Dr Jaishree Naidoo was in charge of pediatric radiology at a South African hospital in 2014 when she had a moment of revelation after coming across a news report about the use of AI recognition patterns in differentiating animals.
As a radiologist with 20 years of experience, Naidoo was already familiar with pattern recognition and immediately saw how AI could be used in the industry to transform access to diagnostic imaging. The flame was lit and in 2019, Naidoo, along with her husband Terence Naidu and Andrei Migatchev, launched Envisionit Deep AI, a health tech startup that uses AI to bridge the demand for diagnostic imaging.
Imagine Deep AI is now on track for growth, supported by a $1.65 million investment from New GX Ventures SA, a joint venture between New GX Capital, RMB Ventures and GIIG Africa. This was after the startup became South Africa’s regional winner at the African Startup Awards.
“We have this exciting goal to combine revolutionary technology like artificial intelligence with radiology and we want to change the way radiologists see, interpret imaging and make diagnoses,” said Naidoo, who also serves as CEO of the company.
Hybrid solution
The startup has a range of products it plans to scale up outside of South Africa, including the Radify AI platform, which they say ensures fast, accurate, high-quality and affordable medical imaging diagnosis, factors that are critical in early diagnosis and treatment of diseases.
“Radify AI has received approval from the South African Health Products Regulatory Association. But we want to go global and that is why we are busy seeking approval from the FDA and the European Medical Agency,” said Naidoo.
Naidoo says Envisionit Deep AI’s ultimate goal is to reduce burdens in the healthcare system, especially in Africa, where investment in infrastructure and human resources remains dismal.
Data shows that the doctor-to-patient ratio in sub-Saharan Africa is one of the lowest in the world, a ratio even worse for specialty doctors. In radiology, the scarcity of personnel is so great that the radiologist/population ratio in Kenya, for example, is the same 1:389.255, while in Nigeria it is 1:566.000.
This lack of radiologists is what drove Naidoo to make Radify AI accessible to everyone, especially in peri-urban and rural regions, and prompted the start-up to build a hybrid solution.
She says Radify AI can be deployed anywhere, “be it in the first world or in a rural clinic that may not have major broadband capacity or the best infrastructure…because the whole idea for our product is to democratize access to diagnostic imaging, and we will not be democratizing if we don’t have solutions that can go to the countryside.”
The startup’s on-site product integrates with devices such as x-ray machines to deliver diagnosis and treatment at the point of care. They also offer teleradiology for patients who need radiology reports.
“Usually a radiologist takes X-rays, after which patients go home and collect the results later, sometimes after several months. Delayed diagnosis means that diseases can progress further. We are removing that delay because if you know what to handle, you handle it quickly,” said Naidoo, adding that they plan to introduce their solutions to the mining sector in South Africa, where workers are at greater risk to get tuberculosis.
The startup started building models for interpreting chest X-rays, with the capacity to detect 25 different pathologies, including tuberculosis, breast cancer and pneumonia, the number one cause of death among children under five in Africa.
This platform, Naidoo said, proved especially useful during the Covid pandemic, when Envisionit Deep AI unveiled a product that could detect Covid pneumonia on chest X-rays in less than 25 milliseconds. This was used to increase efficiency in a 700-bed hospital in South Africa’s Northern Cape province, which had only one radiologist. Naidoo says it was also used for triage in several ICUs, especially during the second peak of the pandemic.
The startup says that while the volume of data it processes is integral, it ensures that its models are trained using high-quality anonymized data pulled globally and from different ethnic groups.
The data can also be reviewed by radiologists through a validation tool that gives them some assurance that the product is working accordingly; and to get their input and feedback, which helped the startup improve the accuracy of its models.
Envisionit Deep AI recently rolled out a computer-aided training model (an edtech tool) for physicians eager to gain radiology skills.
Janice has been with businesskinda for 5 years, writing copy for client websites, blog posts, EDMs and other mediums to engage readers and encourage action. By collaborating with clients, our SEO manager and the wider businesskinda team, Janice seeks to understand an audience before creating memorable, persuasive copy.