This Indian-led US startup deploys AI to spot abnormalities in CT scans of heads

San Francisco-based Qure.ai, a healthcare startup founded by Indians, said it has developed an artificial intelligence (AI) system that can spot bleeds, fractures and other abnormalities in CT (computed tomography) scans of heads within seconds. The step, which is the latest example of how AI and machine learning are working through the health care industry, promises automation of tasks often held back by shortage of professionals, who anyway take up much more time.

The news come nearly two weeks after a report that said a new AI engine had been developed by Oregon Health and Science University to detect the cause of blindness in babies more accurately than doctors. The university had said the tech would help cope with the huge shortage of ophthalmologists trained and willing to diagnose retinopathy of prematurity. 

Qure.ai, on its part, used a collection of 313,318 anonymised head CT scans, along with their corresponding clinical reports, to train the AI system. Of these, 21,095 scans were used to validate the AI's algorithms, said the company, which has operations in India as well.

Finally, the AI’s reading of 491 head CT scans were compared with the readings of three senior radiologists. The comparison found that AI was more than 95% accurate in identifying abnormalities.

To give you an idea, Oregon Health and Science University’s AI engine was able to diagnose the causes of blindness in babies with 91% accuracy. By contrast, a team of doctors was only 82% accurate. 

The Hindu BusinessLine has reported that Qure.ai is in talks with health care service providers both in the US and India. The report also cited co-founder Prashant Warrier as saying that the service, which acts on the cloud and comes up with a diagnosis in seconds, can be used on a low-speed internet connection.

Warrier said that his company has formed partnerships with 10 hospital and research labs for imaging data and interpreting them using his company's AI application.

The report further said that the solution was developed in such a way that it could be added to existing CT scanners or integrated with imaging devices.

Before coming out with this new solution, the company had earlier developed a similar tool that could be integrated with chest X-ray machines to identify tuberculosis in patients. The X-ray solution has already been deployed across 10 centres including hospitals and labs in Mumbai, New Delhi and Bengaluru.

Qure.ai makes money based on the number of scans the AI interprets but Warrier said the company was looking at a subscription model for its customers in the US.

In another tech tie-up, Apollo Hospitals is partnering Microsoft to infuse its products and services with AI, in a bid to slash healthcare costs.

According to Apollo Hospitals executive director Sangita Reddy, the company was working to bring down time in treating patients and offering more care. For example, by infusing AI into the treatment system, multiple doctors can look at the patient and serve him/her better. Apollo is also using devices such as tablets to keep the doctor abreast of the patient’s conditions at all times. 

The cost-reduction drive by Chennai-based Apollo comes on the heels of a tie-up with Microsoft to help doctors in the early detection of heart-related diseases using AI.