- Wroclaw-based MX Labs is working on 2 smartphone apps: Heart Monitor and Beauty, which will assess patients’ skin, eyes and cardiovascular system
- Powered by AI, the apps only need a smartphone with a medium-quality camera and good lighting
- SMOK VC invested 500,000 USD in MX Labs
- The startup plans to further develop the AI for use cases in telemedicine and healthcare
Polish startup MX Labs received 500,000 USD (approximately 418,000 EUR) as pre-seed investment to develop an AI engine and smartphone apps that would allow users to diagnose their health in real-time.
“We are currently working on two mobile applications – ‘Heart Monitor‘ – which we will launch with the first set of Shen.AI-supported features in April, and ‘Beauty‘, which provides insight into skin aging and early prediction of common skin conditions”, Remigiusz Koscielny, CEO and co-founder of MX Labs, told ITKeyMedia.
Shen.AI is the startup’s platform that feeds computer vision and vital signs processing into an AI, for health and wellness monitoring, providing, according to MX Labs, near real-time display of several health parameters, biofeedback, preliminary diagnosis and recommendations. Heart Monitor will allow the self-diagnosis of hypertension and other non-communicable diseases (NCD – diseases that are not transmissible directly from one person to another – editor’s note), and minor ailments.
Koscielny says MX Labs’ apps will be free to download, with premium features unlocked as part of a subscription. He did not offer further information about the pricing model.
The investment, announced in February 2021, was led by SMOK Ventures, with participation from Verge HealthTech in Singapore (Joseph Mocanu), and several business angels: Pipedrive founders Ragnar Sass and Martin Tajur, as well Aaron Patzer, the founder of Mint.
“In 2021, they are planning (…) to test the market and get feedback from the community. The next step on the funding landscape is a seed round, and then a Series A, followed by Series B, but it is too early to predict the timeline, as MX Labs is a research-heavy project and a lot depends on the results from the research”, explains for ITKeyMedia Borys Musielak, founding partner at SMOK Ventures, adding that it is possible that the fund will be increasing its stake in the startup in the next years.
He foresees MX Labs might be looking at a vast, untapped market and has the potential to disrupt the entire medtech ecosystem. The value of the segment where they operate is “currently zero”, says Musielak, “but, if they are successful in bringing proactive health checks to the masses via mobile – without additional devices – they are going to build one of the most valuable companies ever created.”
If they are successful in bringing proactive health checks to the masses via mobile – without additional devices – they are going to build one of the most valuable companies ever created.
— Borys Musielak, founding partner at SMOK Ventures
How Does It Work?
Using the camera (of a smartphone/ tablet/ computer), the app transforms the user’s facial image into a 3D model, which is constantly tracked, resulting in a stable video of the patient’s facial texture. The images are processed to extract the colour information, which is then transposed into an rPPG signal – remote photoplethysmography, a contactless technique of recording blood pulsations in the skin blood vessels – to determine the exact heart pulse signal for every skin pixel. The AI analyses the timing of each pulse wave, it’s shape, amplitude, to determine blood pressure, risks related to cardiovascular health, as well as any potential skin or eye problems.
What is being monitored and determined?
- Skin: biological age, skin health, hydration, 3d facial skin model and texture, moles, wrinkles, marks, common diseases;
- Eyes: visual iris abnormalities, common diseases;
- Cardiovascular system: pulse, blood pressure, heart rate variability, breathing rate;
MX Labs say users need only a medium-quality camera on their smartphone for the app to work, but there are two crucial factors affecting the accuracy of measurements, explains Koscielny: image stability and good lighting conditions. “We already have a very advanced image acquisition and stabilisation engine (…) To improve the accuracy of AI diagnosis, as well as to make it more holistic, we intend to add additional data streams, both from device sensors and from external sources, like Google Fit, Apple Health.”
The startup is looking to achieve blood pressure measurement accuracy in line with the AAMI standards. “Once we get there, we will first confirm it with a clinical trial, and then certify it through SaMD and CE marks”, adds MX Labs’ CEO. (SaMD or Software as a Medical Device = software intended to be used for one or more medical purposes that perform these purposes without being part of a hardware medical device, according to IMDRF; CE is an administrative marking that confirms health, safety, and environmental protection standards compliance for products sold in the common European Economic Area – editor’s note).
Thousands of Samples for AI Training
MX Labs’ Shen.AI comes with an SDK (Software Development Kit) that allows integration with mobile and desktop apps, as well as with embedded hardware systems, opening up a wide range of applications in telemedicine (remote triage, contactless vital sign measurement) or in specific hardware devices (smart mirrors, driver attention monitors, fitness screens, companion robots).
In each case, users will be able to measure pulse, blood pressure and other cardiovascular system metrics anywhere, anytime, without the need for any medical devices or a medical visit, reiterates Koscielny.
He says it is still to early to be actively looking for B2B (business-to-business) clients, but they are currently working with medical institutions from Europe (such as the Antoni Jurasz University Hospital No. 1 in Bydgoszcz, Poland), Africa and South-east Asia in order to feed data into the AI, to improve its accuracy.
Patients have their blood pressure measured multiple times by qualified staff, using the auscultatory method, while a video of the patient’s face is recorded using a smartphone mounted on a tripod. The traditional blood pressure readings are then used as reference values for the machine learning algorithms extracting data from the video. Koscielny explains MX Labs need several thousand recordings for the first stage of development. They are offering research participants a free 3-month subscription for their app.
Plans to Almost Double the Team
MX Labs was founded in Wroclaw, Poland, late 2020, by Remigiusz Koscielny and Przemek Jaworski, whom Borys Musielak describes as “serial entrepreneurs with years of experience building and scaling tech companies”.
Koscielny was a co-founder of Vivid Games, one of the largest Polish mobile game developers, where he worked for over 14 years. “While the gaming industry is great, my motivation for this shift was to devote as much of my professional time as possible to a meaningful project. I believe that our technology can positively change the lives of many people worldwide”, he commented. Koscielny invested and was a member of the supervisory board of ZMorph, a 3D printing company set up by MX Labs CTO and co-founder Jaworski, who also co-founded Lekko, a company selling anti-smog masks and scarfs.
While the gaming industry is great, my motivation for this shift was to devote as much of my professional time as possible to a meaningful project. I believe that our technology can positively change the lives of many people worldwide.
— Remigiusz Koscielny, CEO and co-founder of MX Labs
MX Labs has an eight-person team at the moment, has four job openings posted on their website, and Koscielny anticipates they will have a team of up to 14 people by the end of the year. Though the team works remotely in the context of the pandemic and most of the employees are located in Wroclaw, MX Labs’ website also lists an address in Tallinn, Estonia.
Sabin Popescu works as content editor, web designer/ developer and occasionally graphic designer for various companies and institutions across Eastern Europe and was an IT journalist for Romania’s leading business daily, Ziarul Financiar.