Student Internship IP2TIS 2024 - Mapping of African Genomics Program Electronic Health Records (EHR) and Genomics Data to the Observational Medical Outcomes Partnership Common Data Model (OMOP CDM at Roche Kenya

Key Responsibilities

• Work closely with other data scientists to develop reproducible codes for automating the mapping of EHR data to the OMOP common data model
• Developing codes for data mapping, cleaning, reshaping and loading data in SQL databases
• Defining Extract, Transform, Load or Extract, Load, Transform data engineering workflows for automating the data standardization and ingestion for large scale EHR
• Provide complete documentation and communication of all processes, methods, and results
• Work closely with other data scientists to develop processes to measure and ensure quality, completeness and integrity of the mapped data
• Engage in other department activities to ensure an inclusive and transparent work culture

Who You Are

• You are enrolled or have completed your Bachelor’s or Master’s studies at a university, preferably in the field of Biostatistics , Data science, Bioinformatics, Mathematics, Computer Science or a Life Sciences within the last 12 months and are interested in applying your knowledge in a modern working environment as part of an internship of at least 3 months and getting to know the pharmaceutical industry.

Furthermore you are

• Hands-on experience with real world data, especially OMOP Common Data Model and more specifically for mapping source data to the OMOP data model
• Experience working with SQL, R and/or python applied to medical data engineering for cleaning, reshaping data
• Experience working with genomics data, Standard Medical Vocabularies, like SNOMED, ICD10
• Experience with data quality assessment and data validation techniques
• Ability to understand scientific literature, experimental procedures and their limitations, and applications of this information in the research and clinical setting
• Experience working with RWD, EHR data, other common data models or global interoperability data standards are considered a plus
• A positive problem-solving attitude and you are solution driven
• An aptitude for developing software solutions to replace mundane manual tasks
• Have strong communication skills, both oral and written, with attention to detail