Collaborating Authors

How Artificial Intelligence is Transforming Clinical Trial Recruitment


The medical world is shifting underneath our feet. To keep up with the rising demands of empowered patients, physicians and pharma businesses regularly test innovative treatments and medicines during rigorous clinical trials. But one misguided move can trigger a domino effect, such as when the wrong patients are selected for a clinical trial. Today's infographic comes to us from Publicis Health, and it highlights why the current model of clinical trial recruitment urgently needs to change. Clinical trials help to determine if a new treatment, drug, or device is safe for the larger patient population.

The Role of Artificial Intelligence in Clinical Trial Transparency – Certara


European and U.S. clinical trial data transparency initiatives -- such as EMA Policy 70 -- are creating additional disclosure compliance requirements for pharma and biotech companies. These transparency initiatives have, at their core, the distribution of clinical trial data for public consumption. Clinical trial data typically are contained within regulatory documents such as Clinical Study Reports (CSRs), Marketing Application Submission Documents (NDAs, MAAs, BLAs, etc.) and others. To achieve compliance with these mandates, pharma and biotech companies will need to anonymize and de-identify data sets in their clinical study reports and submission documents, produce research summaries suitable for a lay audience, and publish their clinical study information publicly. In this webinar, Synchrogenix President, Keith Kleeman will discuss how Artificial Intelligence (AI) and natural language recognition and processing are significantly improving the accuracy and efficiency of successfully anonymizing personally identifiable information, patient protected data, company confidential information and other sensitive information from clinical trial documents for public disclosure.

NIH redefines clinical trials, attracting critics


A new National Institutes of Health (NIH) policy aimed at boosting the rigor and transparency of clinical trials is triggering concerns among many behavioral scientists. They are worried that the agency's widening definition of clinical trials could sweep up a broad array of basic science projects studying the human brain and behavior that do not test treatments. The clinical trials designation would impose a raft of new requirements on work that has already passed ethics review, such as different standards for applications submitted for funding, and a mandate to report results on, Critics say that would result in wasted resources and public confusion. NIH officials say they are still determining which behavioral studies will be defined as clinical trials.

Artificial Intelligence Supports Clinical Operations in Oncology Studies


As the pharmaceutical and medical care industries move toward adoption of artificial intelligence technologies, new possibilities are arising for improvements in drug trials through streamlined clinical operations processes. Worldwide Clinical Trials' recent partnership with Deep Lens could provide evidence of how future drug studies can benefit from AI-driven technologies. A recent study estimates the average dropout rate for all clinical trials at 30%.1 Such patient discontinuation can necessitate exponential increases in patient numbers to achieve required levels of statistical significance. The goal is to minimize additional recruitment costs and delays by improving efficiencies during study execution. As clinical trial stakeholders seek to streamline clinical processes, artificial intelligence emerges as an innovative approach to improving patient monitoring and clinical care, as well as enhancing and accelerating end point detection.

Crowdsourcing a Comprehensive Clinical Trial Repository

AAAI Conferences

We present the open problem of building a comprehensive clinical trial repository to remove duplication of effort from the systematic review process. Arguing that no single organization has the resources to solve this problem, an approach based on crowdsourcing supplemented by automated data extraction appears to be the most promising. To determine the feasibility of this idea, we discuss the key challenges that need to be addressed.