What you should know:
– Triomica company that leverages generative AI to revolutionize cancer care, today announced it has secured $15 million in funding led by prominent Silicon Valley companies like Speed of light, Nexus Venture Partners, General catalyst, And Y combiner.
– Triomics partners with leading academic cancer centers and researchers to develop benchmarks and best practices for generative AI performance and security. Triomics partners include the Collaboration for Oncology-focused LLM Training (COLT), a consortium of leaders from a dozen NCI-designated cancer centers, and Cancer Informatics for Cancer Centers (CI4CC).
Transforming oncology workflows with GenAI
Currently, oncology staff are grappling with manually searching through enormous amounts of patient data to identify appropriate clinical trials and treatment pathways. This tedious process often leads to:
- Delays in patient care: Manual data analysis can take hours per patient, which can result in missing critical clinical trials or biomarker-based treatments.
- Delays and inefficiencies: Health systems often experience delays in oncology workflows, impacting the overall quality of care.
- Supplier exhaustion: The overwhelming workload can contribute to provider dissatisfaction and burnout.
Triomics solution: OncoLLM™ and AI-based software
Triomics co-founders Sarim Khan (CEO) and Hrituraj Singh (CTO) recognized the limitations of existing software that only analyzes structured data. They identified the potential for generative AI to unlock the vast potential of unstructured medical data, such as doctor’s notes, which account for approximately 80% of patient information.
OncoLLM™: Unlocking the Power of Unstructured Data
Triomics has developed OncoLLM™, a generative AI model specifically trained on oncology data. In collaboration with researchers at the Medical College of Wisconsin, Triomics has demonstrated that OncoLLM™ can:
- Identify patients eligible for clinical trials in minutes: A process that would take trained nurses days or weeks is dramatically accelerated, potentially improving patient access to critical therapies.
- Extract unstructured note data with high accuracy: OncoLLM™ achieves similar or better accuracy compared to leading models like GPT-4 or Claude, at a significantly lower cost (40 times cheaper).
- Outperform other recovery models: Triomics’ information search engine has been shown to be 1.5 to 2 times more efficient than other state-of-the-art models.
Triomics software integrates AI into existing systems
OncoLLM™ powers the Triomics software suite, which seamlessly integrates with electronic health record (EHR) systems used by hospitals. This enables features such as:
- Triomic Prism: Automates patient-trial matching by pre-screening oncology patients for relevant clinical trials based on upcoming appointments.
- Triomic Harmony: Organizes and analyzes EHR data to support quality reporting, cohort analysis, and personalized cancer care (precision oncology).
Triomics plans to publish further research on the effectiveness of OncoLLM™ in various patient populations and healthcare settings.
