machine learning Archives - European Industrial Pharmacists Group (EIPG)

Home  /  Generative AI in drug development  /  machine learning

The EU Parliament voted its position on the Unitary SPC


by Giuliana Miglierini The intersecting pathways of revision of the pharmaceutical and intellectual property legislations recently marked the adoption of the EU Parliament’s position on the new unitary Supplementary Protection Certificate (SPC) system, parallel to the recast of the current Read more

Reform of pharma legislation: the debate on regulatory data protection


by Giuliana Miglierini As the definition of the final contents of many new pieces of the overall revision of the pharmaceutical legislation is approaching, many voices commented the possible impact the new scheme for regulatory data protection (RDP) may have Read more

Environmental sustainability: the EIPG perspective


Piero Iamartino Although the impact of medicines on the environment has been highlighted since the 70s of the last century with the emergence of the first reports of pollution in surface waters, it is only since the beginning of the Read more

•••

Generative AI in drug development

March 11, 2024 , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,

by Giuliana Miglierini

Generative AI is perhaps the more advanced form of artificial intelligence available today, as it is able to create new contents (texts, images, audio, video, objects, etc) based on data used to train it. Applications of generative AI are not limited to, for example, the famous ChatGPT chatbot used to write complex texts, or to algorithms producing incredible images.

Generative AI is becoming a new paradigm in drug discovery, as it promises to greatly reduce both time and costs to develop new molecules, or to repurpose already existing ones for new indications. A fundamental goal for pharmaceutical companies, given that the average cost of developing a new medicines is estimated at $2.6 billion.

Algorithms can be trained on chemical-physical characteristics and 3D shapes of molecules in order to generate completely new molecules of interest for a certain application, and/or to predict their behaviour in the biological context (e.g. binding to a specific receptor). We resume the current status of implementation of generative AI in the field of drug development.

Quintillions of data
It seems ages since the first full sequencing of the human genome was completed in year 2000. Since then, vast amounts of genomic and other biological data have rapidly accumulated. To give an idea, the National Human Genome Research Institute estimates between 2 and 40 exabytes (i.e. quintillions) of data available within the next decade. The number becomes even more larger when considering other domains relevant to drug development, including chemical structures and properties, complex biochemical pathways, 3D protein structures and receptors, data on the efficacy and toxicity profile of already approved medicines and candidates in the pipelines, etc.
No matter to say, the parallel growing interest in artificial intelligence that characterised the last twenty years has turned fundamental for the availability of new technologies able to digest, extract and analyse these extremely large datasets.
Machine learning and deep learning algorithms represented just the first step towards this goal. Generative AI came as a consequence, its birth is attributed to a paper by Ian Goodfellow et al., published in 2014.

Opportunities and challenges of generative AI for drug discovery
The implementation of generative AI in the pharmaceutical and medtech sectors may lead to the an estimated economic value of $60-110 billion/year, says the report by McKinsey and Co. “Generative AI in the pharmaceutical industry: Moving from hype to reality”.
More specifically, McKinsey analysed 63 generative AI use cases in life sciences, calculating the potential economic impact for different domains. The higher values ($18-30 bln) are expected for the commercial domain, followed by research and early discovery ($15-28 bln) and clinical development ($13-25 bln). Less impacted appear enterprise ($8-16 bln), operations ($4-7 bln) and medical affairs ($ 3-5 bln).
Implementation of generative AI may prove not a so easy exercise for pharma companies, as it has to fit within an already complex organisation and with the strict regulatory requirements typical of the pharmaceutical lifecycle. An important message comes from the analysis from McKinsey: it is of paramount importance to exit the hype climate surrounding generative AI and understand exactly what it can and cannot be done.
The question is highly complex to be solved, and it requires multiple skills (data scientists, researchers, medical affairs, legal, risk and business functions) jointly working to set up the solution more suited to each company. The availability of a proper data infrastructure is just the first step, the chosen generative AI model has to be adapted to the complexity of the specific case of use, focusing on key applications to avoid disruption of the business.

