Artificial Intelligence and Real-World Evidence in Oncology Research

In this Q&A, Managing Principal Eric Wu discusses Analysis Group’s work applying artificial intelligence (AI) to real-world data (RWD) and generating real-world evidence (RWE) that can advance our understanding of disease and improve health care outcomes.

What is the value of RWD?

Eric Wu: Managing Principal, Analysis Group

The interactions of patients with health care systems worldwide produce tremendous amounts of rich and complex real-world data (RWD), which can advance our understanding of disease and health care outcomes. The benefits of RWD include large sample sizes, multidimensionality, representativeness and inclusivity of patient populations, timeliness and rapidity, and longitudinal perspectives.

However, obstacles such as the lack of interoperability, heterogeneity, missing or erroneous data, and varying contextual conditions under which the data were collected make it extremely difficult to harvest research-grade RWD that provides the full picture of patient characteristics, treatment patterns, and clinical and economic outcomes.

What are key challenges of RWD?

To translate large volumes of multi-source data into clinically meaningful, high-quality datasets, three key challenges of RWD need to be addressed.

First is the temporality of the data – that is, when the data were collected. The state of medical consensus at the time of collection must factor into the translation of point-in-time factual information, such as lab values, to form medical judgements – for example, diagnoses or prognoses.

Second is the spatiality of the data – that is, where it was generated. The state of medical practice, research methodologies, and data privacy regulations vary from region to region and country to country. All these differences may influence the content and interpretation of the data. 

Third, data quality may be affected by its completeness and accuracy. There may be missing data elements, for example, related to disease staging, progression, or lines of therapy, and there is also the risk of miscoding or data errors. For example, clinician notes may document only the initial treatment choice but not the entire patient journey throughout subsequent treatment choices and outcomes. Or it may be unclear how diagnoses of exclusion or suspected diagnoses that are mentioned differ from the final diagnosis.

Many studies to date have not fully addressed these issues with RWE generation and interpretation, but it is critical to do so to ensure data relevance in the fast-evolving health care field. This is especially important for complex disease areas, such as oncology or rare diseases, that involve multiple diagnostic criteria and small or isolated clinical trials.

How can AI-powered dynamic disease models help address RWD challenges?

The AI-powered dynamic disease model harnesses the power of RWD by enhancing the integration of data from various sources, establishing consistency and relevancy to any specific research question, and maximizing the usability of historical information. It uses an automated data processor to process information from various sources or multiple sites, while resolving data conflicts and unifying standards and definitions. The dynamic disease model provides a fact-based lens to review data based on traceable records, and the algorithms used are continuously updated by and implemented in scientific research.

How do you anticipate that dynamic disease models may shape the future of RWE?

The benefits of dynamic disease models go beyond their ability to generate fit-for-purpose RWE capable of addressing various local and current research questions. They are also designed to incorporate adequate information for addressing future questions and those from other regions or settings. Such efforts can help to eventually bridge fragmented and inconsistent data to create a truly coherent and dynamically evolving system with broad, rigorous applications.

Thus, the thoughtful design of real-world data synthesis and the perpetual inclusion of information to interpret clinical consensus via AI algorithms can be valuable for propelling research and informing medical decision making.

How may dynamic disease models affect health inequality and disparities in health care?

Dynamic disease models can be used to improve RWE about underrepresented or underserved populations. Real-world data sources can capture more diverse populations than clinical trials that have strict criteria for enrollment and that often underrepresent elderly, minority, or low-income populations. Therefore, dynamic disease models can contribute to better understanding of patient characteristics, treatment patterns, and clinical outcomes in underrepresented or underserved populations. ■