Dr. Jaishree Naidoo was in charge of Pediatric Radiology at a hospital in South Africa in 2014. He had an epiphany moment after he came across a news article about AI recognition patterns being used to identify animals.
With 20 years of experience as a radiologist, Naidoo was already familiar with pattern recognition and quickly understood how the industry could use AI to transform access to diagnostic imaging. Her flame has been ignited and in 2019, along with her husband Terence Naidu and her Andrei Migatchev, Naidoo launched her Envisionit Deep AI. This is a healthtech startup that uses AI to bridge the demand for diagnostic imaging.
Envisionit Deep AI is now on its path to growth, backed by a $1.65 million investment from New GX Ventures SA, a joint venture of New GX Capital, RMB Ventures and GIIG Africa. This was after the startup was the South African region winner at the African Startup Awards.
Naidoo, who is also CEO of the company, said:
hybrid solution
The startup has a range of products it plans to expand beyond South Africa, including the Radify AI platform. The Radify AI platform claims to ensure fast, accurate, high-quality, and affordable medical imaging, which is a key factor in early diagnosis and treatment of disease.
“Radify AI has received approval from the Health Products Regulatory Association of South Africa. However, we want to go global and are busy seeking approval from the FDA and the European Medical Authority to do so.” said Naidoo.
According to Naidoo, Envisionit Deep AI’s ultimate goal is to ease the strain on health systems, especially in Africa, where investment in infrastructure and human resources remains underwhelming.
Data show that sub-Saharan Africa as a whole has one of the lowest doctor-to-patient ratios in the world, and specialist ratios are even worse. In the radiology department, there is a serious shortage of human resources, for example, the ratio of radiologists to the population in Kenya is 1:389,255 him, while in Nigeria it is 1:566,000.
This shortage of radiologists is what drove Naidoo to make Radify AI available to everyone, especially in peri-urban and rural areas, and inspired the startup to build a hybrid solution.
She says Radify AI can be deployed anywhere. We cannot democratize without solutions that are applicable to the local environment. ”
The startup’s onsite offerings can integrate with devices such as X-ray machines to provide diagnosis and treatment at the point of care. We also offer teleradiology for patients who require radiation reports.
“Usually a radiologist takes the x-ray and the patient goes home to collect the results later, sometimes months later. If you know what to treat, you can treat it quickly, so it eliminates this lag,” said Naidoo, adding that the company’s work in South Africa’s mining sector, where employees are at high risk of contracting tuberculosis. I added that I am planning to implement that solution.
The startup started by building a model for interpreting chest X-rays. The model has the ability to detect 25 different medical conditions, including tuberculosis, breast cancer, and pneumonia, the number one killer of children under the age of five in Africa.
According to Naidoo, the platform has proven beneficial, especially during the Covid pandemic. That’s when Envisionit Deep AI unveiled a product that could detect Covid pneumonia from a chest X-ray, he said, in less than 25 milliseconds. It was introduced by a radiologist to increase efficiency at his 700-bed hospital in South Africa’s Northern Cape province, where he had only one. Naidoo says it was used for triage in several ICUs, especially during his second peak of the pandemic.
The amount of data to process is essential, but the startup says it ensures that it uses high-quality, de-identified data drawn from different ethnic groups around the world to train its models.
Data can also be reviewed by radiologists using validation tools. This gives you peace of mind that your product is working properly. And with their input and feedback, the startup was able to improve the accuracy of its model.
Envisionit Deep AI recently rolled out a computer-aided training model (edtech tool) for medical professionals interested in mastering radiology skills.
