopathies, bronchopulmonary dysplasia, and degenerative neuromuscular. Each of the use-case is planned to lead to submission and regulatory approval of at least one validated M&S tool via the EMA qualification procedure. Training will be proposed to familiarise regulatory assessors, drug developers and clinical researchers with this new approach.

Cross-border collaboration can tackle the challenges in accessing relevant health data essential for international collaboration between scientists and clinicians, researchers, and health industry. Privacy concerns and regulations on personal data have made the sharing of health data increasingly complex and time-consuming for data controllers, thus severely limiting the access of SMEs, researchers, and innovators to health data. Further complications in cross-border collaboration arise from differences in interpreting the EU GDPR, national regulations, and heterogenous and changing data permit processes at hospital sites. The PHEMS project will provide European children’s hospitals with a decentralized and open health data ecosystem concept consisting of technical components and governance frameworks. The objective is to facilitate access to health data, advance federated health data analysis and build services for the ondemand generation of shareable, synthetized, and anonymized datasets. To achieve this, the project will focus on bridging the gaps in data access and use, especially in the integration of ethical, legal, and technical requirements, including the responsibilities of data controllers and the rights of data subjects. This will allow health data controllers to engage in collaboration without losing control on compliance with respect to GDPR, national legislation or internal policies of their organization. The techniques and tools for generating algorithmically anonymized and synthetic datasets will undergo robust validation processes through three clinical use cases conducted by the European Children’s Hospitals Organisation (ECHO) community. The goal is to assess the usage of custom-generated synthetic data with real-life questions. Data users, such as researchers, SMEs, innovators and the pharmaceutical and MedTech industry, will be engaged through community building, hackathons, and interaction with relevant European large-scale initiatives.

To use machine learning techniques, develop and validate risk stratification models to support improved outcomes for patients with diabetes and expand the technical capability in advanced analytics.

Head Injury is a devastating injury not only to the victim but also to their carers and to the society that supports their recovery, which is often long term. Unlike other forms of pathology including cancer, stroke or cardiovascular disease, there have been no proven effective therapies for brain injury. What is needed is a step-change in approach, one that brings recent advances in big data modeling directly into clinical practice, one that allows agile development and testing of new interpretations of high-frequency data for improved detection and prediction of clinically relevant and treatable events that occur during their early management in intensive care. This will be achieved by: 1) enabling the extraction of high-frequency patient data from in-hospital patient monitoring devices via collaboration with Philips Medical. The data will be anonymised and then passed to Aridhia’s platform; 2) development of Aridhia’s AnalytiXagility platform to provide storage of high-frequency data, support agile development and deployment of clinical analysis algorithms as "apps" to allow clinicians to control the analysis; and 3) presenting the results of analyses at the bedside.

Medical imaging has evolved over the years and is now used to provide interventional treatments, such as stent insertion for heart attacks and to screen for early onset cancers. Medical imaging can provide information about tissues adjacent to areas of abnormality, helping clinicians decide whether certain treatments are likely to be of benefit or may cause unwanted side effects. As imaging techniques have developed to provide greater detail, the size of the images files has also increased significantly. This has an impact on storage costs and computer performance required to process these images. Automated computer analysis of medical images can highlight abnormal areas but also identify those areas that are likely to be of clinical relevance and need further attention. These techniques have been used to support radiologists’ workload and have been shown to improve accuracy of diagnosis. There is a large amount of research being undertaken to determine new ways of analysing images to enable early detection of disease and to develop new biomarkers and drugs that will provide treatments targeted only at areas of abnormality. Achievement of these objectives requires the ability to have a platform to analyse clinical and research images at speed and in detail, without impacting on the performance of the IT infrastructure already in place. Our proof of concept proposal aims to take each image and separate out the descriptive information from the image data so these can be stored separately. Images will be broken up into constituent pixels and distributed on a newer type of computing infrastructure, which can store huge amounts of data. This computing platform will also provide tools to enable researchers to model pixel data so that they perform complex analyses. We feel this platform will provide a novel way of developing new models for analysing image data that can be implemented back into the clinical environment to enhance current diagnostic techniques.

DECIPHER is an ambitious, new, scalable, population-based commercial IT solution for the storage, integration, retrieval and analysis of electronic patient records (EPRs) and assay data from a wide variety of sources for the purposes of cancer research, with the long term aim of incorporating data for research into other long term conditions including cardiovascular disease, diabetes, renal and respiratory diseases. The scope of DECIPHER Health is an exclusive focus on cancer, in particular Ovarian, Breast, Colorectal, Lung, Skin, Renal and Prostate cancers. The consortium is only handling data from two Scottish Health Boards.