Team
Two juniors from Naperville, Illinois.
That is the whole company. We would rather you knew that up front.
Akshobya Rao
Co-founder
Junior at Neuqua Valley High School. Works on the rule compiler, the training pipeline and the calibration, and writes most of the interface.
Abhinav Byju
Co-founder
Junior at Neuqua Valley High School. Works alongside Akshobya on the product and on getting the tool in front of the people who screen patients for a living.
Why we built it
Eligibility criteria are public. They are also written for trial coordinators, published as unformatted prose, and routinely dozens of conditions long for a single study. People who might qualify for a trial never get as far as contacting a site, because the first step is reading something that was not written for them.
We spent a year before this on independent work in non-invasive diagnostics, which is where we got used to an idea that runs through everything here: a measurement is worth nothing until you know how wrong it is allowed to be.
Why it refuses to guess
The easy version of this product answers every criterion and sounds confident. We did not build that one. A deterministic rule compiler makes every verdict, the machine learning layers are only allowed to group and surface what the compiler could not read, and below a fixed confidence threshold the system abstains and shows you the sentence instead.
Every search reports how much of the eligibility text it could not read. A tool that hides its own coverage is misrepresenting itself, and in this domain that is not a small thing to get wrong.
What we are not
We are not clinicians, and Inclusion Health is not a medical device. It gives no diagnosis, no advice and no probability of enrolment. A study that is not ruled out is not a study you are eligible for. The tool has never been clinically validated, which is the single largest gap in the project and the thing we are actively looking for help with.
We say all of this on the landing page, in the first-run agreement, in the Terms and beside every result. Stating it here as well is not modesty. It is the same argument the product makes: say what you cannot support, and the things you can support become worth believing.
Working with us
If you run trials, screen patients, or teach people who do, there are three ways to help that range from one hour of your time to a co-authored validation study.
hello@inclusionhealth.xyz reaches both of us. There is no form and no calendar link.