Big data from Hong Kong used to build predictive AI and more AI instructions
CU Medicine develops predictive AI for severe hypoglycemia
Researchers from the Faculty of Medicine of the Chinese University of Hong Kong (CU Medicine) have used anonymized big data from the Hospital Authority Data Collaboration Laboratory to develop a new machine learning model that reduces the risk of severe hypoglycemia in older adults with diabetes. can predict.
They analyzed approximately 1.5 million data from more than 360,000 seniors with diabetes between 2013 and 2018. Based on the machine learning algorithm XGBoost, the risk prediction model uses 258 predictors, including demographics, admissions and diagnoses, to predict serious hypoglycemia events requiring hospitalization in the next 12 months.
In addition to prolonged hospitalization, there is severe hypoglycemia also associated with an increased risk of falls, cardiovascular disease, dementia and all-cause mortality, CU Medicine noted.
By achieving a positive predictive value of 85% in one study, the model could potentially be integrated into EHR decision support systems for preventive interventions, such as correcting the timing and dosage of insulin injections or switching to lower hypoglycemic diabetes medications. potential.
The Indian Army wants to develop AI for diagnostic support
The Medical Services of the Indian Armed Forces are working with the Indian Institute of Technology, Kanpur, Uttar Pradesh, for the joint research and development of technological solutions to address the health challenges of soldiers deployed in difficult terrains.
According to their memorandum of understanding, IIT Kanpur will also assist the Armed Forces Center for Computational Medicine at the Armed Forces Medical College in creating AI diagnostic models.
Alodokter joins Indonesia’s digital health mission
Digital healthcare company Alodokter is working with the Indonesian government to expand access to healthcare services across the country through telemedicine.
It signed a memorandum of understanding with the Ministry of Health to cooperate in areas such as increasing the capacity of health workers through the provision of professional credit units; health communication and education; conducting surveys on health development; and offering telemedicine services.
Mahidol University to test Japanese endoscopic AI
Mahidol University in Thailand is collaborating with Japanese startup AI Medical Service (AIM) to assess the applicability of the latter’s endoscopic AI in the Thai setting.
This comes as AIM looks to expand its market presence globally following regulatory approvals in Japan and Singapore in the past four months.
Indonesian university to test Korean medical AI for lung disease and stroke diagnosis
Universitas Gadjah Mada University Hospital in Indonesia will also conduct a clinical trial of three diagnosis-assistive AI from South Korean medical AI company Deepnoid.
According to their memorandum of understanding, the hospital will test Deepnoid’s diagnostic tool software for multiple lung diseases, lung nodules and brain aneurysms for 18 months. This comes as the hospital, which has seen a two-fold increase in X-ray, MRI and CT readings over the past three years, is bracing for growing demand for imaging while having just 22 readers so far.
The results of this clinical trial will inform Deepnoid’s application for a regulatory license in Indonesia, the company shared.