Periodic Reporting for period 1 - Real4Reg (Development, optimisation and implementation of artificial intelligence methods for real world data analyses in regulatory decision-making and health technology assessment along the product lifecycle)
Periodo di rendicontazione: 2023-01-01 al 2024-06-30
Real-world data (RWD) is routinely collected data relating to a patient’s health status or use of health care from sources other than clinical studies such as registers, health insurances, and electronic health records. RWD is regularly used in regulatory processes such as safety monitoring of drugs and medical products, which are already on the market (post-authorisation). On the other hand, few examples exist for the use of RWD for processes taking place before drugs and medical devices are authorized to be used on the market (evaluation and pre-authorisation). Also, the use of RWD in post-authorisation steps is constrained by data variability and by challenges in analysing data from different settings and sources. In addition, ever new possibilities to use artificial intelligence (AI) arise, but there is little knowledge on how to use AI to create evidence from heterogeneous RWD sources that can be used for health technology assessment (HTA) and by regulatory bodies to make decisions. Thus, the development of new and optimised AI-supported methodologies for RWD analyses is essential. In addition, Real4Reg established four use cases to be investigated, which are a matter of ongoing research and of high regulatory interest.
The main objective of the study is to develop tools and technologies for the effective analyses of real-world data (RWD) in regulatory decision-making and HTA based on four highly relevant uses cases along the pre- and post-authorization steps of the product life cycle.
The main objective of the study is to develop tools and technologies for the effective analyses of real-world data (RWD) in regulatory decision-making and HTA based on four highly relevant uses cases along the pre- and post-authorization steps of the product life cycle.
Primary outcomes will be:
(1.) Description of heterogeneity within and between European health claims data:
(1.1.) to subsequently investigate the accessibility/usability of registry and health claims data for describing a study population and
(1.2.) to examine how these data can serve as a high-quality external control, i.e. these data are compared to data from single-arm trials which otherwise would not have a comparison group. Thus, RWD can help making decisions in the evaluation and pre-authorisation steps of the product life cycle of a drug or medical product.
(2.) Methods for several tasks which are usually or sometimes performed while conducting a study (study population selection, summary statistic, as well as standardised result reporting)
(3.) Development and evaluation of AI/ML approaches
(3.1.) for target trial emulation as well as prediction of drug effectiveness and safety
(3.2.) to cluster and statistically characterize disease trajectories
(4.) Knowledge for improving guidelines which give general rules on how to best use RWD in the regulatory context; training concept on data-driven decision making for experts in health regulatory authorities and HTA bodies
Secondary outcomes will be evidentiary value insights into…
(1.) …the natural history of amyotrophic lateral sclerosis (ALS) and breast cancer (BC), its epidemiological measures and signals for disease progression in routine care in Portugal, Finland, Denmark and Germany as well as changes in standard of care of BC stratified by its subtypes, if applicable.
(2.) …alterations in how often and to what type of patients (age, sex,…) physicians prescribe fluorquinolone (FQs) in routine care in Portugal, Finland, Denmark, and Germany, since FQs authorisation changes as well as estimated risk of adverse drug reactions (ADRs) in patient characteristics before and after authorisation changes. The authorisation changes emphasize, e.g. that risks and benefits of FQ must be carefully assessed as rare but severe ADRs may occur.
(3.) … trends over time in how often and to what type of patients (age, sex,…) physicians prescribe SGLT2 inhibitors by comparing patient characteristics before and after repurposing SGLT2 inhibitors for the prevention of heart-failure related outcomes in Portugal, Finland, Denmark, and Germany; also, an estimation of how effective SGLT2 inhibitors agents are in comparison to a different type of antidiabetic drugs, called DPP4 inhibitors.
(1.) Description of heterogeneity within and between European health claims data:
(1.1.) to subsequently investigate the accessibility/usability of registry and health claims data for describing a study population and
(1.2.) to examine how these data can serve as a high-quality external control, i.e. these data are compared to data from single-arm trials which otherwise would not have a comparison group. Thus, RWD can help making decisions in the evaluation and pre-authorisation steps of the product life cycle of a drug or medical product.
(2.) Methods for several tasks which are usually or sometimes performed while conducting a study (study population selection, summary statistic, as well as standardised result reporting)
(3.) Development and evaluation of AI/ML approaches
(3.1.) for target trial emulation as well as prediction of drug effectiveness and safety
(3.2.) to cluster and statistically characterize disease trajectories
(4.) Knowledge for improving guidelines which give general rules on how to best use RWD in the regulatory context; training concept on data-driven decision making for experts in health regulatory authorities and HTA bodies
Secondary outcomes will be evidentiary value insights into…
(1.) …the natural history of amyotrophic lateral sclerosis (ALS) and breast cancer (BC), its epidemiological measures and signals for disease progression in routine care in Portugal, Finland, Denmark and Germany as well as changes in standard of care of BC stratified by its subtypes, if applicable.
(2.) …alterations in how often and to what type of patients (age, sex,…) physicians prescribe fluorquinolone (FQs) in routine care in Portugal, Finland, Denmark, and Germany, since FQs authorisation changes as well as estimated risk of adverse drug reactions (ADRs) in patient characteristics before and after authorisation changes. The authorisation changes emphasize, e.g. that risks and benefits of FQ must be carefully assessed as rare but severe ADRs may occur.
(3.) … trends over time in how often and to what type of patients (age, sex,…) physicians prescribe SGLT2 inhibitors by comparing patient characteristics before and after repurposing SGLT2 inhibitors for the prevention of heart-failure related outcomes in Portugal, Finland, Denmark, and Germany; also, an estimation of how effective SGLT2 inhibitors agents are in comparison to a different type of antidiabetic drugs, called DPP4 inhibitors.
Results will be published as soon as possible.
With regulatory bodies and academia working together, this project bridges some gaps between these two stakeholders, e.g. by developing a training that can be offered to both.
A key need is the sustainability of the developed trainings on data-driven decision-making.
With regulatory bodies and academia working together, this project bridges some gaps between these two stakeholders, e.g. by developing a training that can be offered to both.
A key need is the sustainability of the developed trainings on data-driven decision-making.