Back to Search Start Over

Clinical trials, real-world evidence, and digital medicine

Authors :
Gabriela Feldberg
Mishal Patel
Jim Weatherall
Richard Dearden
Sajan Khosla
Glynn Dennis
Thomas E. White
Khader Shameer
Faisal Khan
Publication Year :
2021
Publisher :
Elsevier, 2021.

Abstract

The development of new medicines through the clinical trials process offers countless opportunities for the application of approaches such as those offered by artificial intelligence and machine learning. Broadly speaking, the application of these techniques is usually aimed at doing one of the following: 1. Increasing the speed and therefore reducing the time to develop a medicine and get it to patients who need it. 2. Becoming more accurate at picking the winners—those potential new medicines that will go on to succeed, rather than produce negative clinical trial results. 3. Generating productivity or efficiency gains to offset the large costs of running clinical trial programs. These are all difficult problems to solve. However, the good news is that the clinical trials process tends to generate large volumes of data, some of which are of good quality—because it is required to be according to regulatory standards. These data are vital for using AI and machine learning techniques to achieve gains in one of the three opportunity areas outlined above. In addition, new data streams are maturing all the time—such as patient data from sensors and wearable devices, genomic testing, and real-world evidence.

Details

Database :
OpenAIRE
Accession number :
edsair.doi...........55cd71e4c658118f0970ff88efc44dfa
Full Text :
https://doi.org/10.1016/b978-0-12-820045-2.00011-8