How AI simplifies data management for drug discovery


Calithera conducts registered clinical trials of its products to study their safety, whether they are effective in patients with certain genetic mutations, and how well they work with other treatments. The company must collect detailed data on hundreds of patients. While some of its trials are still in its early stages and involve only a small number of patients, others extend to more than 100 research centers worldwide.

“In the world of life sciences, one of the biggest challenges we face is the massive amount of data we generate, more than any other business,” says Behrouz Najafi, chief IT analyst at Kalythera. (Najafi is also the chief information and technology officer for healthcare technology company Innovio.) Calithera must store and manage data while making sure it’s readily available when needed, even years from now. It must also comply with Food and Drug Administration requirements for how data is generated, stored, and used.

Even seemingly simple things like upgrading a file server must follow a strictly defined FDA protocol with multiple testing and review steps. Najafi says all of these compliance controversies can add 30% to 40% to the overhead for a company like his, in terms of direct cost and hours of employee time. These are resources that could otherwise be devoted to further research or other value-added activities.

Calithera has avoided much of that extra cost and greatly improved its ability to track its data by placing it in what Najafi calls a secure “storage container,” a protected area for structured content, part of a larger cloud document management application, largely driven by artificial intelligence. . AI never sleeps, never gets bored, and can learn to distinguish between hundreds of different types of documents and data forms.

Here’s how it works: Clinical or patient data is entered into the system and scanned by artificial intelligence, which learns about specific features related to accuracy, completeness, compliance with regulations, and other aspects of the data. AI can report when a test result is missing, or when a patient does not provide a required entry in the diary. It knows who is allowed to access certain types of data and what is and is not allowed to do so. It can detect and avoid ransomware attacks. It can document all of this automatically to the satisfaction of the Food and Drug Administration or any other regulatory body.

“This approach takes the burden of compliance off our shoulders,” Najafi says. Once the data is from the platform’s many search sites, Kalethera knows the AI ​​will make sure it’s safe, complete and compliant with all regulations, and will know about any issues.

Managing drug discovery data to match research needs and regulators’ requirements, Najafi notes, can be cumbersome and costly. The life sciences industry can borrow data management technologies and platforms developed for other industries, but they must be modified to handle levels of security, validation, and detailed audit trails, which are a lifestyle for drug developers. AI can simplify these tasks, and improve data security, consistency, and validity – freeing up the overhead for pharmaceutical companies and research organizations to implement their core mission.

Complex data management environment

Regulatory compliance helps ensure that new drugs and devices are safe and work as intended. It also protects the privacy and personal information of thousands of patients who participate in clinical trials and post-market research. No matter their size—huge global conglomerates or small startups trying to bring a single product to market—drug developers must adhere to the same standard practices of documenting, auditing, validating, and protecting every ounce of information associated with a clinical trial.

When researchers conduct a double-blind study, the gold standard for demonstrating drug efficacy, they have to keep patients’ information anonymous. But they must easily remove the data from an anonymous source at a later time, making it identifiable, so that patients in the control group can receive the test drug, and so the company can track — sometimes for years — how the product is performing in real use.

The burden of data management falls on emerging and mid-sized biosciences companies, says Ramin Firasat, chief strategy and product officer at Egnyte, a Silicon Valley software company that manufactures and supports the AI-enabled data management platform used by Calithera and hundreds of other life-companies Sciences.

“This approach takes the burden of compliance off our shoulders,” Najafi says. Once the data from its many search sites is in the platform, Calithera knows the AI ​​will make sure it’s safe, complete and compliant with all regulations, and will identify any issues.

download full report.

This content was produced by Insights, the dedicated content arm of the MIT Technology Review. It was not written by the editorial staff of the MIT Technology Review.



Source link

Leave a Reply

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