For cancer patients, drugs given in clinical trials may help save or extend life.
But despite hundreds trials in the United States each yr 3% to 5% eligible patients are involved in research into latest treatments.
Triomics, a generative artificial intelligence startup, says it will possibly significantly reduce the time it takes for doctors to match patients to tests.
Physician recommendations are often key to patient recruitment. However, busy oncologists and nurses often lack time to review all clinical trials that could be appropriate for their patients.
I’m not a doctor, so I do not know the challenges that oncology medical staff face on a each day basis. But unfortunately, I know from my very own experience how difficult it is to find clinical trials involving cancer patients. I spent countless hours browsing Clinicaltrials.gov, a website and database containing hundreds of ongoing trials involving my father. And just in March, I spent half a Saturday trying to find a clinical trial for a friend who has stage IV cancer. Her doctor only suggested one attempt, so she asked me if there have been other options.
Because most clinical trials have complex criteria, there are often dozens of things that qualify for trial participation, equivalent to cancer stage, mutations, and previous treatments. It often takes many hours for medical staff to manually review a patient’s medical records to find an appropriate clinical trial. However, due to a shortage of oncology specialists, many cancer patients are not offered access to the program or miss their eligibility period.
The company was founded by former MIT biotechnology researcher Sarim Khan and Adobe artificial intelligence scientist Hrituraj Singh. The pair, who have been friends since college, decided to build Triomics in 2021 after realizing that advances in generative AI and LLM could help extract data from electronic health records (EHRs) to help find the right fit clinical trials for cancer patients in minutes, not hours. .
Khan and Singh entered Y Combinator in the winter of 2021 and began working on an LLM system built specifically for cancer centers and oncology departments in hospital systems.
Three years later, Triomics says six cancer centers and hospitals are actively using or piloting the LLM program, with plans to double that number by the end of the yr. And now the company has raised $15 million in Series A funding from Lightspeed, Nexus Venture Partners, General Catalyst and Y Combinator to help it proceed to expand its platform and make it available to latest customers.
While reducing the time it takes to match patients to clinical trials may seem to be the most beneficial use of Triomics software, Khan says Triomics is much greater than just a clinical trials company. “Doctors use it for several different things that I could go on and on about,” he said.
After Triomics’ LLM, which the company calls OncoLLM, “reads” a patient’s medical records, the data might be used to prepare doctors and other medical staff for patient visits or to submit cancer data with details of affected organs and stage of progression to state regulatory agencies.
Of course, Triomics is not the only company dealing in this area. Other startups focused on AI clinical trial matching include Deep 6 AI, QuantHealth, Trajectory
Khan, nevertheless, believes that Triomics is one of the few startups processing big data specifically for cancer centers.