2 minutes reading time (354 words)

Artificial Intelligence: Useful for Designing Clinical Trials

Artificial intelligence.

Due to lackluster recruiting techniques, a suboptimal number of patients are selected to participate in clinical trials. In addition, the researchers often have limited ability to observe and coach patients during clinical trials. These factors contribute to high clinical trial failure rates, which have a negative impact on the drug development cycle, not to mention 10 to 15 years and hundreds of millions of dollars wasted.

However, scientists have proposed a potential solution to this problem: artificial intelligence (AI). Lead author of this study, Stefan Harrer, PhD, Research Staff Member at IBM, commented, "AI is not a magic bullet and is very much a work in progress, yet it holds much promise for the future of health care and drug development."

In this study, published in Trends in Pharmacological Science, Dr. Harrer and colleagues conducted a review of AI for clinical trial design. They reported that by using deep learning and machine learning, AI could consolidate important potential participant information, such as identified biomarkers, to determine which patients would be eligible to enroll in the clinical trials, in order to increase the likelihood of the trial's success. Artificial intelligence was also reported to potentially be able to help with patient adherence to therapeutic interventions and reduce patient drop-out rate by relieving participants' burden of keeping a detailed record of medication intake and bodily functions. Instead, AI technology can be used for video monitoring to automatically collect and compile patient data. In addition, AI has the capability to analyze data to discover why a clinical trial may have failed.

However, further research needs to be conducted. As Dr. Harrer stated, "Major further work is necessary before the AI demonstrated in pilot studies can be integrated in clinical trial design. Any breach of research protocol or premature setting of unreasonable expectations may lead to an undermining of trust—and ultimately the success—of AI in the clinical sector."

For More Information

Harrer S, Shah P, Antony B & Hu J (2019). Artificial intelligence for clinical trial design. Trends Pharmacol Sci. [Epub ahead of print] DOI:10.1016/j.tips.2019.05.005

Image Courtesy of Creative Commons. Licensed Under CC-BY-SA-3.0


Depression and Suicide Risk in Oncologists: Daniel...
Mystery Behind 5-FU Resistance Solved

Related Posts

© Copyright 2019 i3 Health. All rights reserved.