THANK YOU FOR SUBSCRIBING
Pharma Tech Outlook | Tuesday, January 28, 2020
Big Data and AI technologies complement each other, as AI can help synthesize and analyze ever-growing data. AI-enabled capabilities such as data integration and interpretation, pattern recognition, and evolutionary modeling are critical for collecting, normalizing, analyzing, and harnessing growing data mountains that fuel the development of modern therapy. Artificial intelligence has many potential applications in both short- and long-term clinical trials. AI technologies enable critical innovations to transform clinical trials, including the seamless integration of phase I and phase II trials, the development of new patient-centered endpoints, and Real-World Data collection and analysis.
Clinical trials advancement
Stay ahead of the industry with exclusive feature stories on the top companies, expert insights and the latest news delivered straight to your inbox. Subscribe today.
Clinical trial AI transformation begins with protocol development. It includes reducing or eliminating results that may be more responsive to change than traditional methods and using remotely connected technologies that eliminate patients’ need to travel long distances for site visits. Reliance on conventional site-based outcome assessments can result in suboptimal protocol design, slow enrolment, and low patient retention, resulting in higher test costs or even a doomed program.
Incorporating AI into big data can transform insights gleaned from massive amounts of real-world data (RWD) into protocol designs. Objective data collected in real-time from devices and sensors worn by individuals as they go about their daily lives can provide more meaningful clinically relevant insights and evaluate and develop trial goals, endpoints, and procedures.
Historically, researchers assessed patient progress through verbal or written patient evidence during clinical visits and direct clinical observations.
Subjective evidence may be unreliable, subject to inter-and intra-rater variability, and lack sufficient analytical and decision-making information. While patient-reported outcomes are an essential component of any trial, adding objective data to contextualize subjective evaluation is critical, especially when using machine learning and artificial intelligence platforms.
More in News