EU | EMA Guidance – Harnessing AI in Medicines Regulation: Use of Large Language Models (LLMs) GalleryEU | EMA Guidance – Harnessing AI in Medicines Regulation: Use of Large Language Models (LLMs)
2024, AI, EMA, Members-Only, Minor Update, RWD to Support Reg Decisions, Secondary Use of Existing Data-
Real World Evidence (RWE) 201 – France – CNIL Regulatory Sandbox: Digital Health
RWE 201 – France – CNIL Regulatory Sandbox: Digital Health
The French Data Protection Agency (CNIL) has been actively supporting digital health technology innovators through its regulatory “sandbox.” These projects range from federated learning across health data warehouses to building diagnostic tools in oncology, statistical indicators for medical research, and a therapeutic game for minors with eating disorders. The CNIL provides crucial guidance on overcoming regulatory challenges, including the nature of data, legal frameworks, and data security measures.
Benefits for RWD, RWE, and Digital Health Innovators:
- Navigating Regulatory Challenges: The CNIL’s sandbox provides a safe environment to test solutions and understand regulations. For RWD and RWE developers, this means an easier path to compliance with GDPR and other privacy laws.
- Interconnected Data Sources: For projects like Resilience in oncology, CNIL’s guidance enabled the interconnection of various data sources. This has implications for RWD, as it becomes easier to integrate data from disparate sources for more comprehensive Real-World Evidence.
- Data Security: With its focus on secure data processing, the sandbox offers a blueprint for ensuring the safety of health data, which is invaluable for digital health innovators dealing with sensitive patient information.
- AI and Machine Learning: Projects like the one carried out at Lille University Hospital utilized federated learning protocols, offering a roadmap for implementing machine learning algorithms in healthcare. This aids RWD and RWE applications where machine learning could provide new insights.
- Specialized Use-Cases: The Vertexica project focusing on minors with eating disorders shows how data protection can be maintained even in specialized healthcare solutions, thereby ensuring the ethical use of Real-World Data.
- Knowledge Sharing: The joint work and multiple exchanges with CNIL have generated lessons that could be useful for the broader health sector, facilitating faster and more secure innovation.
- ‘Privacy by Design’: The emphasis on integrating GDPR compliance from the design phase benefits all stakeholders by baking in data protection from the outset, which is a fundamental need in RWD and RWE applications.
- Stakeholder Collaboration: The sandbox projects involve multi-disciplinary teams, demonstrating a collaborative approach that could benefit digital health innovators, RWD and RWE developers in addressing complex regulatory and ethical issues.
In essence, the CNIL’s regulatory sandbox serves as an invaluable resource, not just as a testing ground but as a knowledge base for RWD, RWE, and digital health innovators. It provides practical insights into overcoming regulatory challenges and implementing secure, effective healthcare solutions.
Share this story...
Real World Evidence (RWE) 201…THE END – A Landscape Analysis of Regional RWE Frameworks – The European Health Data Space and DARWIN-EU
RWE 201 - THE END - A Landscape Analysis of Regional RWE Frameworks - The European Health Data Space and DARWIN-EU In our real world evidence (RWE) 201 series [...]
Real World Evidence (RWE) – Event Horizon
RWE 201 - RWE Event Horizon The term "event horizon" in the context of pharmaceuticals, particularly when discussing the shift towards real-world evidence (RWE) in regulatory submissions, is metaphorically [...]
Real World Evidence (RWE) 201 – Advancing Healthcare in Australia: Embracing Real-World Evidence and Data in Medicine Regulation and Development
RWE 201 - Advancing Healthcare in Australia: Embracing Real-World Evidence and Data in Medicine Regulation and Development Australia has several real-world evidence (RWE) initiatives to support healthcare [...]
Real World Evidence (RWE) 201 – South Korea’s Pioneering Approach: Integrating Real-World Evidence in Healthcare and Drug Development
RWE 201 - South Korea's Pioneering Approach: Integrating Real-World Evidence in Healthcare and Drug Development South Korea has several initiatives to support healthcare and drug development using [...]
Real World Evidence (RWE) 201 – Taiwan: Integrating Real-World Evidence for Drug Development and Policy Making
RWE 201 - Taiwan: Integrating Real-World Evidence for Drug Development and Policy Making Taiwan has several real-world evidence (RWE) initiatives to support healthcare and drug development. Over the past [...]
Real World Evidence (RWE) 201 – Revolutionizing Healthcare in Japan: The Rise of Real-World Evidence in Drug Development
RWE 201 - Revolutionizing Healthcare in Japan: The Rise of Real-World Evidence in Drug Development Japan has several initiatives to support healthcare and drug development using real-world evidence (RWE). [...]
