Ping An Smart Healthcare has developed a smart image-reading system aimed at helping medical professionals to improve efficient and accurate diagnosis of the new COVID-19 virus that is currently taxing the resources of the global healthcare communities.
Leveraging on its AI expertise, Ping An Smart Healthcare’s new smart image-reading system could help control the epidemic through earlier diagnosis and treatment, especially on the frontlines.
"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%", said Geoff Kau, co-president and chief strategy officer of Ping An Smart City. By comparison, it usually takes radiologists about 15 minutes to read the CT images of a patient suspected of contracting COVID-19.
The company launched the smart image-reading system on February 19. Ping An Smart Healthcare is affiliated with Ping An Smart City, which is part of Ping An Insurance (Group) Company of China.
Closing the gap in COVID-19 detection and treatment
As COVID-19 is a new disease, medical institutions, especially at the primary level in China, lack diagnosis experience, according to Ping An Healthcare. The Nucleic Acid Test (NAT) had been regarded as the major reference for COVID-19 diagnoses. But as the epidemic continues to spread, the NAT has had several problems, including long detection times and a high proportion of false negative cases. This resulted in some patients missing the chance for early treatment or quarantine.
The company said Computed Tomography (CT) images is being used by many doctors for diagnosis, but the lack of radiologists in the epidemic areas to review the volume of CT images is a major challenge. Ping An's COVID-19 smart image-reading system aims to close the gap.
Ping An Smart Healthcare used clinical data to train the AI model of the COVID-19 smart image-reading system. The AI analysis engine can conduct a comparative analysis of multiple CT scan images of the same patient and measure the changes in lesions. It helps doctors to track the development of the disease, evaluate the treatment and have prognosis of patients, ultimately it assists doctors to diagnose, triage and evaluate COVID-19 patients swiftly and effectively. Ping An Smart Healthcare's COVID-19 smart image-reading system also supports AI image-reading remotely by medical professionals outside the epidemic areas.
Medical institutions that require COVID-19 smart image-reading services can also gain access on public or private cloud platforms or on premises. At the same time, the public or private cloud platforms support storing and sharing electronic film. The smart image-reading system can also be quickly transplanted to CT equipment with the help of manufacturers to assist diagnosing the COVID-19.
“Patients with COVID-19 need multiple CT scans during the treatment. Comparing multiple images is a time-consuming task and it cannot be accurately completed manually. Utilizing Ping An Smart Healthcare's COVID-19 smart image-reading system, it can effectively improve the diagnostic accuracy and the doctor's image-reading efficiency,” said Dr. Xiao Jing, chief scientist at Ping An.