Aardvark released exploratory data from its stopped Phase 3 HERO trial in Prader-Willi syndrome after FDA lifted the hold, and plans a redesigned Phase 3.
|Articles|June 30, 2015
Mining Twitter Hashtags to Find Unknown Drug Issues
A team of scientists at the University of Vermont has invented a new technique for discovering potentially dangerous drug interactions and unknown side-effects using Twitter hashtags.
Advertisement
A team of scientists at the University of Vermont has invented a new technique for discovering potentially dangerous drug interactions and unknown side-effects using Twitter hashtags.
Previous studies have shown that Twitter can be mined for bad drug interactions, but the Vermont team advances this idea by focusing on the distinctive information contained in hashtags-like “#overprescribed,” “#kidneystoneprobs,” and “#skinswelling”-to find new associations. The overall goal of the project, supported by the National Science Foundation, was to discover is to discover any relationship between two drugs that is not known.
Using their new algorithm, the team has created a website that will allow an investigator to explore the connections between search terms (say "albuterol"), existing scientific studies indexed in PubMed-and Twitter hashtags associated with the terms and studies.
A report on how the algorithm works, and its preliminary discoveries, was published online, June 8, in the Journal of Biomedical Informatics.
Advertisement
Related to this article
Clinical trials capture data faster than ever, but the real bottleneck is the distance between data capture and a decision teams can trust.
In today’s ACT Brief, we examine why the future of AI in trials is a trusted orchestration system rather than a single model, how coordinators rate eSource-enabled workflows, and what a bipartisan bill proposes for reusable trial networks.
The Faster Clinical Trials Act would create an FDA Center for Clinical Trial Innovation and aims to cut trial costs and enrollment time by at least 30%.
Standardized measurement across five oncology centers found that clinical research coordinators rated eSource-enabled workflows positively (Overall Mean Satisfaction 5.79 of 7), with reduced manual entry and electronic data transfer earning strong marks, while perceived reduction in sponsor and monitor queries lagged as the one domain below threshold.
In this video interview, Rajneesh Patil, global head of AI, digital, and innovation in clinical development at Syneos Health, describes the industry’s trajectory toward a unified intelligence orchestration environment—and explains why the future isn’t one model that knows everything, but a trusted system that brings the right evidence to the right human decision.
In today’s ACT Brief, we examine how sites can avoid both fear-driven and overly aggressive AI adoption, why community-based research needs sustained financial investment, and why patient access matters more than organizational size.
Pacing obesity trial enrollment, anchoring eligibility to stable real-world therapies, and building site and physician relationships improve retention and data quality more than aggressive recruitment or restrictive exclusion criteria do.
Advertisement
Advertisement
Trending on Applied Clinical Trials Online
1
Building Standardized Evidence for eSource-Enabled Clinical Trials: Multi-Site Validation of a Clinical Research Coordinator Satisfaction Methodology
2
Where the Industry Is Headed as Clinical, Operational, and Real-World Data Connect
3
Bipartisan Bill Would Build Reusable Clinical Trial Networks, With a Focus on Rare Disease
4
Where AI Governance in Clinical Development Falls Short
5