PHUSE Education

Data science describes a cross-functional field which uses scientific methods to extract knowledge from data.

Professionals in this field apply techniques from disciplines such as mathematics and statistics. Computational and information science are also used to generate hypotheses and draw conclusions based on data sources.

Programming languages are an integral component of data science, with varied uses within the pharmaceutical industry.

For example, they can provide analytics from a wide variety of data sources (such as real-world evidence and findings from clinical or nonclinical trials) to assess the efficacy and safety of drugs and/or devices (e.g. inhalers).

The Data Engineering Cluster explores how techniques deployed in other industries could be used in our sector.

Techniques span traditional data warehousing and the big data lake to data marketplaces, ePRO and IoT. The challenge is to identify analytical value from these disparate data sources and aggregate it into one easily digestible format.

PHUSE was founded to help our Community collaborate with and share knowledge about the latest healthcare technology and applications.

This cluster explores the many and varied drivers which influence how we select and use technologies and applications, with a focus on identifying, categorising and educating users about the choices available.

Job skills are an essential aspect of developing a career in clinical data science.

These curated educational resources encompass a broad range of skills, which have been broken down into categories for easy navigation. Some skills may relate to other topic clusters within PHUSE Education.

The regulatory environment is often difficult to navigate, but understanding how to do so is essential for anyone working in the clinical data science sector. This section clarifies the regulatory process from a data scientist’s perspective.

The regulatory framework summarises the key inflection points with regulators, explains how regulatory bodies use submitted data to support drug approval, and discusses emerging approaches that could influence the way clinical trial data is submitted.

Clinical documents are the foundation of the clinical drug development process. The purpose and the relevance of these documents for stakeholders can be overwhelming. This cluster provides insight into the clinical documents available, showing which are of particular interest to the PHUSE Community.

Industry standards determine how we capture, clean and analyse data within the clinical data science sector.

This cluster includes information about the latest standards and introduces you to the key organisations that have shaped industry standards to date.

Therapeutic Area (TA) expertise becomes more and more important for clinical data scientists working in the pharmaceutical industry as it is crucial for the understanding of patients’ needs and the interpretation of analysed data.

For a profound knowledge of a TA, the following information is of critical importance for the clinical data scientist:

• Description of Disease
• Demographics and Baseline Characteristics
• CDISC Standards and Therapeutic Area User Guides
• Agency Guidelines
• Study Design and Study Endpoints
• Data Challenges

This educational cluster focuses on aspects of drug development in the pharma industry. Drug development in commercial biopharma may be divided into three sequential domains:

• Pre-clinical – using in vitro and in vivo data
• Clinical drug programme development (CLINICAL) – using in-human data
• Postmarketing using Real-World Data (RWD) and Real-World Evidence (RWE) data