Drug Evaluation Committee Model Prototype for Investigating the Use of AI in Data Management Operations
June 2024
In the field of data management, there are still quite a few processes that rely on manual work. This not only places a burden on staff but also raises concerns about the risk of human error affecting data quality.Therefore, the Data Science Subcommittee’s FY2023 Task Force 1-1 decided to identify routine tasks within the data management domain where the use of AI could potentially improve efficiency and reduce errors, and to conduct three types of AI prototyping.For these prototyping projects, the members themselves carried out the entire process—from selecting the natural language processing and large language models to be used, to preparing training and test data, and training, validating, and testing the AI models to achieve the intended processing.This report summarizes these prototyping efforts, organized into sections on objectives, methods, results, and discussion. We hope readers will find this report an engaging way to “relive” the prototyping process.
Japan Pharmaceutical Manufacturers Association, Drug Evaluation Committee,
, Data Science Subcommittee, FY2023 Task Force 1-1
Model Prototype for Investigating the Use of AI in Data Management Operations