In partnership with

Today’s startup is all about making a big impact at the lowest price point possible, thanks to some clever machine learning.

Read on to learn all about Concepto NIPT.

Fun fact: I first came across the company’s co-founder Atal Malviya when one of his previous startups went through the Ignite100 accelerator… a whole 15 years ago. It’s always interesting to see what entrepreneurs come back with…

– Martin

Investor-ready updates, by voice

High-stakes communications need precision. Wispr Flow turns speech into polished, publishable writing you can paste into investor updates, earnings notes, board recaps, and executive summaries. Speak constraints, numbers, and context and Flow will remove filler, fix punctuation, format lists, and preserve tone so your messages are clear and confident. Use saved templates for recurring financial formats and create consistent reports with less editing. Works across Mac, Windows, and iPhone. Try Wispr Flow for finance.

Try Wispr Flow

Concepto NIPT is using machine learning to bring prenatal genetic testing to the whole world

Non-invasive prenatal testing (NIPT) is a popular way of checking unborn babies for genetic anomalies early in a pregnancy. But the cost to deliver these tests means they aren’t accessible to all who could benefit from them.

Now Concepto NIPT is developing a new version of the test that could significantly cut costs. This could open the tests up to many more people around the world, including in developing nations. It could also potentially make them available to more NHS patients in the UK than is currently the case.

To do this, the company aims to bridge the gap between two existing ways of conducting NIPT tests.

Currently there’s a choice between NGS-based (next-generation sequencing) tests or PCR (polymerase chain reaction) tests. NGS tests are expensive but incredibly accurate, while PCR tests cost less but are far less accurate.

Concepto NIPT co-founder Atal Malviya says an algorithm being developed by the company will combine the accuracy of NGS with the cost benefits of PCR.

Once fully developed, the process will involve a blood sample going through a PCR test in a lab. The data produced by this test will then pass through the algorithm which will produce results as accurate as an NGS-based test.

To develop the tech, Malviya says the company is using an approach that takes two blood samples from the same patient. One is run through an NGS test, the other is run through a PCR test. The algorithm training process spots the difference in the outcomes coming from both tests.

Over time, patterns in the gaps between an NGS test and a PCR test start to emerge, with the ultimate goal that the PCR test can be ‘filled in’ to the accuracy of an NGS test using the algorithm.

The story so far

Malviya has a long history of entrepreneurship. After completing an MBA in 2010, he launched Odimax, a tech startup focused on data analytics.

Since selling that company in 2015, he has largely been working in the healthcare domain. This has included operating some ultrasound testing clinics as a franchisee and investing in a few startups, including Medwise AI, a startup we wrote about in the early days of this newsletter.

Malviya co-founded Concepto NIPT with Eileen Flatley, an expert in the NIPT space. The pair previously ran a Covid testing business together. The new company was started a year ago and already operates as an NIPT test provider using the accurate but expensive NGS tech.

“We wanted to reach out in the market and establish ourselves as a trusted provider of NIPT, while at the same time knowing that there is a clear gap of the cost and accuracy, and working on that in parallel. So we are taking a less traditional route than a typical startup,” Malviya says.

“We realised that if given a chance, if there was no cost constraint, how many women would take this test? Everybody. 99.9%.”

So far, Concepto NIPT has developed an initial prototype for its new technology, trained on synthetic data. The plan for this year is to work with more real patient data as they move towards validating the algorithm.

Subscribe to Premium to read the rest.