According to an analysis by Boston Consulting Group, generative AI may prove useful to include also unstructured data among those used as data sources by the pharmaceutical industry. Possibly a challenging goal to achieve, as data access and management must fulfil regulatory requirements, for example in relation to the possibility to use data generated in clinical trials to support regulatory approval.
Governance of generative AI must also reflect the key principles established in the EU for AI systems, i.e. they “must be ‘safe, transparent, traceable, non-discriminatory and environmentally friendly,’ as well as ‘overseen by people, rather than by automation, to prevent harmful outcomes’.”

The need to integrate generative AI with human activities would probably call companies to redesign core processes. To this instance, selection of the more suited AI infrastructure and platform may turn critical for success of the initiative. Integration with already existing AI tools and flexibility are among other main features to be kept in mind. Not less important is the choice of the right partners, that should fit with the strategic business goals.

Many algorithms already available
The first AI applications based on deep learning algorithms were used, for example, to predict the sequence and structure of complex biological molecules. It was the case of the AlphaFold Protein Structure Database, which contains over 200 million protein structure predictions freely available to the scientific community. Other algorithms of this kind are ESMFold (Evolutionary Scale Modeling) and and Microsoft’s MoLeR, specifically targeted to drug design.
A more recent generation of generative AI are IBM’s MoLFormers UI, a family of foundation models trained on chemicals which can deduce the structure of molecules from simple representations. MoLFormer-XL screening algorithm, for example, was trained on more than 1.1 billion unlabelled molecules from the PubChem and ZINC datasets, each represented according to the SMILES notation system (Simplified Molecular Input Line Entry System). As reported by IBM, MoLFormer-XL is able to predict many different physical, biophysical and physiological properties (e.g. the capacity to pass the blood-brain barrier), and even quantum properties.

Mutual Information Machine (MIM) learning is the approach used by NVIDIA to built its MolMIM algorithms, a probabilistic auto-encoder for small molecule drug discovery. The NVIDIA BioNeMo cloud service uses these models to deploy a generative AI platform to create molecules that, according to the company, should fulfil all properties and features required to exert the desired pharmacological activity.

Not only big players: many new companies were born specifically to support the creation of generative (often end-to-end) AI platforms for drug discovery. Among the main ones, Insilico Medicine’s Pharma.AI platform is being used to build a fully self-generated pipeline comprehensive of 31 programs and 29 targets. The more advance product under development targets the rare disease idiopathic pulmonary fibrosis and is currently in Phase 2 in the US and China. The company’s inClinico AI data-driven multimodal platform to calculate the probability of success of single clinical trials proved useful to predict outcomes of Phase 2 to Phase 3 trials and to recognise weak points in study design.

UK’s based Exscientia, founded in 2012, is an AI-driven precision medicine company. Among its main achievements is the creation of the first functional precision oncology platform to successfully guide treatment selection and improve patient outcomes. The more advanced product in its pipeline is GTAEXS617, an oncology product targeting CDK7 in advanced solid tumors.
These are just few main examples, you can learn more on companies focused on AI for drug discovery in these articles published on Forbes and Pharmaceutical Technologies.


EMA’s reflection paper on AI in the pharmaceutical lifecycle

September 22, 2023 , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,

by Giuliana Miglierini

The rapidly evolving role of artificial intelligence (AI) and its possible application in the pharmaceutical field led the European Medicines Agency (EMA) to publish a draft Reflection paper on the use of AI along the entire lifecycle of both human and veterinary medicines.

The Reflection paper summarises the current view on the possible use of AI and machine leaning (ML) technologies and is open to public consultation until 31 December 2023. Comments, together with the outcomes of the joint HMA/EMA workshop to be held on 20-21 November 2023, will support its finalisation, as well as the possible development of new guidance. The initiative aims to identify the aspects of AI/ML use that would fall within the remit of EMA or of the single National Competent Authorities (NCAs) in charge of the dossiers’ assessment.

