Medical Image AI Determination Analysis System
Tri-Service General Hospital
Tri-Service General Hospital developed its own AI image analysis system using the electrocardiogram image to predict the blood potassium concentration for auxiliary decision-making information in emergency medical treatment. This function uses R language to write related machine learning programs based on the concept of Convolutional Neural Networks (CNN). It successfully interfaced with the hospital system. The accuracy rate of AI interpretation is over 90%. It supports immediate upload of ECG and AI real-time calculation, so the attending physician and the physician who prescribes the prescription can receive prompt notification in 15 seconds if any blood potassium abnormality occurred.
Source：2020 Application of Smart Medical Technology brochure