Using real-world evidence in haematology.

Area of Science:

• Hematology
• Clinical Research
• Health Informatics

Background:

• Randomized clinical trials (RCTs) are standard for drug approvals but have limitations.
• Generalizability of RCT findings can be restricted, creating a gap with real-world practice.
• Contradictory conclusions from similar RCTs highlight the need for complementary data sources.

Purpose of the Study:

• To explore the potential of real-world data (RWD) in hematology.
• To assess how real-world evidence (RWE) from RWD can support regulatory decision-making.
• To highlight the role of artificial intelligence in processing RWD for RWE generation.

Main Methods:

• Review of existing literature on RCTs, RWD, and RWE in drug approval.
• Discussion of the application of artificial intelligence in analyzing RWD.
• Exploration of the gap between RCT conclusions and real-world observations.

Main Results:

• Real-world data (RWD) from registries offers a valuable complement to RCT data.
• Artificial intelligence can effectively process RWD to generate robust real-world evidence (RWE).
• RWE derived from RWD shows potential in bridging the gap between clinical trial findings and clinical practice.

Conclusions:

• Real-world evidence (RWE) from real-world data (RWD) can supplement RCT data for regulatory submissions.
• The integration of RWD and AI holds promise for improving the precision and applicability of drug approval decisions in hematology.
• Further research into RWE methodologies is crucial for its optimal utilization in regulatory science.