Pooja Rao, a doctor, data scientist and entrepreneur, wants to make cutting-edge medical care available to communities around the world, regardless of their resources. Her startup, Qure.ai, is doing exactly that, with technology that’s used in 150+ healthcare facilities in 27 countries.
Rao is the cofounder and head of research and development at the Mumbai-based company, which started in 2016. The company develops AI technology that interprets medical images, with a focus on pulmonary and neurological scans.
Qure.ai is also a member of the NVIDIA Inception startup accelerator program.
“Qure.ai received an NVIDIA Inception Social Innovation award back in 2016,” Rao said in advance of the interview. “This was our first ever external recognition, generating exposure for us in the AI ecosystem. Since then, we’ve been a regular participant at GTC – the world’s premier AI conference. NVIDIA’s commitment to the startup community is unmatched, and I’m always inspired by the new applications of AI that are showcased at the conference.”
Qure.ai technology has proven extremely useful in rapidly diagnosing tuberculosis, a disease that infects millions each year and can cause death if not treated early. By providing fast diagnoses and compensating in areas with fewer trained healthcare professionals, Qure.ai is saving lives.
Their AI is also helping to prioritize critical cases in teleradiology. Teleradiologists remotely analyze large volumes of medical images, with no way of knowing which scans might portray a time-sensitive issue, such as a brain hemorrhage. Qure.ai technology analyzes and prioritizes the scans for teleradiologists, reducing the time it takes them to read critical cases by 97 percent, according to Rao.
Right now, a major focus is helping fight COVID-19 — Qure.ai’s AI tool qXR is helping monitor disease progression and provide a risk score, aiding triage decisions.
In the future, Rao anticipates eventually building Qure.ai technology into medical imaging machinery to identify areas that need to be photographed more closely.
Key Points From This Episode:
- Qure.ai has just received its first U.S. FDA approval. Its technology has also been acknowledged by the World Health Organization, which recently officially endorsed AI as a means to diagnose tuberculosis, especially in areas with fewer healthcare professionals.
- Because Qure.ai’s mission is to create AI technology that can function in areas with limited resources, it has built systems that have learned to work with patchy internet and images that aren’t of the highest quality.
- In order to be a global tool, Qure.ai partnered with universities and hospitals to train on data from patients of different genders and ethnicities from around the world.
“You can have the fanciest architectures, but at some point it really becomes about the quality, the quantity and the diversity of the training data.” — Pooja Rao [7:46]
“I’ve always thought that the point of studying medicine was to be able to improve it — to develop new therapies and technology.” — Pooja Rao [18:57]
You Might Also Like:
How Nuance Brings AI to Healthcare
Nuance, a pioneer of voice recognition technology, is now bringing AI to the healthcare industry. Karen Holzberger, vice president and general manager of Nuance’s Healthcare Diagnostic Solutions business, talks about how their technology is helping physicians make people healthier.
Exploring the AI Startup Ecosystem with NVIDIA Inception’s Jeff Herbst
Jeff Herbst, vice president of business development at NVIDIA and head of NVIDIA Inception, is a fixture of the AI startup ecosystem. He joins the NVIDIA podcast to talk about how Inception is accelerating startups in every industry.
Anthem Could Have Healthcare Industry Singing a New Tune
Health insurance company Anthem is using AI to help patients personalize and better understand their healthcare information. Rajeev Ronanki, senior vice president and chief digital officer at Anthem, talks about how AI makes data as useful as possible for the healthcare giant.
Tune in to the AI Podcast
Get the AI Podcast through iTunes, Google Podcasts, Google Play, Castbox, DoggCatcher, Overcast, PlayerFM, Pocket Casts, Podbay, PodBean, PodCruncher, PodKicker, Soundcloud, Spotify, Stitcher and TuneIn. If your favorite isn’t listed here, drop us a note.
Make the AI Podcast Better
Have a few minutes to spare? Fill out this listener survey. Your answers will help us make a better podcast.