For cancer patients, medicines given in clinical trials can help save or prolong their lives.
However, even though thousands of clinical trials are conducted in the United States each year, only 3% to 5% of eligible patients participate in investigations of new treatments.
Generative AI startup Triomics claims it can significantly reduce the time it takes for doctors to match patients with clinical trials.
A doctor's recommendation is often the key to patient enrollment. However, busy oncologists and nurses often do not have time to learn about all the clinical trials that may be appropriate for their patients.
I'm not a doctor, so I don't know about 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 became ill, I spent countless hours looking at a website and database called clinicaltrials.gov that lists thousands of ongoing trials. And just as he was in March, I spent half my Saturday looking for a clinical trial for a friend who has stage IV cancer. Her doctor only suggested one test so she asked me if there were any other options.
Most clinical trials have complex criteria, often including dozens of factors to determine eligibility, including cancer stage, mutations, and previous treatments. Medical staff often spend hours manually reviewing a patient's medical record to find the appropriate clinical trial. However, due to a shortage of oncology experts, many cancer patients are not encouraged to participate or miss out on participation.
Triomics was founded by former MIT biotech researcher Salim Khan and Adobe AI scientist Hrituraj Singh. The pair, who have been friends since college, are hoping advances in generative AI and LLM can extract data from electronic health records (EHRs) to find the right clinical trial for cancer patients in minutes instead of hours. In 2021, I decided to build Triomics. .
Khan and Singh joined Y Combinator in the winter of 2021 to work on developing an LLM built specifically for hospital system cancer centers and oncology departments.
Three years later, Triomics says six cancer centers and hospitals are actively using or piloting its LLM, and it plans to double that number by the end of the year. And now, the company has raised $15 million in Series A from Lightspeed, Nexus Venture Partners, General Catalyst, and Y Combinator to continue developing the platform and deploy it to new customers.
While reducing the time it takes to match patients to clinical trials may seem like the most directly valuable application of Triomics software, Khan says Triomics is more than just a clinical trial company. Is called. “Physicians are using this for several different use cases, and I could go on and on about that,” he said.
When Triomics' LLM (which the company calls OncoLLM) “reads” a patient's medical record, the data is used to help doctors and other medical staff prepare for the patient's examination, identify affected organs, It can be used to submit cancer data including stage details. Transition to State Regulatory Authority.
Of course, Triomics is not alone in this field. Other startups with AI clinical trial matching include Deep 6 AI, QuantHealth, and Trajectory.
But Khan believes Triomics is one of the few startups that processes large data sets specifically for cancer centers.