Real World Evidence
Working Group Scope |
The Real World Evidence Working Group aims to support, address and answer pertinent questions around real-world evidence. The Working Group is dedicated to sharing across the PHUSE Community (through Community Forums) and aligning on the best industry practices. Some of the questions we intend to address are:
|
 b.snoeijer@clinline.eu Berber Snoeijer started in clinical research in 1997 as a biometrician and has since then worked with clinical data in different functions. In 2001 she started a CRO – Biometric Support – aimed at the data management, data analysis and reporting of clinical trials. In 2011 she started as an R&D manager dedicated to investigating and utilising the potential of real-world data from electronic health records. This resulted in many different solutions including a full reporting system to give feedback information to clinical research professionals. Berber is experienced with software and database engineering, process engineering and improving efficient utilisation and interaction of people based on management drivers. Nowadays, she uses these skills and knowledge to help life science companies assess, design and improve business solutions and processes at smaller and larger scales. |  ashwin.rai@thermofisher.com With over 15 years of experience in data science across pharma, life sciences and healthcare, Ashwin Rai is a prominent leader in RWE and RWD. As Director of Data Science & Analytics at Evidera, a PPD-ThermoFisher company, Ashwin leads a dynamic team that develops cutting-edge AI algorithms, ML, and NLP models in domains such as RWE, HEOR and PASS studies. His expertise includes implementing ML, NLP and predictive analytics projects – particularly focused on monitoring and management of clinical trials – predictive healthcare modeling, patient segmentation, disease progression analysis, advancing precision medicine, and proactive healthcare management using diverse data sources such as clinical trials, EHR, EMR, labs and pharmacy data. Ashwin also supports Evidera’s Real World Data Solutions team, which contributes to data feasibility assessments, validation, and analysis of third-party real-world data. Ashwin’s leadership has been instrumental in expanding Evidera’s RWE data science business, forging collaborations with clients and experts to deliver innovative, data-driven solutions. Ashwin’s commitment to pushing the boundaries of data science for healthcare advancement is further underscored by his abstracts and poster presentations in AI and ML within the healthcare field, including the selection and presentation of his AI prototypes at the prestigious PHUSE/FDA Data Science Innovation Challenge in both 2020 and 2024. These accomplishments highlight Ashwin’s dedication to driving innovation and leveraging data science to address critical challenges in healthcare. Ashwin holds a master of science in predictive analytics from Northwestern University and is based in Overland Park, Kansas. |  evalkanova@endpointclinical.com Elena Valkanova began her career in clinical research more than 20 years ago, specialising in statistical programming and data analysis across diverse therapeutic areas. Throughout her career, she has contributed to the design, validation and reporting of regulatory deliverables, ensuring accuracy, reproducibility and compliance with global standards such as CDISC. Elena’s early academic research into algorithmic game theory focused on developing randomised and strategy-improvement algorithms for simple stochastic games – a rare class of combinatorial problems that belong to both NP and co-NP and have no known polynomial-time solutions – providing a strong foundation in probabilistic modelling, computational complexity and optimisation. Elena leads collaborative initiatives to develop practical frameworks and implementation guidance for privacy-preserving methods, including differential privacy, federated learning and synthetic data generation. Her leadership centres on building cross-disciplinary resources that integrate statistical programming, machine learning (ML), artificial intelligence (AI) and large language models (LLMs) to enable compliant, scalable and scientifically robust use of real-world data (RWD). |