Real World Evidence (RWE) 101 – Patient Recruitment
RWE 101 – Patient Recruitment
Real-world evidence (RWE) is health care information derived from real-world data (RWD). It can be generated through various study designs or analyses, including pragmatic clinical trials, observational studies, and health surveys. In the context of RWE, patient recruitment plays a significant role, as the data collected from these individuals helps in understanding the effectiveness, safety, and usage of medical products in the real world.
Traditional Patient Recruitment: In traditional methods, patient recruitment generally happens through methods like physician referrals, media advertising, patient registries, and patient advocacy groups. This method can be time-consuming, costly, and sometimes inefficient, as it often relies on manual efforts. It can also be challenging to find patients who fit specific inclusion and exclusion criteria for a particular study.
AI-Enabled Recruitment: Artificial intelligence (AI) has started transforming patient recruitment in many ways. AI can analyze vast amounts of real-world data from electronic health records (EHRs), medical claims, health surveys, and other digital health platforms to identify eligible patients rapidly. This approach reduces the recruitment timeline and the costs associated with patient enrollment.
AI algorithms can predict the likelihood of patients participating in the study, improving the precision of recruitment. They can also monitor and analyze patient behavior, enabling the refinement of recruitment strategies in real-time. AI can further enhance the diversity of recruited patients by considering a wide range of demographic and geographic factors, leading to a more inclusive and representative study.
AI-enabled recruitment can also help in mitigating potential biases in patient selection by utilizing a data-driven approach. By analyzing historical clinical trial data, AI models can identify patterns and biases in previous studies and correct them in future ones. Furthermore, AI can help in patient retention by predicting the potential drop-out risks and enabling timely intervention.
In conclusion, while traditional methods are essential and remain relevant in certain contexts, AI-enabled recruitment offers the possibility of increased speed, reduced costs, and improved diversity and representativeness of patients in studies generating real-world evidence.
Share this story...
Real World Evidence (RWE) 101 – ICH GCP (R3) – Real World Evidence Context
RWE 101 - ICH GCP (R3) - Real World Evidence Context Revision 2 of ICH GCP caused confusion to those of us who work with non-interventional studies. The glossary [...]
Real World Evidence (RWE) 101 – Non-Interventional Studies vs Market Health Research
RWE 101 - Non-Interventional Studies vs Market Health Research Key differences between a non-interventional study (NIS) and market health research include:1. Research Objective: NIS are conducted to examine real-world [...]
Real World Evidence (RWE) 101 – Real World Evidence (RWE) 101 – Audits vs Inspections
RWE 101 - Real World Evidence (RWE) 101 - Audits vs Inspections In the context of regulatory compliance for Real-World Evidence (RWE), both audits and inspections play crucial roles, [...]
Real World Evidence (RWE) 101 – A Career of Many Pathways
RWE 101 - A Career of Many Pathways Real-world evidence (RWE) refers to the information on health care that is derived from analysis of real-world data (RWD). RWE [...]
Real World Evidence (RWE) 101 – Evolution of Regulatory Affairs
RWE 101 - Evolution of Regulatory Affairs Real-world evidence (RWE) and real-world data (RWD) are increasingly influencing regulatory affairs in the biopharmaceutical and healthcare industry. This change has been [...]
Real World Evidence (RWE) 101 – Project Managers
RWE 101 - Project Managers Real-World Evidence (RWE) observational studies and clinical trials are both key elements of medical research, but they involve very different methodologies, aims, and requirements. [...]
Real World Evidence (RWE) 101 – Ethical Principles and Safeguards for Medical AI in the Context of Real World Evidence
RWE 101 – Real World Evidence (RWE) 101 – Ethical Principles and Safeguards for Medical AI in the Context of Real World Evidence
Medical AI applications hold great promise for improving healthcare outcomes, but they also raise ethical concerns related to patient privacy, algorithmic bias, and the reliability of the underlying data. When deploying medical AI in the context of real-world evidence, there are several ethical principles and safeguards that should be considered:
Transparency: Medical AI algorithms should be transparent about how they make decisions, what data they use, and the potential limitations of their predictions. This allows patients and clinicians to better understand the reasoning behind the AI’s recommendations and assess its accuracy.
Data privacy: Medical AI algorithms should comply with data privacy regulations, such as HIPAA in the United States, and should ensure that patient data is protected from unauthorized access, use, or disclosure.
Informed consent: Patients should be informed about how their data will be used by medical AI algorithms and should provide explicit consent for its use. They should also have the right to withdraw their consent at any time.
Fairness and bias: Medical AI algorithms should be designed to minimize bias and ensure that their predictions are fair across different patient populations. This requires careful attention to the selection of training data and the use of appropriate validation methods.
