首页|Royal Adelaide Hospital Reports Findings in Artificial Intelligence (Artificial Intelligence Age Prediction Using Electrocardiogram Data: Exploring Biological A ge Differences)
Royal Adelaide Hospital Reports Findings in Artificial Intelligence (Artificial Intelligence Age Prediction Using Electrocardiogram Data: Exploring Biological A ge Differences)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Artificial Intelligenc e is the subject of a report. According to news reporting from Adelaide, Austral ia, by NewsRx journalists, research stated, “Biological age can be predicted usi ng artificial intelligence (AI) trained on electrocardiograms (ECGs), which is p rognostic for mortality and cardiovascular events. We developed an AI model to p redict age from ECG and compared baseline characteristics to identify determinan ts of advanced biological age.” The news correspondents obtained a quote from the research from Royal Adelaide H ospital, “An AI model was trained on ECGs from cardiology inpatients aged 20-90 years. AI analysis used a convolutional neural network with data divided in an 8 0:20 ratio (development:internal validation), with external validation undertake n using data from the UK Biobank. Performance and subgroup comparison measures i ncluded correlation, difference and mean absolute difference. 63,246 patients wi th 353,704 total ECGs were included. In internal validation, the correlation coe fficient was 0.72, with a mean absolute difference between chronological and AI- predicted age of 9.1 years. The same model performed similarly in external valid ation. In patients aged 20-29, AI-ECG biological age was older than chronologica l age by a mean 14.3±0.2 yrs. In patients aged 80-89 years, biological age was y ounger by a mean 10.5±0.1 yrs. Women were biologically younger than men by a mea n of 10.7 months (P=0.023) and patients with a single ECG were biologically 1.0 years younger than those with multiple ECGs (P <0.0001). Th ere are significant between-group differences in AI-ECG biological age for patie nt subgroups. Biological age was greater than chronological age in young, hospit alized patient, and less than chronological age in the older hospitalized patien t.”
AdelaideAustraliaAustralia and New Z ealandArtificial IntelligenceEmerging TechnologiesMachine Learning
NETL
NSTL
