BEGIN:VCALENDAR VERSION:2.0 PRODID:https://github.com/derhansen/sf_event_mgt METHOD:PUBLISH BEGIN:VEVENT UID:4-16@hms-data.de CLASS: PUBLIC SUMMARY:PHUSE EU Connect 2025 DESCRIPTION:From November 16 to 19, PHUSE EU Connect 2025 brings together l eading experts from life sciences, clinical research, and data analytics in Hamburg. The international conference provides a platform for exchanging i deas on regulatory topics, emerging technologies, and data-driven innovatio n in drug development.\n\nThe event is all about open knowledge sharing, pr actical insights, and engaging discussions. That is why HMS is once again t aking part – contributing our own talks, sharing insights from our project work, and looking forward to new ideas and connections.\n\n\n\nOur contribu tion to PHUSE\n\nTalk\n\nHow to Identify and Operationalize GenAI Use Cases Which really help You\n\nChristoph Bergen, Luis Wirth\n\nGenerative AI (Ge nAI) is everywhere right now – but particularly within the complex workflow s and regulatory structures of the pharmaceutical industry, it can be diffi cult to determine whether it is actually the right solution for a specific challenge.\n\nIn this beginner-friendly session, we provide practical guida nce to help make that decision. We start by clearly distinguishing between traditional (or “discriminative”) AI and generative AI and explore the type s of problems each approach is particularly well suited to address. Using r eal-world examples from the pharmaceutical industry, we explain how GenAI m odels can be applied in practice – and which additional components are need ed to successfully implement a specific use case. We also present different strategies for operationalizing GenAI, ranging from self-service platforms to distributed systems that provide GenAI tools via MCP servers.\n\nThis s ession is aimed at both GenAI beginners and decision-makers looking to inte grate generative AI into real-world business processes in a targeted way an d with clear benefits.\n\nDownload presentation now Download paper now\n\n\ n\nTalk\n\nPoseidon: streamlined regulatory screening of HA websites with A I/ML extracting updates reducing manual efforts\n\nMaria Giovanna Zill (Mer ck KGaA), Fabian Wahren\n\nThe “Poseidon” project aims to streamline the re gulatory screening of websites operated by international Health Authorities (HAs) at Merck Healthcare. Currently, subject matter experts (SMEs) invest significant manual effort in screening relevant content and subsequently p rioritizing it.\n\nBy developing an AI/machine learning system that automat ically evaluates updates on HA websites, Poseidon aims to significantly red uce this manual workload and free up resources for more strategic tasks. Th e project not only increases efficiency and reduces the risk of human error , but also creates a centralized knowledge base that supports informed asse ssments of regulatory impact and improves compliance.\n\nScalability: The s ystem is designed to be transferable to other areas within healthcare and l ife sciences – for example, regulatory topics related to clinical developme nt, medical devices, manufacturing, or pharmacovigilance.\n\nTime savings: The solution is expected to measurably reduce the time subject matter exper ts spend on regulatory screening.\n\nDownload presentation now Download pap er now\n\n\n\nTalk\n\nSAMBA: Bridging the Gap – How GenAI Transforms Analys is Plans into ADaM Specs\n\nThiago Figueiredo, Richard Becker (Mreck KGaA), Fabian Wahren\n\nProgramming specifications, particularly ADaM specificati ons, combine study-specific information with established industry standards to ensure that analysis results are comparable across studies. Creating an alysis packages for clinical trials requires a thorough understanding of th e study protocol and Statistical Analysis Plan (SAP) in order to implement statistical analyses based on the variables and datasets described in these documents.\n\nIn practice, however, creating these specifications is time- consuming and involves numerous manual steps, making it difficult to standa rdize metadata across studies.\n\nWe present the Smart Assistant for Metada ta and Biostatistics Analysis (SAMBA), a tool that helps statistical progra mmers create ADaM specifications more efficiently based on existing study d ocuments. SAMBA uses Large Language Models (LLMs) to partially automate the creation and updating of specifications, significantly reducing the effort involved.\n\nWe provide insights into the system architecture, the develop ment process, user feedback, and potential directions for future developmen t.\n\nDownload presentation now \n\n\n\nTalk\n\nLeveraging AI for Seamless SAS to R Migration: Challenges and Opportunities\n\nCorinna Stöckinger (Boe hringer Ingelheim), Milena Kraus, Dr. Robert Bauer\n\nWhile SAS has traditi onally been the de facto standard for the statistical analysis of clinical trials, the industry has increasingly turned its attention to open-source a lternatives in recent years. One of the most prominent is the R programming language. At Boehringer Ingelheim, a ClinPharm task force was established to support the transition from SAS to R, backed by a team of HMS experts.\n \nIn this talk, we present our joint project to migrate a collection of SAS macros and templates used in PK/PD analyses to R. The aim was to make the migration process more efficient with the help of Generative AI (GenAI). We explore several approaches tested during the project – ranging from direct code translation to the use of existing packages from the pharmaverse – an d discuss their respective advantages and disadvantages.\n\nFinally, we exa mine both the opportunities and limitations of GenAI in this context, as we ll as the need for a structured framework to harness its potential effectiv ely and successfully.\n\nDownload presentation now Download paper now\n\n\n \nPoster\n\nHow can agile R Package validation workflows be achieved?\n\nDr . Sophia Stahl-Toyota\n\nMoving from feature requests or bug reports to the next validated release of an R package within an agile workflow is a visio n shared by many product owners, developers, validation specialists, and us ers. Add stakeholders from quality assurance, deployment pipeline teams, or management, and it becomes clear that success depends not only on the righ t tools, but above all on effectively coordinating people and processes.\n\ nWe show how the tool landscape for software development and validation can be set up using the technical capabilities of platforms such as GitLab, Ji ra, Azure DevOps, and GitHub. This includes the effective use of workflows, status fields, labels, scoped labels, tags, components, and time-based str uctures such as iterations, sprints, and milestones.\n\nHowever, efficient tracking of development and validation activities – which typically involve numerous reviews and coordination steps – ultimately depends on configurin g and using these options effectively. And that is where the real challenge lies.\n\nDownload poster now Download paper now LOCATION:CCH – Hamburg Congress Center DTSTAMP:20261005T122901Z DTSTART:20251117T080000Z DTEND:20251119T160000Z END:VEVENT END:VCALENDAR