This article briefly:
Big pharmaceutical company Johnson & Johnson is using AI to recruit a more diverse group of clinical trial participants.
AI software aims to make recruiting of minorities easier through AI clinic consultation maps.
Some companies using or developing clinical trial technology believe that AI is only effective when guided by human experts.
Pharmaceutical giant Johnson & Johnson (J&J) has begun using artificial intelligence (AI) to make clinical trials more diverse, and it hopes its technology will make treatments more effective for marginalized communities.
Johnson & Johnson’s artificial intelligence created a heat map of clinics frequented by Black people to recruit some patients for clinical trials that previously kept disadvantaged communities from participating due to cost and distance, hindering the fuller development of drugs.
Johnson & Johnson plans to increase artificial intelligence trials
The new technology helped increase participation of black cancer patients by 5.2%, a trend J&J hopes will continue. It plans to increase diversity in 50 trials first, and then 100 trials by 2024.
Trials that do not test effectiveness across sex, race, and age can widen health disparities and reduce the effectiveness of a drug. Large pharmaceutical companies often recruit existing academic medical centers, whose populations may not be diverse, to ensure equitable treatment.
About three-quarters of participants in drug trials approved in 2020 were white. Eleven percent were Hispanic and 8% were Black.
Artificial Intelligence Succeeds in Clinical Trials
Smaller pharmaceutical companies, known as “biotech” firms, are using AI in other ways. For example, Palo Alto-based Inceptive is testing whether AI can develop messenger RNA (mRNA) vaccines similar to the COVID-19 vaccine.
Artificial Intelligence in Clinical Trials | Source: HIT Consultants
COVID-19 vaccine maker Moderna recently affirmed the role of artificial intelligence in developing a COVID-19 vaccine. Recursion Pharmaceuticals has begun human trials of five new drugs, including one for the treatment of neurovascular disease.
However, since the advent of the Moderna vaccine, AI has not yet developed a drug with proven effectiveness in the real world. Scientific American pointed out in 2022 that the effectiveness of AI models depends on the data processing practices of researchers.
It recommends that AI models for clinical use be developed with input from patients and the U.S. Federal Drug Administration.Several companies, including Recursion competitor Exscientia, have also tempered expectations for AI’s capabilities.
Professor Andrew Hopkins, CEO of Exscientia, said the company would “focus on high-value” internal projects” that could lead to “significant therapeutic benefit.” Todd Rudo, chief medical officer of Clario, which develops endpoint technology for clinical trials, agreed that AI is little more than a tool.
“Ultimately, we need to remember that AI is not a panacea; AI is a methodology, a tool… As with any tool, finding the right tool for the right job always requires deep scientific expertise.”
Do you have anything to say about J&J’s use of AI in clinical trials or elsewhere? #人工智能 #临床试验