Human oversight: Medical AI algorithms should be designed to augment, not replace, human decision-making. Clinicians should have the ability to review and modify the AI’s recommendations, and patients should have access to human experts to address any concerns or questions they may have.
Accountability: Developers and providers of medical AI applications should be accountable for the accuracy and reliability of their algorithms, and should be transparent about any limitations or uncertainties associated with their predictions.
By following these ethical principles and safeguards, medical AI can be deployed in a responsible and effective manner, enabling healthcare providers to make better-informed decisions and improve patient outcomes.
Share this story...
Real World Evidence (RWE) 101 – ICH GCP (R3) – Real World Evidence Context
RWE 101 - ICH GCP (R3) - Real World Evidence Context Revision 2 of ICH GCP caused confusion to those of us who work with non-interventional studies. The glossary [...]
Real World Evidence (RWE) 101 – Non-Interventional Studies vs Market Health Research
RWE 101 - Non-Interventional Studies vs Market Health Research Key differences between a non-interventional study (NIS) and market health research include:1. Research Objective: NIS are conducted to examine real-world [...]
Real World Evidence (RWE) 101 – Real World Evidence (RWE) 101 – Audits vs Inspections
RWE 101 - Real World Evidence (RWE) 101 - Audits vs Inspections In the context of regulatory compliance for Real-World Evidence (RWE), both audits and inspections play crucial roles, [...]
Real World Evidence (RWE) 101 – A Career of Many Pathways
RWE 101 - A Career of Many Pathways Real-world evidence (RWE) refers to the information on health care that is derived from analysis of real-world data (RWD). RWE [...]
Real World Evidence (RWE) 101 – Evolution of Regulatory Affairs
RWE 101 - Evolution of Regulatory Affairs Real-world evidence (RWE) and real-world data (RWD) are increasingly influencing regulatory affairs in the biopharmaceutical and healthcare industry. This change has been [...]
Real World Evidence (RWE) 101 – Project Managers
RWE 101 - Project Managers Real-World Evidence (RWE) observational studies and clinical trials are both key elements of medical research, but they involve very different methodologies, aims, and requirements. [...]
RWE 101 – Why is there so much excitement about the use of AI in the context of real world evidence?
RWE 101 – Why is there so much excitement about the use of AI in the context of real world evidence?
The use of Artificial Intelligence (AI) in the context of Real World Evidence (RWE) is generating excitement because it has the potential to transform the way healthcare is delivered and improve patient outcomes. RWE refers to data collected outside of the traditional clinical trial setting, such as electronic health records, claims data, and patient-generated data. This data provides valuable insights into how drugs and medical devices perform in real-world settings and how they impact patient health.
AI has the ability to rapidly analyze large volumes of complex data from multiple sources and identify patterns and insights that can help healthcare providers make better treatment decisions. For example, AI can help identify patient populations who may benefit most from a particular treatment, or it can help identify adverse events associated with a medication or medical device that may not have been detected in clinical trials.
The use of AI in RWE can also lead to cost savings by identifying more efficient and effective treatment options, reducing the need for trial-and-error treatments, and avoiding unnecessary procedures and tests.
Overall, the excitement surrounding the use of AI in RWE is due to its potential to improve patient outcomes, enhance healthcare delivery, and reduce costs.
Share this story...
Real World Evidence (RWE) 101 – ICH GCP (R3) – Real World Evidence Context
RWE 101 - ICH GCP (R3) - Real World Evidence Context Revision 2 of ICH GCP caused confusion to those of us who work with non-interventional studies. The glossary [...]
Real World Evidence (RWE) 101 – Non-Interventional Studies vs Market Health Research
RWE 101 - Non-Interventional Studies vs Market Health Research Key differences between a non-interventional study (NIS) and market health research include:1. Research Objective: NIS are conducted to examine real-world [...]
Real World Evidence (RWE) 101 – Real World Evidence (RWE) 101 – Audits vs Inspections
RWE 101 - Real World Evidence (RWE) 101 - Audits vs Inspections In the context of regulatory compliance for Real-World Evidence (RWE), both audits and inspections play crucial roles, [...]
Real World Evidence (RWE) 101 – A Career of Many Pathways
RWE 101 - A Career of Many Pathways Real-world evidence (RWE) refers to the information on health care that is derived from analysis of real-world data (RWD). RWE [...]
Real World Evidence (RWE) 101 – Evolution of Regulatory Affairs
RWE 101 - Evolution of Regulatory Affairs Real-world evidence (RWE) and real-world data (RWD) are increasingly influencing regulatory affairs in the biopharmaceutical and healthcare industry. This change has been [...]
Real World Evidence (RWE) 101 – Project Managers
RWE 101 - Project Managers Real-World Evidence (RWE) observational studies and clinical trials are both key elements of medical research, but they involve very different methodologies, aims, and requirements. [...]
