Hello everyone, my name is Vamsi Upaduri and I work as a senior statistical programmer at Gilead Science. Today I'll talk about the role of statistical programming in accelerating clinical drug development process. Did you know that it can take anywhere between 5 to 10 years and millions of dollars to bring a drug from discovery stage to market? Today I'll discuss how statistical programming Place a critical role in accelerating this process, transforming the raw data into actionable insights to evaluate the drug safety and efficacy. With growing complexities in clinical trial designs, increased data volumes, and stringent regulatory requirements from agencies like FDA and EMEA, The robust statistical programming has become essential. We'll explore its impact at every stage, from managing and analyzing data, to ensuring regulatory compliance, ultimately leading to faster and more effective treatments to improve patient outcomes. Let's explore the evolution of tools in statistical programming and how they have transformed clinical data analysis over time. SAS laid the foundation as a gold standard with validated procedures, robust audit trials, and comprehensive documentation to ensure regulatory compliance. R introduced flexibility and innovation, providing advanced statistical modeling, high quality data visualizations, and collaborative ecosystem of user contributed packages, making it ideal for an exploratory analysis. Python revolutionized the field with its integration of machine learning, automated workflows, and powerful data processing tools. to support the real world evidence analysis. Together, these tools help programmers to address the increasing complexity of clinical trials with precision and adaptability. Clinical programming plays a key role. critical role in providing data analysis across all phases of clinical trials. In phase one, it analyzes the safety data, identifies any adverse events, and determines the dose tolerability of a drug. Phase two, focus on assessing the safety and preliminary efficiency, efficacy in a small population. While phase 3 evaluates the safety and confirms the efficacy in large patient groups. In phase 4, statistical programming team monitors long term safety and real world effectiveness. by integrating real world data and detecting any safety signals. Comprehensive statistical data analysis ensures reliable trial outcomes by evaluating the safety and efficacy. And furthermore, The regulatory standards are upheld by developing the STDM and ADaM datasets based on the CD standards and generating TLFs as per the Statistical Analysis Plan to ensure the data traceability, integrity, and seamless regulatory submissions. Statistical programming often bridges the gap between the protocol and data analysis by converting the complex protocol into precise programming specifications, ensuring the accurate implementation of study endpoints. and analysis methods. Adaptive trial design leverage advanced algorithms for dynamic sample size calculations and treatment allocations enabling responsive trial modifications based on the accumulated data. Automated systems for safety monitoring enables continuous surveillance tracking adverse events and conducting risk benefit assessments with statistical outputs by data monitoring committee. Finally, a predefined interim analysis will be performed to review the validated outputs generated by a statistical programmer to make evidence based decisions to make sure the trial, continuation or modification or a decision to early terminate the study. Regulatory compliance is the cornerstone of any clinical data submissions, and standardized datasets play a critical role in this process. STDM and ADaM datasets are developed and validated to meet the stringent FDA and EMA requirements by following the CD standards, implementation guidelines, and therapeutic area specific guidance documents. For example, the requirements can vary between significantly between the oncology and virology studies. Adhering to these guidelines ensure alignment with evolving industry standards. Comprehensive submission documents such as DEFINE. XML, STDM Data Reviewer's Guide, Analysis Data Reviewer's Guide, facilitates a thorough submission regulatory assessment. Additionally, leveraging validation tools like PNaCl 21 enables conformance checks. And ensure data integrity, minimize risk and delays throughout the submission process. As clinical trial grows more complex, leveraging innovative technologies is essential for efficiency and accuracy. AI and machine learning revolutionized trials by automating the data cleaning process, reducing manual errors, and using its predictive models to optimize the outcomes like forecasting patient enrollment and identifying any patient reports. Cloud based platforms enables seamless global collaboration with secure, scalable infrastructure, supporting the real time data processing and integrated version control systems to prevent delays. Additionally, an interactive and dynamic visualization tools. create dashboards for data safety monitoring reviews, DSMB, to improve the regulatory submissions with graphs, which enhances stakeholders communication. Together, these advancements streamline the trial processes. and enable faster and more informed decision making. Let's look at two contrasting case studies. One demonstrating the success of statistical programming during the rapid development of COVID 19 vaccines. And the other highlighting the challenges in the regulatory compliance phase during an oncology trial. Together, these examples show the critical, the statistical programming role place in the clinical trials. The COVID 19 vaccine development showcased how advanced statistical programming can transform the clinical trials using sophisticated adaptive trial designs and real time data analysis. researchers were able to reduce the development timelines by significantly 80 percent enabling simultaneous phase 2 and phase 3 trials. Rolling regulatory submissions further accelerated this process, submitting a new, setting a new benchmark for its efficiency. On the other hand, a pharmaceutical company faced a significant challenge with its oncology trial. A six month submission delay occurred due to clinical CDISC failures, CDISC compliance failures. including inconsistencies in derived variables and missing documentations. This highlights the critical importance of robust statistical programming and stringent quality control to ensure smooth regulatory submissions. As clinical trials grow more complex, Adopting best practices in statistical programming is essential to ensure efficiency, accuracy, and compliance. Successful programming involves integration of expertise from protocol development all the way to the submission, establishing series compliance templates, And automated workflows for process standardization, performing systematic data validations at every milestone to maintain quality assurance and investing in continuous training to stay up to date with the regulatory standards and leveraging cutting edge tools like AI to enhance the efficiency and accuracy. Together, these practices. form a comprehensive framework that drives the success in drug development process. The future of statistical programming is defined by four key directions. First, integrating real world evidence data using AI powered analytics enables the seamless inclusion of data from electronic health records, insurance claims, and patient registries, providing deep insights into clinical treatment outcomes. Thank you. Second, the decentralized trials are becoming increasingly important, relying on robust systems to validate and analyze real time patient reported outcomes from its wearable device data, making clinical research more accessible and flexible. Third, adopting open source tools like. R and Python fosters collaboration and innovation while maintaining strict regulatory compliance and validation standards to ensure high quality outputs. Finally, traceability is critical with automated documentation and versioned environments ensuring that all the analyses are transparent, replicable, and ready for regulatory review. As the landscape of clinical trials evolves, regulatory bodies like FDA are modernizing clinical trial processes by introducing innovative frameworks for complex trial design and master protocols. They are also developing comprehensive guidelines to integrate real world evidence with a focus of deep quality and validation and to establish standards for validating AI and machine learning algorithms to ensure transparency, reproducibility, and support for advanced analytics in clinical research. As we look ahead to the future of clinical drug development, statistical programming remains a driving force for innovation and efficiency. By continually evolving to meet new challenges and adopting advanced technologies, the field ensures faster, more cost effective trials. Collaboration between programmers, researchers and regulators will be essential to overcome the complexities paving the way for improved patient outcomes and the need to deliver the life saving treatments worldwide. Thank you for attending the talk.