Utilizing Augmented Intelligence and ML to Deal with High Placebo Response


Details
Utilizing Augmented Intelligence and ML To Help Pharmaceutical Companies Deal with High Placebo Response and Sub-Population Response Effects
NetraPharma has access to machine learning technology that utilizes standard methods such as gradient boosting and deep neural networks in addition to novel proprietary methods that have been designed to overcome the complexities inherent when dealing with patient populations. Common obstacles that we help pharmaceutical companies deal with are unexpectedly high placebo response and inefficacy for the whole patient population. We provide aid to these difficulties by creating models that help predict who will be placebo responders and models that identify patient subpopulations of actual responders. Together, models like these can rescue clinical trials that would otherwise fail or have already failed. Our ability to extract subpopulations is made possible by a new paradigm of machine learning in addition to a process we call NetraPlay that allows pharmaceutical scientists and clinicians to interact with data in a unique and powerful way via augmented intelligence, where human and machine intelligence empower each other. We will discuss our innovations and review some recent work.
About Joe:
Dr. Joseph Geraci is a mathematical physicist with a background in quantum computation, quantum and classical machine learning, oncology, and Neuropsychiatry. He holds an adjunct position at Queen's University in the department of Molecular Medicine. He has led machine learning teams for both medical and financial applications. Dr. Geraci is currently the CEO of NetraMark Corp which is a machine learning startup in Toronto specializing in the pharmaceutical industry. He created a novel paradigm for machine learning which allows for the quick discovery of subpopulations in complex heterogeneous data and which can learn from small data sets. He utilizes this technology to personalize medications and resurrect failed drugs.

Utilizing Augmented Intelligence and ML to Deal with High Placebo Response