The document is part of the effort to improve the European Medicines Regulatory Network’s capability in data-driven regulation set forth by the joint HMA-EMA Big Data Steering Group (BDSG), and it has been developed in coordination with EMA’s CHMP and CVMP committees.

“The use of artificial intelligence is rapidly developing in society and as regulators we see more and more applications in the field of medicines. AI brings exciting opportunities to generate new insights and improve processes. To embrace them fully, we will need to be prepared for the regulatory challenges presented by this quickly evolving ecosystem” said Jesper Kjær, Director of the Data Analytics Centre at the Danish Medicines Agency and co-chair of the BDSG.

“With this paper, we are opening a dialogue with developers, academics, and other regulators, to discuss ways forward, ensuring that the full potential of these innovations can be realised for the benefit of patients’ and animal health” added Peter Arlett, EMA’s Head of Data Analytics and Methods, co-chair of the BDSG.

The main contents of the Reflection paper

The Reflection paper addresses the use of AI/ML with a dedicated chapter for each one of the steps, part of the overall lifecycle of a medicinal product. The interactions with regulators are then explored, as well as the different technical aspects to be taken into consideration. The final chapters discuss the governance of AI/ML applications, the integrity, and ethical aspects to be considered and how to address data protection.

The increasing use of AI technologies is based on the wide availability of big amounts of data produced and captured in electronic format on a routine basis. This data can be analysed by machine learning algorithms to inform the training of other systems able to analyse data and take actions with some degree of autonomy in order to achieve specific goals. These latter systems are the truly intended AI algorithms, those use is under discussion also in the field of regulatory decision making.

The Reflection paper recalls how the diffusion of these new technologies carries with it also some new risks, due to the “exceptionally great numbers of trainable parameters arranged in non-transparent model architectures”. Measures should thus be taken to ensure the safety of patients and the integrity of data, as well as to avoid the integration of bias into AI/ML applications.

The contents of the Reflection paper may also refer to combinations between a medicinal pro-duct and AI/ML-including medical device, as in such occurrence EMA is involved in the assessment of the characteristics of the device.

In general terms, existing guidelines, best practices, and recommendations relative to model in-formed drug development and biostatistics also apply to AI/ML; the adjacent methodology guidelines which may be relevant to this instance are listed in the document. The Reflection paper warns readers about the differences between the human and veterinary regulatory domains, suggesting that another reflection document specific for veterinary may be developed in future.

A risk-based approach

The usual risk-based approach typical of pharmaceutical development should be used to identify risks throughout the entire AI/ML tool lifecycle, including regulatory impact. According to the Reflection paper, the level of risk may depend also on the context of use and the degree of influence the AI technology exerts.

Developers should always seek early regulatory interaction and scientific advice, especially in cases where the AI/ML system may impact on the benefit-risk ratio of the medicinal product un-der development. To this instance, the EMA Innovation Task Force (ITF) is responsible for pro-viding early interaction on experimental technology, while scientific advice and qualification of novel methodologies in medicines development is provided by the Scientific Advice Working Parties (SAWP) of the CHMP for human medicines and of the CVMP for the veterinary ones.

As for all other steps of pharmaceutical lifecycle, the final responsibility for the suitability and use made of AI/ML algorithms, as well as their compliance to ethical, technical, scientific, and regulatory standards (GxP standards) and to current EMA scientific guidelines falls under the Marketing Authorisation Holders (MAHs) or applicants.

According to the Reflection paper, risks referred to in the discovery step may be limited, but they may impact the final evidence presented for regulatory review, thus principles for non-clinical development should be followed. This second step may include, for example, AI/ML modelling approaches according to the 3R principles. Regulators would expect to receive Standard Operating Procedures (SOPs) for AI/ML applications in preclinical studies; advisory documents on Application of GLP Principles to Computerised Systems and GLP Data Integrity should be also considered where appropriate. A pre-specified analysis plan would be needed for preclinical data potentially relevant for the assessment of the benefit-risk balance.

