Abstract: It is disclosed a blood glucose prediction system and method using saliva-based artificial intelligence deep learning technique.

Abstract: The present disclosure relates to a continuous blood sugar measuring sensor member, wherein: since an electrode layer formed on one surface of a substrate is connected to a sensor contact point part on the other surface of the substrate through a via hole and thus two electrode layers may be formed on different opposite surfaces without having to be formed on the same surface of the substrate, the width of the substrate may be further reduced and an overall minimized and simplified structure may be ensured; since an electrode connection layer formed at the via hole is not formed in a shape of filling the via hole but is formed only on the inner circumferential surface, a filling defect occurring in a process of filling the via hole and a fault in electrical connection according thereto may be prevented and thus a more stable structure may be ensured; and since a plurality of via holes are formed, despite damage to or the occurrence of a defect in an electrode connection layer formed at one of the via holes, e