How artificial intelligence simplifies data management for drug discovery


Calithera is conducting registered clinical trials of its products to study their safety, whether they are effective in patients with specific gene mutations, and how effective they are in combination with other therapies. The company must collect detailed data on hundreds of patients. Although some of its trials are in the early stages and involve only a few patients, others span more than 100 research centers around the world.

“In the life sciences, one of the biggest challenges we face is that we generate more data than any other business,” said Behrooz Najafi, chief information technology strategist at Callithera. (Najafi is also the chief information and technology officer of Innovio, a healthcare technology company.) Callithera must store and manage data while ensuring it is always available when needed, even after a few years. It must also meet FDA’s specific requirements on how to generate, store, and use data.

Even something as simple as upgrading a file server must follow a strictly defined FDA protocol, which includes multiple testing and review steps. Najafi said that all of these compliance-related data disputes will increase the management expenses of companies like him by 30% to 40%, including direct costs and staff time. These resources could have been used for more research or other value-added activities.

Calithera avoids most of the additional costs and greatly improves the ability to track data by putting the data in what Najafi calls a secure “storage container”. This is a protected area for regulated content and a larger cloud document management application. Part of the program is mainly composed of artificial intelligence. AI never sleeps, never gets bored, and can learn to distinguish hundreds of different types of documents and data forms.

It works as follows: clinical or patient data is put into the system and scanned by artificial intelligence, which recognizes specific characteristics related to the accuracy, completeness, compliance, and other aspects of the data. AI can flag when test results are missing or the patient has not submitted the required diary entries. It knows who can access certain types of data and what they are and what they are not allowed to do with it. It can detect ransomware attacks and stop them. It can automatically record all of this to the satisfaction of the FDA or any other regulatory agency.

Najafi said: “This approach reduces our compliance burden.” Once the data from its many research sites enters the platform, Callithera knows that AI will ensure it is safe, complete, and comply with all regulations, and will flag any issues.

As Najafi has observed, managing drug discovery data to meet research needs and regulatory agency requirements can be burdensome and expensive. The life sciences industry can learn from data management technologies and platforms developed for other industries, but they must be modified to handle security and verification levels and detailed audit trails, which is a way of life for drug developers. Artificial intelligence can simplify these tasks and improve the security, consistency and effectiveness of data-freeing up expenses for pharmaceutical companies and research institutions to apply to their core tasks.

Complex data management environment

Compliance helps ensure that new drugs and devices are safe and work as expected. It also protects the privacy and personal information of thousands of patients participating in clinical trials and post-marketing research. Regardless of the size-whether it is a large global conglomerate or a small start-up company trying to bring a single product to market-drug developers must follow the same standard practices to record, audit, verify and protect everything related to clinical trials information.

When researchers conduct double-blind studies (the gold standard for proving the efficacy of drugs), they must anonymize patient information. But they must easily deanonymize the data later to make it identifiable so that patients in the control group can receive the test drug, so the company can track (sometimes for several years) the performance of the product in actual use.

Ramin Farassat, chief strategy and product officer at Silicon Valley software company Egnyte, said that the burden of data management falls heavily on emerging and mid-sized bioscience companies. Egnyte is a company that manufactures and supports artificial intelligence data used by Calilithera and hundreds of other life companies. Software company that manages the platform. Scientific company.

“This approach reduces our compliance burden,” Najafi said. Once the data from its many research sites enters the platform, Callithera knows that AI will ensure its safety, integrity, and compliance with all regulations, and will flag any issues.

download Full report.

This content was produced by Insights, the custom content division of MIT Technology Review. It was not written by the editors of MIT Technology Review.


Source link