Applying cloud technologies, artificial intelligence (AI) and big data, China-based Ping An Technology is empowering the healthcare community with the aim of providing patients with the opportunity to benefit from technological advancement.
Applying cloud technologies, artificial intelligence (AI) and big data, China-based Ping An Technology is empowering the healthcare community with the aim of providing patients with the opportunity to benefit from technological advancement.
Ping An Technology is developing solutions that have applications across the entire treatment process, starting from the moment the patient walks through the door of the doctor’s office or the entrance to the emergency room at a hospital seeking medical treatment, on through the medical examination and to the final diagnosis.
Worldwide, cancer is still a scourge without an apparent solution, especially for cancers that are ultimately terminal, for which, if diagnosed early, the successful outcome rate will be dramatically increased. For this reason, early screening and diagnosis is critically important. Existing screening methods based mainly on CT pose a huge challenge to physicians in terms of accurately interpreting the results. The large number of CT scans that need to be interpreted and the massive workload of physicians everywhere inevitably lead to diagnostic errors.
In response to this challenge, Ping An Technology came up with the solution of integrating the theory of Robust Control with advanced artificial intelligence algorithms involving deep as well as transfer learning and has achieved major breakthroughs in terms of using AI to interpret results.
In January of this year, Ping An Technology broke the world records for detection of lung nodules and reduction in the number of false positives with the respective accuracy rates of 95.1% and 96.8%, ranking the firm the leader for these two indexes which are part of the Lung Nodule Analysis (LUNA) assessment standard, the internationally accepted standard within the medical imaging field.
AI-based interpretation of CT scans, which is gradually being installed in more and more hospitals, is expected to help pathologists reduce the time needed to interpret a scan by more than 50%, effectively decreasing the number of missed diagnoses and misdiagnosis due to human factors.
Helping to alleviate poverty
In China, the uneven distribution of medical resources has long been a chronic problem, especially in the country’s remote and poorer areas, where the difficulty of obtaining proper medical services and the associated high cost have led to the impoverishment of less fortunate households. In response, in the 2.0 version of Ping An Technology’s Village Doctor app, the medical technology firm has implemented facial and voiceprint recognition technology to achieve identity verification and login through intelligent “duplicate record” of personal vaccination information in ethnic minority communities, as well as in remote and disadvantaged areas of the country where medical facilities are lacking.
The app can also be used in an offline environment. The new feature not only enhances the security of personal information, but also facilitates login by inhabitants in remote areas, providing technical support for the app so that remote and disadvantaged areas of the country can be better covered and served.
Disease prediction through AI and big data
Ping An Technology’s intelligent disease prediction and screening models can forecast the occurrence of infectious diseases one week ahead of an outbreak as well as guide the public in the prevention of acute diseases. According to data from the Chinese Center for Disease Control and Prevention, the prediction models for influenza and hand-foot-and-mouth disease both have accuracy of more than 86 percent and, during seasonal peaks, accuracy can rise above the 90 percent mark. The intelligent screening model for COPD has an accuracy of 92 percent.