Artificial intelligence is getting a lot of attention for its role in drug discovery, where it is designed to speed up the process of identifying targets and molecules that can anesthetize them. But that’s just one of the places where AI is taking hold in the life sciences. A panel at the MedCity News INVEST Digital Health conference discussed how artificial intelligence can solve other pain points for biopharma companies.
Steve Prewitt, senior vice president and global head of digital innovation at Sumitomo Pharma Americas, said most of the new technology for clinical trials is for project management. He doesn’t see many good tools to help with clinical trial strategy — how to design the study to make trade-offs to improve recruitment and improve outcomes. As an example, he pointed to a Sumitomo study testing a schizophrenia drug in adolescents. The process required an overnight stay. But Prewitt said it’s difficult to get parents of an adolescent with newly diagnosed schizophrenia to commit to a sleepover. Recruiting students was therefore difficult.
Prewitt said that in a phase 3 trial for a general indication, most of the costs are not for recruiting a patient. The main cost is elapsed time. Every day there is a trial period, he spends money. Sumitomo is doing a lot of work trying to shorten sample times. For example, the company is looking for doctors who might have access to certain groups of patients. The firm also analyzes patient recruitment to find ways to recruit patients more quickly, which in turn reduces study costs.
Massive Bio’s technology uses AI to connect cancer patients to clinical trials. CEO and co-founder Celine Kurnaz said that for a cancer clinical trial that tests a drug that doesn’t require a specific biomarker, it costs about $65,000 to find a patient. But for a biomarker-based study, it costs about $150,000 to find each patient. Kurnaz said she has seen drug companies pay $2 million per patient in studies that require a specific rare biomarker.
“It’s the extent of the cost structure that we’re talking about the burden on pharma to find the right patient in oncology,” she said.
Kurnaz said it takes about 25 minutes to manually screen one patient for a clinical trial. With its technology, Massive Bio tries to reduce this time to just over a minute. But Kurnaz noted that even before clinical trial participants are processed, the first step is to find them. The company’s technology can mine de-identified patient data to find potential participants in clinical trials.
Sorcero’s AI platform provides life sciences companies with analytics and insights to inform decision-making in a range of areas, such as regulatory issues and market access. CEO Dipanvita Das compared the approach to how the retail industry analyzes data to gain insights into customers and their behavior. One key difference between the retail industry and the life sciences sector is that life sciences data is not stored in any one place. Data can be found in many places, such as electronic health records, payer information, peer-reviewed articles, and regulatory bodies.
Despite the differences in data, Das said the life sciences industry could still learn from the retail sector. Retailers have reached a level of understanding of customer preferences, down to the colors they like for shoes and the channels they choose to make their purchases. This is a level of detail that life sciences service and product providers must achieve.
“When you look at this, you see a lot of possibilities, not only [for] AI, but the technology itself,” Das said.
Photo by MedCity News