In the field of clinical trials, ICH E6 and VICH GL9 on human and veterinary GCPs should also be applied to the use of AI/ML. In particular, regulators expect the full model architecture and description of the data processing pipeline would be made fully available for comprehensive assessment should a model be generated for clinical trial purposes, as they would be considered parts of the clinical trial data or trial protocol dossier.

From precision medicine to pharmacovigilance

Particular considerations may be needed for applications of AI/ML in precision medicine, to individualise treatment according to the patient’s characteristics. AI/ML application supporting indication or posology decisions should be referenced in the Summary of product characteristics and their assessment falls under medicines regulation, representing a high-risk use both from the patient and regulatory perspectives. Close human supervision is also expected for AI applications used to draft or translate product information documents.

Many are the possible applications of AI/ML in the manufacturing of medicinal products, where they should follow the usual quality risk management principles (ICH Q8, Q9 and Q10) to guarantee safety, quality, and data integrity. New recommendations are also expected from EMA.

In the post-authorisation phase, AI/ML tools can effectively support efficacy and safety studies and post-marketing surveillance studies for veterinary medicines, as well as pharmacovigilance activities. Good pharmacovigilance practices should always be respected, and the used model should be validated, monitored and documented under the responsibility of the MAH. For conditional marketing authorisations, AI/ML applications should be discussed within a regulatory procedure unless details are agreed already at time of authorisation.


Trends for the future of the pharmaceutical manufacturing

April 21, 2023 , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,

By Giuliana Miglierini

The technological evolution of pharmaceutical manufacturing towards the full implementation of the Industry 4.0 paradigm is rapidly advancing. Digitalisation of productions is supported by the wide spread of automation, devices connected to the Internet of Things, and machine learning algorithms able to keep entire processes under control. Looking at pharmaceutical development, new types of treatments are emerging, also requiring a retuning of current approaches. Results from a survey among experts and industry insiders (56 respondents from 13 different countries) run by Connect in Pharma show new challenges are to be faced in the incoming years by the pharmaceutical industry in order to maintain its market position.

The combined value of the global pharmaceutical market in 2022 is estimated to be approx $650 billion. The main component reflects pharmaceutical manufacturing (US$ 526 billion in 2022, data Insight Slice), while the global pharmaceutical packaging market value is roughly US$131 billion (data Fact.MR).

Many different factors supporting the transformation of pharmaceutical manufacturing have been identified by Connect in Pharma, ranging from ageing of population to Covid19 and Ukraine crisis, to climate change and pressures on energy costs, up to the shortage of healthcare professionals. The final conclusions and opportunities identified by the report indicate new partnerships and collaborations (mainly with startups, and small and medium-sized companies) will remain fundamental to support competitiveness, together with growing investments in tech-driven innovations. Involvement of patients and healthcare professionals in identifying unmet needs and optimal solutions is another item to be considered in order to increase adherence to therapy, suggests the report.

Digitalisation still waiting to full exploit its potential

Innovation in automation and digitalisation of processes has been introduced in the pharmaceutical sector at a slower pace compared to other industrial sectors, due to its higher regulatory barriers. About one third (28%) of respondents to the survey indicated their companies are developing artificial intelligence (AI) or other digital tools for application in the manufacturing and packaging process. The main drivers towards the implementation of such systems are more efficient data collection, reduction of manufacturing down times and human errors, and the use of machine learning to support continuous manufacturing. Better workflow integration and anticounterfeiting, and the ability to share supply chain data with regulators are also relevant. These are all objectives that would need to provide new specific training to the workforce, e.g. on AI or tools for augmented reality.

