TECHNOLOGY

How AI simplifies data management for drug discovery


Calithera is conducting registered clinical trials on its products to study its safety, whether they are effective in patients with certain gene mutations, and how well they work with other therapies. The company needs to collect detailed information on hundreds of patients. While some of its experiments are in the early stages and involve a small number of patients, others span more than 100 research centers around the world.

“In the world of life sciences, one of our biggest challenges is the huge amount of data we create, more than any other business,” said Behruz Najafi, Kalithera’s chief information technology strategist. (Chief Information and Technology Officer at Najafi Health-Care Tech Company Innovio.) Calithra must store and manage data while making sure it is readily available when needed, even a few years from now. It must comply with specific FDA requirements regarding how data is created, stored and used.

Even seemingly simple things like upgrading a file server must follow the strictly defined FDA protocol with multiple testing and review steps. Najafi says all of this consent-related data hassle can add 30% to 40% to the overhead of a company like his, both in terms of direct costs and staff time. These are assets that could otherwise be put to further research or other value-added activities.

Callithera leaves much of that extra cost behind, and Najafi calls it a secure “storage container,” a protected area for controlled content, part of a larger cloud document management application, powered by artificial intelligence. AI never sleeps, never gets bored, and can learn to distinguish between hundreds of different types of documents and data.

Here’s how it works: Clinical or patient data is kept in the system and scanned by AI, which recognizes specific features that relate to accuracy, completeness, compliance with regulations, and other aspects of the data. AI can flag when there is a missing test result, or when a patient does not submit the required diary entry. It knows who is allowed to access certain types of data and what they are and is not allowed to do it with them. It can detect ransomware attacks and stop them. And it can automatically document everything to the satisfaction of the FDA or any other regulatory body.

“This approach takes away the burden of our consent,” Najafi said. When many of its research sites appear on the data platform, Calithra knows that AI will ensure that it is safe, complete and compliant with all regulations, and that any flag will give trouble

Drug discovery data can be handled in accordance with research requirements and regulatory requirements, as Najafi sees, difficult and expensive. The life-science industry may borrow data management strategies and platforms for other industries, but they need to be modified to manage security and legitimacy levels and detailed monitoring pathways, a way of life for drug developers. AI can integrate these tasks, improve security, consistency, and data validity – freeing up drug companies and research firms to apply them to their core missions.

A complex data management environment

Regulatory compliance helps ensure that new drugs and devices work safely and on purpose. It protects the privacy and personal information of thousands of patients participating in clinical trials and post-market studies. Drug developers must adhere to the same standard practice for documenting, auditing, verifying, and protecting every piece of information associated with clinical trials, regardless of their size বি large global organizations or small start-ups trying to market a single product.

When researchers run a double-blind study, the gold standard for proving the effectiveness of a drug, they have to keep their patients ’information secret. But they must then easily de-anonymize the data so that it is identifiable, so patients in the control group can take the test drug, and so the company can track কখনও sometimes year after year কী how the product is used in the real world.

The burden of data management falls on emerging and medium-sized bioscience companies, says Ramin Farasat, chief strategy and product officer at Silicon Valley software company Ignite, which builds and supports the AI-enabled data management platform used by Calithra and several others.

“This approach takes away the burden of consent from us,” Najafi said. Once on the data platform of many of his research sites, Calithra knows that AI will ensure that it is safe, complete and in compliance with all regulations, and will identify any problems.

Download the full report.

This content was produced by MIT Technology Review Custom Content Force Insights. It was not written by the editorial staff of MIT Technology Review.



Source link

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button