Department of Biotechnology and Medical Engineering, National Institute of Technology Rourkela, Odisha, India.
Biomed Tech (Berl). 2023 Mar 27;68(4):393-409. doi: 10.1515/bmt-2022-0430. Print 2023 Aug 28.
Atrial Tachycardia (AT) and Left Atrial Enlargement (LAE) are atrial diseases that are significant precursors to Atrial Fibrillation (AF). There are ML models for ECG classification; clinical features-based classification is required. The suggested work aims to create stacked ML models that categorize Sinus Rhythm (SR), Sinus Tachycardia (ST), AT, and LAE signals based on clinical parameters for AF prognosis.
The classification was based on thirteen clinical parameters, such as amplitude, time domain ECG aspects, and P-Wave Indices (PWI), such as the ratio of P-wave length and amplitude ((P (ms)/P (µV)), P-wave area (µVms), and P-wave terminal force (PTFV1(µVms). Apart from classifying the ECG signals, the stacked ML models prioritized the clinical features using a pie formula-based technique.
The Stack 1 model achieves 99% accuracy, sensitivity, precision, and F1 score, while the Stack 2 model achieves 91%, 91%, 94%, and 92% for identifying SR, ST, LAE, and AT, respectively. Both stack models obtained a computational time of 0.06 seconds. PTFV1 (µVms), P (ms)/P (µV)), and P-wave area (µVms) were ranked as crucial clinical features.
Clinical feature-based stacking ML models may help doctors obtain insight into important clinical ECG aspects for early AF prediction.
心房颤动（AF）的重要前体是房性疾病，包括房性心动过速（AT）和左心房扩大（LAE）。目前已经有用于心电图分类的 ML 模型，但需要基于临床特征进行分类。本研究旨在建立基于临床参数的堆叠 ML 模型，对窦性心律（SR）、窦性心动过速（ST）、AT 和 LAE 信号进行分类，以预测 AF。
该分类基于 13 个临床参数，如振幅、时域心电图方面和 P 波指数（PWI），如 P 波长度与振幅的比值（P（ms）/P（µV））、P 波面积（µVms）和 P 波终点力（PTFV1（µVms））。除了对心电图信号进行分类外，堆叠 ML 模型还使用基于饼图公式的技术对临床特征进行优先级排序。
Stack 1 模型在识别 SR、ST、LAE 和 AT 时的准确率、敏感度、精确度和 F1 评分分别达到 99%、99%、99%和 99%，Stack 2 模型的准确率、敏感度、精确度和 F1 评分分别达到 91%、91%、94%和 92%。两个堆叠模型的计算时间均为 0.06 秒。PTFV1（µVms）、P（ms）/P（µV）和 P 波面积（µVms）被评为重要的临床特征。
基于临床特征的堆叠 ML 模型可以帮助医生了解重要的临床心电图方面，从而有助于早期预测 AF。
