First People's Hospital of Chenzhou City (Emergency Department), Chenzhou, 423000 Hunan, China.
Biomed Res Int. 2022 Aug 8;2022:8552358. doi: 10.1155/2022/8552358. eCollection 2022.
The blockage of blood in the vessels results in heart attacks and cardiac arrests which are referred to as myocardial infarction. Early detection of such infarction is feasible through percutaneous coronary intervention (PCI) based on electrocardiogram (ECG) monitoring. The variations in blood flow and clot are precisely observed through periodic ECG monitoring and previous correlations. This article introduces a concentrated value assessment model (CVAM) for determining PCI levels in treating myocardial infarction. The ECG observations from the previous observation sessions are accumulated and organized for validating the infarction rate. This requires the accompanying concentrated data like a heartbeat, blood pressure, and flow rate observed in different sessions. Based on the session observation and normal data correlation, the PCI level is recommended for the patient. In this analysis process, the value shift due to blocks and high and low blood pressure is accounted for through the deep learning paradigm. This paradigm correlates the above factors with the ECG values for precisely determining PCI from the last known concentration. The learning paradigm is trained based on session and normal observation data through different intervals. This model is validated using the metrics precision, analysis rate, diagnosis recommendation, and complexity.
血管中的血液阻塞会导致心脏病发作和心脏骤停，这被称为心肌梗死。通过基于心电图 (ECG) 监测的经皮冠状动脉介入治疗 (PCI) 可以早期发现这种梗塞。通过定期的 ECG 监测和以前的相关性，可以精确观察血流和血栓的变化。本文提出了一种集中值评估模型 (CVAM)，用于确定治疗心肌梗死的 PCI 水平。从前几次观察中积累和组织 ECG 观察结果，以验证梗塞率。这需要伴随集中的数据，如在不同会话中观察到的心跳、血压和流速。根据会议观察和正常数据相关性，为患者推荐 PCI 水平。在这个分析过程中，深度学习范例考虑了由于阻塞和高低血压导致的数值变化。该范例将上述因素与 ECG 值相关联，以便从上次已知的浓度中准确确定 PCI。学习范例是通过不同的间隔基于会话和正常观察数据进行训练的。该模型使用精度、分析率、诊断建议和复杂度等指标进行验证。
