Triomics Raises $15M to Automate Oncology Workflows with GenAI Platform

Triomics, a San Francisco-based startup, has secured $15 million in funding to revolutionize oncology workflows. The funding came from Lightspeed Venture Partners, Nexus Venture Partners, General Catalyst and Y Combinator.

Led by co-founders Sarim Khan (CEO) and Hrituraj Singh (CTO), Triomics harnesses the power of their proprietary Generative AI models, known as OncoLLMTM, and specialized software to automate and scale oncology data processing.

The current manual process of searching through patient health records to find suitable clinical trials or care pathways is time-consuming and inefficient. Triomics aims to change this by applying their framework to develop institution-tuned large language models, OncoLLM™, and use case-specific software. This approach enables cancer centers to streamline workflows, match patients to clinical trials, and improve the quality of care operations.

Sarim Khan (CEO) and Hrituraj Singh (CTO), both former college friends with backgrounds in biotech research and AI, recognized the need for more efficient data analysis in oncology. While traditional software could handle structured medical data, they saw an opportunity to leverage recent advances in Generative AI to analyze the vast amount of unstructured data found in doctors' free-text notes. This innovation has the potential to significantly reduce clinical delays, improve patient outcomes, and enhance overall healthcare delivery in oncology.

“Triomics is leveraging existing healthcare datasets and Generative AI to empower hospital staff to automate clinical trials and streamline cancer center workflows,” said Dev Khare, Partner at Lightspeed Venture Partners. “We are excited to back Triomics in this important mission.”

After collaborating with researchers from the Medical College of Wisconsin to develop OncoLLM™, the model can identify 90% of eligible patients for clinical trials in just minutes, a process that would traditionally take qualified nurses days or even weeks. Additionally, Triomics' AI can extract structured data from unstructured notes with similar or higher accuracy compared to proprietary models like GPT4 or Claude, all while being 40 times more cost-effective.

Triomics has also recently published the results of its information retrieval engine for oncology, demonstrating its superiority. Their engine outperforms other state-of-the-art retrieval models by 1.5-2 times, highlighting Triomics' commitment to innovation and excellence in the field.

“Our investments in our core areas of focus have been deliberate," commented Hrituraj Singh. "We have successfully merged expertise in two complex functional areas: our AI researchers, who are specialized in customizing language models to specific domains, and our clinical staff, who have decades of oncology-specific experience. As a result, our software can complement the strengths of these advanced models while also proactively addressing potential flaws, all with the intricacies of cancer research and care in mind.”