One of the main barriers that, according to the report, is still slowing down the full potential of AI and digitalisation in the pharmaceutical industry is represented by the need to comply to regulations, including data integrity and security. The human factor may also prove relevant, as many people (including top management) may be reluctant to accept this change in technology. The availability of data scientists with a deep knowledge of the pharmaceutical sector is another critical point to be addressed.

Advances in drug delivery technologies

Connect in Pharma’s report also shed light on some drug delivery technologies that, despite not being an absolute novelty, are gaining relevance for the development of new products and treatments.

The moving of pharmaceutical pipelines towards a continuously increasing number of new biologic / biosimilar products, including mRNA-based and gene therapies, requires the availability of manufacturing and packaging capacities able to accommodate the specific needs of such often very unstable macromolecules. New drug delivery systems have been developed in recent years to provide answers to this need, among which is inhalation technology.

Dry powder inhalers and nasal delivery devices are the preferred formulations for the 50% of respondents to the survey that indicated actions are ongoing to develop new products using inhalation technologies. According to the report, these devices might prove particularly useful to deliver drugs that need to rapidly pass the blood-brain barrier in order to become effective, as well as for the delivery of vaccines. Fast absorption and higher bioavailability compared to other routes of administration are other elements of interest for inhalation technologies, which is also believed to be able to contribute to the reduction of carbon footprint.

Once again, the regulatory environment resulting from the entry into force of the EU Medical Devices Regulation (especially for drug-device combination products), together with the need to demonstrate patient safety and satisfactory bioavailability of these devices, are among the main barriers to their development, says the report. Inhalation technologies may also give rise to a new generation of delivery devices connected to the Internet of Medical Things (IoMT).

Another major trend identified by Connect in Pharma refers to the development of new drug delivery systems for injectable medicines (50% of respondents). This area is greatly impacted by the entry into force of the revised Annex 1 to GMPs, on 25 August 2023, that will increase the requirements for aseptic manufacturing. According to the report, main areas of innovation in this field may include new devices for injectable drug delivery, namely targeted to diabetes (the leading area of innovation), intravitreal ocular injection, autoimmune diseases, oncology, respiratory therapy, and pain management.

Connected devices

Diabetes is a highly relevant field of innovation also with respect to the implementation of connected devices, those embedded sensors and electronics allow for the real-time collection of data on self-administration of the therapy by patients, and their forwarding to health professionals. AI algorithms further enhance the potential of connected devices delivering diabetes treatments, as they support the real-time monitoring of insulin concentration in blood, and the consequent level of insulin delivered by the device. According to Connect in Pharma, other positive characteristics arising from the use of connected devices refer to the possible increase of patient adherence and compliance to treatment, resulting in improved patient outcomes and more personalised treatment.

Regulatory barriers are once again a main burden to the wider spread of connected devices, says the report, due for instance to the ultimate control over the sharing of data, and the choice if to implement single-use or reusable devices. Manufacturing costs, cybersecurity, and patient hesitancy are other hurdles identified by respondents to the survey.

The challenges for sustainability

The green policies put in place especially in the EU are calling industry to revise its processes and products to decrease their environmental impact, improve sustainability of manufacturing and packaging processes, so to eventually meet the climate targets fixed for 2050. According to the report, the global healthcare sector would be responsible for 4.4% of global net emissions. Connect in Pharma’s survey indicates 66% of involved companies are working to implement more sustainable practices. These may include for example the use of recycled materials in secondary packaging, the implementation of energy efficient technologies, and the development of more ecofriendly drug delivery systems. Costs have been identified as the main barrier to transition, together with the lack of common definitions. According to some of the experts, a wider use of data to monitor manufacturing systems and processes may help in improving the overall efficiency and in lowering the carbon footprint. Transport, for example, has a great impact on the sustainability of packaging.


