For cancer patients, medications given clinical trials can help save or prolong lives.
But despite thousands of trials conducted each year in the United States, only 3 to 5 percent of eligible patients enroll in research into new treatments.
Triomics, a generative AI startup, says it can significantly reduce the time it takes for doctors to match patients to trials.
Physician recommendations are often key to patient recruitment. However, busy oncologists and nurses often lack the time to learn about all the clinical trials that might be suitable for their patients.
I am not a doctor, so I do not know the daily challenges of oncology medical staff. But unfortunately I know from personal experience how difficult it is to find clinical trials for cancer patients. When my father was ill, I spent countless hours consulting clinicaltrials.gov, a website and database listing thousands of ongoing trials. And in March alone, I spent half a Saturday trying to find a clinical trial for a friend with stage IV cancer. Her doctor only suggested one trial, so she asked me if there were other options.
Because most clinical trials rely on complex criteria, eligibility often depends on dozens of factors, such as cancer stage, mutations, and prior treatments. Medical staff often need several hours to manually review a patient’s medical record to find an appropriate clinical trial. But due to a shortage of oncology professionals, many cancer patients are not offered to participate or miss their eligibility window.
Triomics was founded by Sarim Khan, a former biotechnology researcher at MIT, and AI scientist at Adobe Hrituraj Singh. The two men, friends since college, decided to create Triomics in 2021 after realizing that advances in generative AI and LLMs could help extract data from electronic health records (EHRs) to help find Appropriate clinical trials for cancer patients in minutes instead of hours. .
Khan and Singh joined Y Combinator in winter 2021 and began working on an LLM specifically designed for cancer centers and hospital systems’ oncology departments.
Three years later, Triomics says six cancer centers and hospitals are actively using or testing its LLM, and plans to double that number by the end of the year. And now the company has raised a $15 million Series A from Lightspeed, Nexus Venture Partners, General Catalyst and Y Combinator to help it continue to develop its platform and roll it out to new customers.
While reducing the time it takes for patients to be matched to clinical trials may seem like the most immediately useful application of Triomics software, Khan says Triomics is much more than a clinical trials company. “Doctors use it for several different use cases that I could go on and on about,” he said.
After Triomics’ LLM, which the company calls OncoLLM, “reads” the patient’s medical record, the data could be used to help prepare doctors and other medical staff for patient visits or to help submit data on cancer with details on the organs affected and the stage of development. progressions to state regulatory agencies.
Of course, Triomics is not alone in tackling this area. Other startups conducting AI clinical trials include Deep 6 AI, QuantHealth, Trajectory, among others.
But Khan believes Triomics is one of the few startups processing vast amounts of data sets specifically for cancer centers.
techcrunch
