The key challenge was to gather raw and unstructured data and convert it into insightful analytics with recommendations for management on drug production.
About
Our client is a pharmaceutical and biotech giant delivering life-changing medicines globally. They‘ve already adopted AI to redefine medical science and look for better ways to discover, test, and accelerate potential drugs. Their new goal was to speed up the time to market for medicines, better document treatment outcomes, and decrease trial costs.
Project Overview
The client recognized that analytical data took a lot of work for scientists to find and access. This led to inefficiencies and duplication of effort. Even though the client has been proficient in using data from trials to analyze, interpret, and report on the safety and efficacy of the trial drug, they wanted to maximize the value of the data.
Our idea was for AI to provide greater access to knowledge, which helps improve collaboration, efficiency, and performance.
Custom large language models (LLMs) could improve the workflow to manage functions ranging from data interpretation to knowledge discovery. We suggested an algorithm that gathers all vital information in one place, identifies patterns on a large scale, and provides deep insights.
Results
We are still finetuning the algorithm to get better results based on historical data. The pilot tests showed decent results and improved workflow for users.
PROJECT INFO
Industry
Pharma
Location
Europe
Team Size
1 Project Manager, 1 Developer, 1 AI Engineer
Technologies
AI Predictive Models, LLM