Using Data Science to Forecast Clinical Trial Outcomes may Help Biomedical Stakeholders De-Risk their Portfolios

A new study published in the inaugural issue of the Harvard Data Science Review, by researchers from the Massachusetts Institute of Technology, applies machine-learning and statistical techniques to predict the outcomes of randomized clinical trials for new drug and device candidates. In addition to the publication, the software used in the study will be made publicly available with an open-source license here. The research is part of an ongoing collaboration between the MIT Laboratory for Financial Engineering (LFE) and Informa Pharma Intelligence, named Project ALPHA (Analytics for Life-sciences Professionals and Healthcare Advocates). Project ALPHA leverages Informa datasets from Citeline and machine learning to train and validate its predictive models, with the goal of providing timely and more accurate estimates of the risks and rewards of clinical trials to the entire biopharma ecosystem. The ultimate goal of the project is to help patients and their families by developing analytics that allow investors, biopharma professionals, regulators, and patient advocates to better manage the tremendous risks of drug and device development. “Everyone is affected by the risk of a drug failing in its clinical trial process,” says Andrew W. Lo, the study’s senior author and director of MIT’s LFE as well as a Principal Investigator at the Computer Science and Artificial Intelligence Laboratory (CSAIL). Kien Wei Siah and Chi Heem Wong, two LFE/CSAIL Ph.D. students who co-authored the publication, observed that “You can’t manage what you don’t measure, so this is a new tool for measuring the risk of clinical trials more accurately, allowing all stakeholders to plan more effectively for these risks.”

Spotlight

Other News
Big Data

Airbyte Racks Up Awards from InfoWorld, BigDATAwire, Built In; Builds Largest and Fastest-Growing User Community

Airbyte | January 30, 2024

Airbyte, creators of the leading open-source data movement infrastructure, today announced a series of accomplishments and awards reinforcing its standing as the largest and fastest-growing data movement community. With a focus on innovation, community engagement, and performance enhancement, Airbyte continues to revolutionize the way data is handled and processed across industries. “Airbyte proudly stands as the front-runner in the data movement landscape with the largest community of more than 5,000 daily users and over 125,000 deployments, with monthly data synchronizations of over 2 petabytes,” said Michel Tricot, co-founder and CEO, Airbyte. “This unparalleled growth is a testament to Airbyte's widespread adoption by users and the trust placed in its capabilities.” The Airbyte community has more than 800 code contributors and 12,000 stars on GitHub. Recently, the company held its second annual virtual conference called move(data), which attracted over 5,000 attendees. Airbyte was named an InfoWorld Technology of the Year Award finalist: Data Management – Integration (in October) for cutting-edge products that are changing how IT organizations work and how companies do business. And, at the start of this year, was named to the Built In 2024 Best Places To Work Award in San Francisco – Best Startups to Work For, recognizing the company's commitment to fostering a positive work environment, remote and flexible work opportunities, and programs for diversity, equity, and inclusion. Today, the company received the BigDATAwire Readers/Editors Choice Award – Big Data and AI Startup, which recognizes companies and products that have made a difference. Other key milestones in 2023 include the following. Availability of more than 350 data connectors, making Airbyte the platform with the most connectors in the industry. The company aims to increase that to 500 high-quality connectors supported by the end of this year. More than 2,000 custom connectors were created with the Airbyte No-Code Connector Builder, which enables data connectors to be made in minutes. Significant performance improvement with database replication speed increased by 10 times to support larger datasets. Added support for five vector databases, in addition to unstructured data sources, as the first company to build a bridge between data movement platforms and artificial intelligence (AI). Looking ahead, Airbyte will introduce data lakehouse destinations, as well as a new Publish feature to push data to API destinations. About Airbyte Airbyte is the open-source data movement infrastructure leader running in the safety of your cloud and syncing data from applications, APIs, and databases to data warehouses, lakes, and other destinations. Airbyte offers four products: Airbyte Open Source, Airbyte Self-Managed, Airbyte Cloud, and Powered by Airbyte. Airbyte was co-founded by Michel Tricot (former director of engineering and head of integrations at Liveramp and RideOS) and John Lafleur (serial entrepreneur of dev tools and B2B). The company is headquartered in San Francisco with a distributed team around the world. To learn more, visit airbyte.com.

Read More