【摘要】：目的研究適用于遠程醫(yī)療服務(wù)系統(tǒng)、體檢中心和臨床應(yīng)用的心電圖(electrocardiogram,ECG)正異常分類算法。方法首先,通過心率篩除異常數(shù)據(jù)。然后,對于心率判為正常的心電圖,采用LCNN對心電圖再次進行正異常分類,并對多個LCNN的分類結(jié)果進行融合。結(jié)果在15萬多條記錄的臨床數(shù)據(jù)集上測試,取得了84.77%的準確率,85.19%的靈敏度和84.45%的特異性。結(jié)論該實驗結(jié)果優(yōu)于對照文獻,同時對應(yīng)用于遠程醫(yī)療和體檢中心的計算輔助分析方法具有一定的參考價值。
[Abstract]:Objective to study the positive classification algorithm of electrocardiogram (electrocardiogram,ECG) for telemedicine service system, physical examination center and clinical application. Methods first, abnormal data were screened by heart rate. Then, for the ECG with normal heart rate, LCNN was used to classify the ECG again, and the classification results of multiple LCNN were fused. Results the accuracy, sensitivity and specificity were 84.77%, 85.19% and 84.45% respectively. Conclusion the results of the experiment are superior to those of the control literature, and it has some reference value for the Computer-Aided Analysis method used in telemedicine and physical examination center.
【作者單位】： 上海大學通信與信息工程學院;中國科學院蘇州納米技術(shù)與納米仿生研究所;
【分類號】：TP18;R540.41
，

本文編號：2345244