New Zealand-based medtech startup HeartLab has raised $2.45 million in seed funding that it says will help the company expand its AI-powered heart scanning and reporting platform to cardiologists in the United States early next year.
HeartLab offers an end-to-end solution to echocardiograms, the ultrasound tests that doctors use to examine a patient’s heart structure and function. Not only does software help sort and analyze ultrasound images to help doctors diagnose cardiovascular disease, but it also streamlines workflows for doctors by generating patient reports that can be added to a patient’s health record. could.
Will Hewitt, 21, started HeartLab when he was 18 years old studying applied mathematics and statistics at the University of Auckland and working as a researcher at the Auckland Bioengineering Institute. The idea for the startup came to him when he listened to cardiologists, and now co-founder, Patrick Glading explains how time-consuming and potentially inaccurate it is for doctors to manually review multiple scans everyday.
“You’ve got really repetitive manual work done by a highly trained professional,” Hewitt told . Hewitt said, “Initially, we decided to train the AI to do a very small part of the doctor’s job, which was to look at these scans and generate a few different measurements that the doctor would usually have to do himself. ” .
To replicate the difficult process doctors were doing, HeartLab built its own in-house labeling tool with sonographers, which includes step-by-step guides and prompts for collecting data on a range of different measurements . Hewitt said the initiative is one of the most valuable engineering efforts the company has invested in to date because it has led to cross validation, which is used to test the ability of machine learning models to predict new data. , as well as flag problems. Like selection bias and overfitting.
Once HeartLab was able to successfully replicate the scanning process, the company worked to expand its services in a way that would relieve doctors from the lack of further administration so that they could actually treat their patients. I can spend more time. Typically, doctors use a software tool that analyzes the images, another that visualizes the patterns and another that actually writes the report, Hewitt says. HeartLab’s platform, called Pulse, can now condense those processes into one software.
Cardiologists and sonographers at four different sites in New Zealand are now testing HeartLab’s technology, which also awaits regulatory approval from the US Food and Drug Administration. HeartLab expects FDA approval of Pulse by the first quarter of 2022, when the startup could begin selling a SaaS product.
“To begin with, we want to talk to small and medium clinics in the US,” Hewitt said. “We have actually found that our product is most popular in those clinics because it replaces more software than in a large clinic. A large clinic has already had to purchase some of these bits of software, a Compared to smaller clinics, this is stuff they couldn’t access anyway. So when we move to the States, we mostly want to start shipping to those types of users, while we’re expanding our value proposition for larger clinics. Presenting in the best possible way.
Hewitt says this round of funding will help the startup hire 10 more staff members to join the existing 13-member team in Auckland. Having more technical talent on board will help HeartLab grow its product offerings. Right now, Pulse is at the point where it sees so many scans and takes so many measurements that it can get through the process faster than a doctor can and actually pick out patterns that a doctor won’t see, According to Hewitt. The next step, with a good chunk of seed funding going, is to learn how to diagnose the disease, rather than just being able to pinpoint it.
“How exactly do we provide something that usually requires doctors to order another scan?” Hewitt said. “One of the key ideas with AI is that you can create mappings from low-resolution images like ultrasound. How can we try to learn a pattern from an ultrasound that you can see from an MRI, for example?
If HeartLab can figure out how to gather advanced information from echocardiograms instead of MRIs, it will be able to save hospitals, clinics and patients a lot of money. Each cardiac MRI can cost around $1,000 to $5,000, which is about five times the price of an echocardiogram.
“I would say the biggest challenge for us is how can we transform from a company that can successfully distribute products to a few local clinics at the moment to actually create a product that will appeal to a lot of users. Really good experience and different hospital?” Hewitt said.
The demand for such devices is increasing due to advances in early diagnosis and imaging technology such as Heartlabs’. As a result, the global AI-enabled medical imaging solutions market is expected to reach $4.7 billion by 2027. By expanding its reach to the US, where heart disease is the leading cause of death, HeartLab is poised to take a big part of it. Pie.
In total, HeartLab has raised about $3.2 million in publicly-funded funding, including a pre-seed of about $800,000 led by Icehouse Ventures with support from Founders Fund, a San Francisco-based VC firm, which announced Thursday in a round. led. Icehouse Ventures also contributed to the oversubscribed seed round, along with another New Zealand firm Outset Ventures and private investor and CEO of design platform Figma, Dylan Fields.
“The use of AI in medicine is reducing the pressure on health systems and ultimately saving lives,” Founders Fund Partner Scott Nolan said in a statement. “The HeartLab team has created a really compelling AI-powered platform that doctors love to use.”