[ad_1]
Dr. Jaishree Naidoo In 2014, she was in charge of pediatric radiology at a South African hospital. She paused after coming across a news report about AI’s use of pattern recognition in animal identification.
As a radiologist with 20 years of experience, Naidu was familiar with pattern recognition and could immediately see how AI could be used to transform access to diagnostic imaging in the industry. The fire was burning, and in
Envisionit Deep AI is now on the growth path thanks to a $1.65 million investment from New GX Ventures SA between New GX Capital, RMB Ventures and GIIG Africa. This comes after a South African startup emerged regional winner at the Africa Startup Awards.
“We have this exciting goal of combining revolutionary technology like artificial intelligence with radiology, and we want to make radiologists look, interpret imaging, and diagnose,” said Naidoo, the company’s CEO.
Mixed solution
The startup has a suite of products it plans to scale beyond South Africa, including its Radify AI platform, which it says ensures fast, accurate, quality and affordable medical imaging, critical to early diagnosis and disease treatment.
“Radifi AI has received approval from the Health Products Regulatory Association of South Africa. But we want to be global and that is why we are busy seeking approval from the FDA and the European Medicines Agency,” said Naidoo.
Naidoo said the ultimate goal of Invision’s Deep AI is to reduce the burden on the healthcare system, especially in Africa, where infrastructure and human resources investments are dire.
The data shows that the doctor-patient ratio in sub-Saharan Africa is one of the lowest in the world, and this ratio is even worse among specialist doctors. The manpower shortage in radiology is so bad that the ratio of radiologist to population in Kenya, for example, is 1:389,255 and in Nigeria it is 1:566,000.
This dilemma among radiologists is what prompted Naidoo Radify to make AI accessible to all, especially in suburban and rural regions, and the startup to build a hybrid solution.
Radify AI can be deployed anywhere, she says, “whether it’s in the first world or a rural clinic that may not have large broadband capacity or the best infrastructure… If we don’t have solutions that can go out into rural areas, we won’t be democratic.”
The startup’s on-site product can be integrated with equipment such as X-ray machines to deliver diagnostics and treatment at the point of care. They also provide tele-radiology services for patients who need radiology reports.
“Typically, a radiographer takes X-rays, and then patients go home and collect the results, sometimes several months later. Delayed diagnosis means diseases can be more advanced. We’re taking that delay, because when you know what to treat, you’re treated faster.” Naidu says they plan to introduce the solutions to South Africa’s mining sector, where workers are at high risk of contracting tuberculosis.
The startup started by building models to interpret chest X-rays, capable of detecting 25 different diseases, including tuberculosis, breast cancer and pneumonia, the number one killer of children under five in Africa.
This platform is especially important during the Covid pandemic when Invisit Deep AI launched a product that can detect Covid-19 pneumonia in less than 25 milliseconds from a chest X-ray, Naidu said. This was deployed to drive efficiency in a 700-bed hospital in the Northern Cape Province of South Africa with only one radiologist. Naidu said it was also used in several ICUs to detect the outbreak, especially during the second peak.
While the amount of data the startup processes is critical, it ensures that the models are trained using low-quality, globally drawn data from different nationalities.
The data can also be reviewed by radiologists through a validation tool that provides some assurance that the product is performing accordingly. And to get their input and feedback, which allowed the startup to improve the accuracy of its models.
Envisionit Deep AI recently released a computer-aided training model (an edtech tool) for medical professionals looking to acquire radiology skills.
[ad_2]
Source link