Chinese tech giant Tencent’s first attempt in AI healthcare was the Miying platform, which has been a point of pride for CEO Huateng Ma since its 2017 launch. Supported by AI-powered medical imaging technologies, Miying assists doctors with the screening of esophageal cancer, pulmonary nodules, cervical cancer, etc. The platform has been well received in the AI and medical communities, with a fast-expanding market in Chinese top-tier AAA hospitals.
At the recent International Congress of Parkinson’s Disease and Movement Disorders in Hong Kong, Tencent unveiled its second layout in AI healthcare: Medical AI Lab. The lab team includes experts in machine learning, computational vision, video analytics, augmented reality (AR), natural language understanding (NLU), etc. Tencent Medical AI Lab is the latest in the company’s continuing efforts on AI to Business marketing.
Tencent identified AI-assisted diagnosis of Parkinson’s disease (PD) as a Medical AI Lab focus, and a global scale network will be created to develop international collaborative research.
At the congress, lab head Wei Fan revealed that groundwork for the Tencent Medical AI Lab had quietly begun in September 2017 in Silicon Valley, Beijing and Shenzhen. He explained the one year deferment in the official unveiling was to maintain a low profile until the lab could make some research progress.
Tencent Medical AI Lab has been working on the application of video analytics technology for diagnosis of dyskinesia, which is usually seen in people with PD. One of the most common health concerns for seniors, patients with Parkinson’s generally suffer resting tremors with symptoms such as abnormal hand shaking, muscle rigidity and bradykinesia.
In partnership with Shanghai Huashan Hospital, Tencent has introduced a PD smart motion assessment system. Patients complete a series of movements in front of a camera, and the system will analyze and provide motion assessment for PD diagnosis within three minutes — ten times faster than with traditional diagnostic methods.
Tencent demonstrated their video analytics for PD diagnosis at the congress: The method enables a quantitative measurement of movement frequency and amplitude when a sitting PD patient performs a finger tapping test from the MDS Unified Parkinson’s Disease Rating Scale. Physicians can also remotely examine patient conditions through video analytics results. This reduces the need for traditional office visits, saving time and costs for patients and reducing doctors’ workloads
At the early stage of the study, Fan says the team faced the problem of limited sample size for patients with dyskinesia. To create a dataset large enough for model training and validation, researchers generated samples through action simulations with a combination of AR and AI technologies. The trained system detects and tracks human motions through motion analysis recognition of 21 key points on a hand.
The tech for Medical AI Lab’s first PD project is now in small-scale clinical testing. Tencent says that the product’s launch strategy will not be determined until its feasibility has been fully verified.
To promote global clinical application of the AI-assisted tech, Tencent announced a collaboration with UK digital health tech startup Medopad and King’s College London PD specialist Professor Kallol Ray Chaudhuri. The plan is to develop a rapid, intelligent and affordable smartphone platform for PD evaluation.
Tencent will also apply video analytics in the assessment of other patients with dyskinesia, including those with cerebral palsy and scoliosis diseases. Moreover, a 24-hour cardiac monitoring tool based on video analytics will soon begin clinical trials.
Fan says other Tencent Medical AI Lab projects will also build on NLU tech, such as analysis and understanding of medical texts, extraction of structured data (e.g., disease descriptions, treatment plans and clinical results) and weighted sorting.
Compared to other tech giants, Tencent was a relatively late arrival in the AI arena. The company however has found an effective entry point for landing business. In addition to Miying and the Medical AI Lab, Tencent will also release supporting products such as healthcare processes optimization and WeChat medical insurance payment programs as part of its “Internet + Smart Hospitals” solutions. The company plans to develop a comprehensive “Internet Medical Tools + Mobile Healthcare + Healthcare AI” product line as a long-term strategy.
Source: Synced China
Localization: Tingting Cao | Editor: Michael Sarazen