Alibaba’s AI helps detect coronavirus pneumonia within a minute

Medical information provider M3 has tapped Alibaba Group Holding’s Artificial Intelligence technology to develop a diagnostic system through CT scan to identify COVID-19,within a minute.

Although this Chinese retailer is known as the Amazon of China,but it is much more than that as TheNextWeb claims:

Alibaba is like Amazon, Microsoft, a video game company, and a nation-wide healthcare network all rolled into one with every branch being fed solutions from the company’s world-class AI department.

What does Alibaba Claims?

Alibaba claims that its new system can detect coronavirus in CT scans of patients’ chests with 96% accuracy against viral pneumonia cases. And it only takes 20 seconds for the AI to make a determination. According to the report, physicians generally take about 15 minutes to diagnose the illness as it needs around 300 images to evaluate.

How it will work?

On Feb. 4, almost two weeks into the lockdown of Wuhan, where the virus was first identified, the DAMO team started to train its algorithms for diagnosing coronavirus using diagnostic guidelines released by Dr. Shi Heshui, a leading radiologist from Tongji Medical College. Since the team had already been doing AI-enabled medical-imaging work for the past three years in fields such as common respiratory diseases, it took us a little under five days before producing the first set of calculations for Covid-19.

Credit –

The RIS(RAdiology Information System)/PACS( Picture Archive and Communication System) will be collected from the hospitals and then it will be circulated through the DAMO Core Algorithm for the decision making of whether the patient is COVID-19 positive or negative,where a PACS file can range upto 300 to 400 per person and will be sent through internet using a API.

This AI system does two things: 

  • One is to track treatment responses in confirmed cases, 
  • And the other is to provide diagnoses for suspected cases.

Hospitals in heavily affected regions like Wuhan passed on the CT scans of the same, often confirmed case every two to three days and they will use this AI system to detect signs of improvement, such as the reduction of white mass in the lungs.

What is the size of the Data required for the training of Algorithm?

The diagnosis algorithm was reportedly trained on data from more than 5,000 confirmed cases of COVID-19, the illness caused by the novel coronavirus from China.

But is this the only one to be in the race?
It’s not the only one in town capable of detecting the Coronavirus. One of the rival healthcare organization Ping An recently announced a very similar-sounding system. The company’s co-president and chief strategy officer of its Smart City division, Geoff Kau, released a statement saying:
Since its launch, the smart image-reading system has provided services to more than 1,500 medical institutions. More than 5,000 patients have received smart image-reading services for free. The system can generate smart analysis results in around 15 seconds, with an accuracy rate above 90%.

The Alibaba AI was first introduced in the new Qiboshan Hospital in Zhengzhou, Henan province, and has since been adopted by at least 100 more healthcare facilities in the regions of Guangdong, Hubei, and Anhui. It is to be mentioned that all the locations listed have seen the highest number of infections.

Where the testing is currently been performed?

The diagnostic system, which is awaiting approval from the health ministry, holds promise as a supplementary testing tool as Japan struggles to expand capacity for PCR (Polymerase Chain Reaction) tests for the coronavirus.

Sony affiliated M3 has been testing Alibaba’s AI in Japan since the end of March, using PCR tests to confirm AI’s screening results.But this new system performs analysis within a minute with high accuracy, although falling short of 90%,said by Japanese Company.But it should be mentioned that Data obtained by the system will be used exclusively in Japan.

Japan has green-lighted saliva-based PCR tests but has still lagged other countries in testing capacity. By following the steps of Japan’s substantial pool of CT scanners to identify coronavirus pneumonia can lead to faster diagnosis, possibly helping deliver treatment to patients before they get seriously ill.

Is Artificial Intelligence for battling against COVID-19?

Artificial Intelligence is gaining traction as a diagnostic tool. Image diagnosis provider Doctor Net, a group member of machine maker Noritsu Koki, has teamed up with Beijing Infervision Technology, which has developed an AI-powered CT scan screening system for COVID-19 that is already used in China.

Is the they are the only players right now in the field on AI assist to world against COVID-19?

No, Medical AI developers in Europe are also playing catch-up with Chinese rivals. Germany’s Siemens has developed software for assisting CT scan reading for coronavirus pneumonia with AI and provides it to medical institutions around the world for research purposes.

The global market for medical AI is projected to reach $36 billion in 2025, according to U.S. firm MarketsandMarkets Research Private.


Leave a Reply