ICH adopts M15 guideline on model-informed drug development
The International Council on Harmonisation (ICH) announced the adoption of its M15 guideline, which aims to harmonize general principles and best practices for utilizing model-informed drug development (MIDD) to aid in drug development.The guideline reached Step 4 of the ICH process on 29 January and is ready for implementation by regulators.
The goal of MIDD is to improve the efficiency of drug development by integrating data from mathematical and statistical models to predict a drug’s effects and minimize unnecessary patient exposure.
The guideline outlines the framework for assessing MIDD evidence, provides an overview of the necessary model evaluation for this assessment, and offers general recommendations for reporting and submission of this information to regulators.
ICH announced that the M15 guideline “covers general principles and good practices for the use of MIDD and harmonises expectations regarding documentation standards, model development, data used in the analysis, and model assessment and its applications.”
The final guidance does not differ significantly from the Step 2 guidance released in November 2024. (RELATED: ICH releases draft GCP annex, MIDD guideline, Regulatory Focus 18 November 2024)
It retains the same framework for assessing MIDD evidence in terms of the questions of interest, the context of use, the model influence, the consequences of a wrong decision, the model risk and the model impact. It also retains the language for evaluating the models and the MDD reporting and submissions.
Some changes include added text in the model influence section and expanded details in the consequences of a wrong decision.
The added text in Section 2.1.3 states that “model influence should be described and rated as low, medium, or high, and then the rating justified. The description, rating, and justification should focus on the weight of the model outcomes in relation to the other relevant information used for answering the question of interest. The model influence rating should increase from low to medium to high as the weight of model outcomes increases. In general, when model outcomes are the sole source to support the decision, model influence should be considered as high. If there is considerable data and evidence coming from other relevant sources, the model influence may be rated low or medium depending on the weight of the model outcomes.”
The added text in Section 2.1.4 states that “the rating for consequence of wrong decision should take into consideration both the severity of potential negative effects as well as the likelihood that a wrong decision will result in potential negative effects. Both of these factors should be considered based on all available information at the time of regulatory interaction (e.g., nonclinical data, clinical data, prior information, and knowledge) and then combined to generate a rating for consequence of wrong decision.”
The guideline states that a variety of approaches can be used for modeling drug development, including population pharmacokinetics and pharmacodynamics, physiologically based pharmacokinetics and biopharmaceutics (PBPK), exposure-response analysis, model-based meta-analysis, quantitative systems pharmacology and toxicology, agent-based models, disease progression models, and applications of artificial intelligence and machine learning. These methods can be used individually or in combination.
ICH has been working on M15 since May 2020, with the formation of a discussion group focused on MIDD. In 2021, this discussion group released a work plan to integrate MIDD approaches into the existing ICH guidelines for drug development. (RELATED: ICH: MIDD concept paper coming by year’s end, Regulatory Focus 20 May 2021)
ICH announced that, while it has developed nearly a dozen guidelines related to various aspects of MIDD, there has not been a comprehensive guideline outlining general principles. This gap has led to uncertainty about the global acceptance of MIDD among regulators.
This uncertainty “has led to differences in the quality of MIDD applications and documentation in regulatory submissions, particularly when it involves novel methods or applications that are not covered in existing, topic-specific ICH Guidelines.”
ICH M15 guideline
×
Welcome to the new RAPS Digital Experience
We have completed our migration to a new platform and are pleased to introduce the updated site.
What to expect: If you have an existing login, please RESET YOUR PASSWORD before signing in. After you log in for the first time, you will be prompted to confirm your profile preferences, which will be used to personalize content.
We encourage you to explore the new website and visit your updated My RAPS page. If you need assistance, please review our FAQ page.
We welcome your feedback. Please let us know how we can continue to improve your experience.