Artificial intelligence (AI) is an area of computer science with an emphasis on simulating and amplifying the human intelligence processes by machines.
AI is already frequently applied in life sciences industries and in precision medicine. However, the use of machine learning (ML), data mining and natural language processing (NLP) methods are limited so far - although it's a well-known fact that these methods can contribute to deeper analysis; generating new insights.
Nowadays, most healthcare facilities (clinics, hospitals) across the US and EU are generating an abundance of data during routine healthcare (real world data - RWD).
Examples of RWD include Electronic Health Records (EHRs), medical claims and billing data, data from disease registries as well as data gathered from other sources such as social media and wearable sensors.
Recent recommendations from the FDA include the development of standards and methodologies for incorporating RWD and real-world evidence (RWE) into clinical trials and regulatory oversight.
Within this framework, the FDA started the “Information Exchange and Data Transformation (INFORMED) initiative”. This is a collaboration with the US Health and Human Services Department’s IDEA Lab to work with additional internal and academic partners to develop an FDA curriculum on ML and AI.
Other initiatives are also being initiated all over the world. Another nice example comes from Finland where possibilities of ML and AI in RWE studies have been explored.
All those initiatives open a new era for RWD/RWE to use new software-based ML algorithms – NLP or deep learning – to help develop regulatory science tools like surrogate endpoints in clinical trials or digital biomarkers that can be used to guide more efficient development programs.
Source: FDA: Real-World Data, Machine Learning Critical for Clinical Trials (Health IT Analytics)