National University Hospital Launches Spinal AI
National University Hospital has introduced an AI tool to analyze lumbar spinal stenosis, a common surgical indication in elderly patients.
The tool, called Spine AI, automatically detects areas of spinal stenosis and classifies them by severity, according to a press release. The tool was trained using more than 18,000 lumbar spine MRI images from 446 patients. In one study, the technology took just “47 seconds” to analyze each spine.
Lumbar spinal stenosis is a condition in which the spinal canal narrows in the lower back and compresses the nerves and blood vessels that supply blood to the lower limbs.
Currently being evaluated across the NUHS radiology department, Spine AI was developed by NUH, together with the NUS Department of Computing and the National University Spine Institute. Siemens Healthineers was also used to help optimize the AI’s user interface.
NUH is said to generate around 4,000 lumbar MRI scans a year. With Spine AI automatically analysing each scan in an average of seven minutes, it could save 466 hours of time a year, estimates Dr Andrew Makmur, NUHS Group Chief Technology Officer and consultant to the NUH Department of Diagnostic Imaging.
South Korea deploys AI to check on elderly living independently
The Ministry of Health and Welfare and the Comprehensive Support Center for Elderly People Alone will use AI to connect with about 42,000 seniors expected to spend the upcoming Chuseok holiday alone.
Chuseok is a major autumn harvest festival on the Korean Peninsula. In South Korea, the festival is celebrated for three days.
As part of the government’s personalized elderly care service, the AI Call service uses text-to-speech and voice-to-text technology to make voice calls and collect and transmit call information.
Meanwhile, SK Telecom and Lotte Welfare Foundation have been selected to provide technical support for the holiday calling service.
Regional Hospital in Thailand Tests CXR AI
Phrapokklao Hospital, a large regional hospital in Chanthaburi, a province southwest of Thailand’s capital Bangkok, recently deployed AI technology to analyze chest X-rays (CXRs) to enhance lung cancer screening in the community.
“In most Thai government hospitals, [CXRs] interpreted by non-radiologists. However, in community hospitals, there are often no radiologists who can read CXRs. By overlaying specialized AI to read all cases, we can support clinicians in detecting incidental high-risk nodules that may lead to lung cancer,” Dr. Passakorn Wanchaijiraboon, deputy director of the Cancer Center of Excellence at Phrapokklao Hospital, was quoted as saying. He led a recent evaluation study of the qXR CXR solution by Indian company Qure.ai.
“The deployment of AI CXR is particularly beneficial in the community hospital setting, where it can significantly enhance diagnostic capabilities when there is no on-site radiologist,” added Dr Wanchaijiraboon, who is also an oncologist.
Earlier this year, Qure.ai received approval from the US Food and Drug Administration for Lung nodules on CXR qXR analysis solution range.