A concept paper on the revision of Annex 11

November 18, 2022 , , , , , , , , , , , , , , , , , , , , , , ,

This concept paper addresses the need to update Annex 11, Computerised Systems, of the Good Manufacturing Practice (GMP) guideline. Annex 11 is common to the member states of the European Union (EU)/European Economic Area (EEA) as well as to the participating authorities of the Pharmaceutical Inspection Co-operation Scheme (PIC/S). The current version was issued in 2011 and does not give sufficient guidance within a number of areas. Since then, there has been extensive progress in the use of new technologies.

Reasons for the revision of Annex 11 include but are not limited to the following (in non-prioritised order):

  • The document should be updated to replace relevant parts of the Q&A on Annex 11 and the Q&A on Data Integrity on the EMA GMP website
  • An update of the document with regulatory expectations to ‘digital transformation’ and similar newer concepts will be considered
  • References should be made to ICH Q9
  • The meaning of the term ‘validation’ (and ‘qualification’), needs to be clarified
  • Guidelines should be included for classification of critical data and critical systems
  • Important expectations to backup processes are missing e.g. to what is covered by a backup, what types of backups are made, how often backups are made, how long backups are, retained, which media is used for backups, or where backups are kept
  • The concept and purpose of audit trail review is inadequately described
  • Guidelines for acceptable frequency of audit trail review should be provided
  • There is an urgent need for regulatory guidance and expectations to the use of artificial intelligence (AI) and machine learning (ML) models in critical GMP applications as industry is already implementing this technology
  • FDA has released a draft guidance on Computer Software Assurance for Production and Quality System Software (CSA). This guidance and any implication will be considered with regards to aspects of potential regulatory relevance for GMP Annex 11

The current Annex 11 does not give sufficient guidance within a number of areas already covered, and other areas, which are becoming increasingly important to GMP, are not covered at all. The revised text will expand the guidance given in the document and embrace the application of new technologies which have gained momentum since the release of the existing version.

If possible, the revised document will include guidelines for acceptance of AI/ML algorithms used in critical GMP applications. This is an area where regulatory guidance is highly needed as this is not covered by any existing regulatory guidance in the pharmaceutical industry and as pharma companies are already implementing such algorithms.

The draft concept paper approved by EMA GMP/GDP IWG (October 2022) and by PIC/S (November 2022) and released for a two-months consultation until 16 January 2023.


Draft topics for the first IHI calls for proposals

May 27, 2022 , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,

by Giuliana Miglierini

The Innovative Health Initiative (IHI) published on its website the first draft topics which may be part of the first two calls for proposals, scheduled in June 2022. Interested parties may start the activities needed to build and formalise the research consortia, taking into consideration that the announced topics are draft, pending their approval by the IHI Governing Board and their final version may differ from the drafts.

IHI call 1 shall focus on innovative technologies for the development of decision-support system for improved care pathways, next generation imaging, personalised oncology and access and integration of heterogeneous health data in areas of high unmet public health need.

IHI call 2 shall address cardiovascular diseases and the development of a harmonised methodology to promote early feasibility studies.

The draft topics of IHI call 1

Innovative decision-support systems are important to make available improved care pathways for patients with neurodegenerative diseases and comorbidities. The actions to be undertaken include the enhanced cross-sectoral and sustainable collaboration between healthcare industries, academia and other stakeholders in order to exchange data (through the new European Health Data Space), analytical tools and material for training and professional development of personnel.

Earlier diagnosis should lead to more clinically effective interventions and reduced hospitalisation and facilitate the adherence to therapy. Clinical outcomes are expected to support a better patient stratification, which is needed to develop more patient-adapted interventions, therapeutics and cost-effective pathways for the management of neurodegenerative diseases. Among the expected outcomes is the development of a re-usable, interoperable, easily adaptable, and scalable digital platform, initially targeted to support patients in this therapeutic area, but further expandable in the future to other areas of interest. The action should also involve the development of agreed standards and guidelines to support data collection and operational features of the digital platform. New algorithms may provide (near) real time feedback on health interventions and support the constant monitoring of the patient’s status.

