Hong Kong big data utilised for building predictive AI and more AI briefs

CU Medicine develops severe hypoglycemia predictive AI 

Researchers from the Faculty of Medicine at the Chinese University of Hong Kong (CU Medicine) have utilised anonymised big data from the Hospital Authority Data Collaboration Laboratory to develop a new machine learning model that can predict the risk of severe hypoglycemia among older diabetic adults.

They analysed about 1.5 million records of more than 360,000 senior individuals with diabetes from 2013-2018. Based on the XGBoost machine learning algorithm, the risk prediction model uses 258 predictors, including demographics, admissions, and diagnoses, to predict severe hypoglycemia events requiring hospitalisation in the next 12 months. 

Besides prolonged hospitalisation, severe hypoglycemia is also associated with an increased risk of falls, cardiovascular disease, dementia, and all-cause mortality, CU Medicine noted. 

Achieving an 85% positive predictive value in a study, the model can be potentially integrated into EHR decision support systems for pre-emptive interventions, such as correcting the timing and dosage of insulin injections or changing to diabetes medications with lower hypoglycemic potential.

Indian military looks to develop diagnosis support AI 

India’s Armed Forces Medical Services has partnered with the Indian Institute of Technology in Kanpur, Uttar Pradesh for the joint research and development of technology solutions addressing the health problems of soldiers deployed in difficult terrains. 

Under their memorandum of understanding, IIT Kanpur will also help the Armed Forces Medical College’s Armed Forces Centre for Computational Medicine in creating diagnostic AI models. 

Alodokter joins Indonesia’s digital health mission

Digital health company Alodokter is cooperating with the Indonesian government in expanding access to health services across the country through telemedicine. 

It signed a memorandum of understanding with the Ministry of Health to collaborate in such areas as raising healthcare workers’ capacity by providing professional credit units; health communications and education; conducting health development surveys; and providing telemedicine services. 

Mahidol Univesity to trial 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 after receiving regulatory approvals in Japan and Singapore over the past four months. 

Indonesian university to test Korean medical AI for lung disease, stroke diagnosis

The Universitas Gadjah Mada Academic Hospital in Indonesia will also conduct a clinical trial of three diagnosis support AI from South Korean medical AI company, Deepnoid.

Under their memorandum of understanding, the hospital will be testing Deepnoid’s diagnosis aid software for multiple lung diseases, lung nodules, and brain aneurysms for 18 months. This comes as the hospital, which saw a two-fold rise in X-ray, MRI, and CT readings over the past three years, is bracing for growing demand for imaging while only having 22 readers to date. 

The results of this clinical trial will inform Deepnoid’s application for a regulatory licence in Indonesia, the company shared.