NetraMark Holdings Inc. announces the release of NetraGPT. Through newly developed algorithms, NetraGPT builds upon the powerful hypotheses generated from the Company's proprietary Good Clinical Practice (GCP) validated AI/ML system, NetraAI. The power of the NetraAI system lies in its ability to learn about special combinations of variables that define patient subpopulations in relation to drug or placebo response and adverse effects, all of which are important considerations for clinical trials. NetraGPT now revolutionizes the power of NetraAI whereby the NetraAI output is fed into generative pre-trained (GPT) models utilizing Large Language Model (LLM) APIs. Currently, LLMs are being trained with a massive volume of data, with ChatGPT4 being trained on approximately 300 billion words of data, including medical literature. This innovation places NetraMark in a unique position to not only build upon the hypothesis and subpopulation definitions derived from NetraAI but to now also potentially discover further insights that leverage the power of LLMs and deliver the output reports in minutes vs. weeks. This creates an unprecedented opportunity for NetraMark to seamlessly integrate output from NetraAI and quickly convey potent insights about patient populations to clientele with heightened efficiency and explainability. NetraGPT ingests information about specific clinical trial patient subpopulations discovered by NetraAI. More specifically, this involves feeding the collection of variables, biological or otherwise, that are statistically significant for the discovered subpopulations of interest, based on the dependent variable, e.g., drug response, placebo response, placebo non-response, adverse event, etc. The resulting output of the NetraGPT module is a detailed human-readable report that leverages the power of LLMs and the massive corpus of medical literature to provide:
Output reports that begin to assemble in seconds and conclude within minutes, Improved explainability of the influential variables underlying discovered subpopulations, Additional insights delineating interconnections among variables, the response, and the disease state, References sourced from relevant and contemporary literature, Importantly, the process is transparent about the variables driving the specific patient subpopulations that can be clearly identified and validated through statistical inspection. This level of transparency is critical for sponsors, particularly when working with LLMs, as it allows human experts and trialists to audit parts of the hypothesis-generation artificial intelligence (AI) process and the LLM-generated report, to ensure the veracity of the generated insights and recommendations.