The second topic is focused on the development of high-quality tools, high-quality data, advanced patient imaging and image-guided technologies and processes for improved early diagnosis, prognosis, staging, intervention planning, therapy and management of cancer. Imaging can be part of new combined cancer therapies (e.g., theranostics, chemotherapy, targeted therapy including immunotherapy, radiotherapy and/or surgery). The call should also include the development of improved validation and evaluation methodologies specific to artificial intelligence (AI)and machine learning (ML), with a particular attention to the creation of new solutions that automatically link images to clinical data. This could be applied, for example, to develop minimally invasive interventions guided by medical imaging, or image-driven planning and predictive tools.

The third topic is also aimed to tackle cancer through the development of personalised interventions. This action should contribute to break down silos that are often still characterizing medicine and technological areas. The availability of harmonised approaches should lead to safe and effective innovative health technologies, to the integration of future products, services and tools and the development of more patient-centred tools. Here again, an expected outcome is represented by a dynamic platform for R&I collaboration across different sectors and stakeholders, focusing on the early stages of applied clinical research on cancer and on the testing and validation of multi-modal therapeutic approaches, including novel or emerging technical and clinical concepts and the possible contribution arising from in vitro diagnostics.

Topic 4 of IHI 1 addresses the integration of future products, services and tools along the healthcare pathway to better respond to specific patients’ needs. The availability of interoperable, quality data which reflect the FAIR principles (Findability, Accessibility, Interoperability, Reusability) is central to this action, as well as the development of advanced analytics/artificial intelligence supporting health R&I. Among the main expected outcomes is the long-term access to diverse types of data enabled by the linkage and integration of novel and cross-sectoral sources. Access to interoperable tools should also become possible for citizens and patients to support the self-management of health and the joint decision making process between healthcare professionals and patients.

The draft topics of IHI call 2

Cardiovascular diseases (CDV) remain one of the main causes of death; the development of new tools for the primary and secondary prevention of CDV is the main focus of Topic 1, to be pursued by the identification of existing comprehensive CVD and heart failure (HF) patient datasets, in order to facilitate the diagnosis of atherosclerosis and HF. These data shall be also integrated with those captured by diagnostic tools (e.g., wearables, imaging devices, bio samples/biopsies).

Classical diagnostic screening, in-vitro- diagnostics, ‘multi-omic’ platforms (e.g. genomic, transcriptomic, proteomic and multimodality imaging data), continuous glucose monitoring (CGM) data, continuous electrocardiogram (ECG) from wearable, HF and activity data, wearable devices and digital health applications are all possible sources for the data. Projects may also leverage data in currently available IMI federated databases in compliance with the GDPR regulation governing protection of personal data.

The utility of already existing or new biomarker combinations shall be assessed to detect patients at risk, also making use of AI models to analyse data. Validated data referred to patient reported outcome and experience measure (PROMs and PREMs) may also be considered for use in the clinical setting.

The second draft topic is targeted to establish a harmonised methodology to promote the diffusion of Early Feasibility Studies (EFS) among healthcare professionals. Once again, the availability of digital technologies easily accessible by patients shall be key to this action. Among expected outcomes are the improvement of the quality of clinical evidence on health technology innovation generated through earlier clinical experience, together with the increase of the attractiveness of clinical research for healthcare technologies in the EU.

These activities are essential to enable the fast translation of innovation into the clinical practice, improving access to patients especially where there are only limited or no alternative therapeutic options. This approach to the development of innovative technologies may also benefit regulators and health technologies assessment (HTA) bodies, as well as notified bodies. All stakeholders involved in clinical practice and research may contribute to the early generation of quality data, so to achieve a better understanding of diseases management and treatment options and to support the future development of new medical guidelines.

The creation of hubs of clinical excellence to attract investment may also be considered under this topic, with involvement of developers of medical devices, drug-device combination products, imaging equipment, in-vitro diagnostics, and SMEs.