CU Medicine develops AI to predict severe hypoglycemia
Researchers at the Chinese University of Hong Kong (CU Medicine) leverage anonymized big data from the Hospital Authority Data Collaboration Institute to develop a new machine learning model that can predict the risk of severe hypoglycemia in older adults with diabetes. developed the model.
They analyzed about 1.5 million records of more than 360,000 older adults with diabetes from 2013 to 2018. A risk prediction model based on the XGBoost machine learning algorithm uses 258 predictors, including demographics, hospitalizations, and diagnoses, to predict severe hypoglycemic events requiring hospitalization within the next 12 months.
In addition to prolonged hospitalization, severe hypoglycemia occurs. It is also associated with an increased risk of falls, cardiovascular disease, dementia, and all-cause mortality, CU Medicine noted.
The model, which achieved a positive predictive value of 85% in the study, can be used as an EHR decision support system for preemptive interventions, such as modifying the timing or dose of insulin injections or switching to diabetes medications that are less likely to cause hypoglycemia. It may be possible to integrate.
Indian military aims to develop diagnostic support AI
The Indian Armed Forces Medical Services has partnered with the Indian Institute of Technology, Kanpur, Uttar Pradesh, to jointly research and develop technological solutions to address health issues for soldiers deployed in difficult terrain.
Under the MoU, IIT Kanpur will also support creation of diagnostic AI models for the Military Center for Computational Medicine at the Armed Forces Medical University.
Allodoktel joins Indonesia's digital health mission
Digital health company Alodokter is working with the Indonesian government to expand access to health services nationwide through telemedicine.
A memorandum of understanding was signed with the Ministry of Health to cooperate in areas such as improving the capacity of medical workers by providing professional credit units. Health communication and education. Conduct health development surveys. Provision of telemedicine services.
Mahidol University introduces Japanese endoscope AI on a trial basis
Thailand's Mahidol University is collaborating with Japanese startup AI Medical Service (AIM) to evaluate the applicability of endoscopic AI in Thailand.
This comes as AIM looks to expand its market presence globally after receiving regulatory approvals in Japan and Singapore in the past four months.
Indonesian university to test South Korean medical AI for lung disease, stroke diagnosis
Indonesia's Gadjah Mada University Academic Hospital will also conduct clinical trials of three types of diagnostic support AI from South Korean medical AI company Deepnoid.
Under the memorandum of understanding, the hospital will test Deepnoid's diagnostic support software for multiple lung diseases, lung nodules and brain aneurysms for 18 months. This means that in the past three years, the hospital has doubled its X-ray, MRI and CT readings, but to date the hospital has only 22 reading devices, and image processing This comes as we prepare for increased demand.
The company shared that the results of this clinical trial will be reflected in Deepnoid's regulatory approval application in Indonesia.