Abstract：
OBJECTIVE: To develop and employ machine learning (ML) algorithms to analyse electrocardiograms (ECGs) for the diagnosis of cardiac autonomic neuropathy (CAN).
METHODS: We used motif and discord extraction techniques, alongside long short-term memory networks, to analyse 12-lead, 10-s ECG tracings to detect CAN in patients with diabetes. The performance of these methods with the support vector machine classification model was evaluated using 10-fold cross validation with the following metrics: accuracy, precision, recall, F1 score, and area under the receiver-operating characteristic curve (AUC).
RESULTS: Among 205 patients (mean age 54 ± 17 years, 54% female), 100 were diagnosed with CAN, including 38 with definite or severe CAN (dsCAN) and 62 with early CAN (eCAN). The best model performance for dsCAN classification was achieved using both motifs and discords, with an accuracy of 0.92, an F1 score of 0.92, a recall at 0.94, a precision of 0.91, and an excellent AUC of 0.93 (95% confidence interval [CI] 0.91-0.94). For the detection of any stage of CAN, the approach combining motifs and discords yielded the best results, with an accuracy of 0.65, F1 score of 0.68, a recall of 0.75, a precision of 0.68, and an AUC of 0.68 (95% CI 0.54-0.81).
CONCLUSIONS: Our study highlights the potential of using ML techniques, particularly motifs and discords, to effectively detect dsCAN in patients with diabetes. This approach could be applied in large-scale screening of CAN, particularly to identify definite/severe CAN where cardiovascular risk factor modification may be initiated.
METHODS: We used motif and discord extraction techniques, alongside long short-term memory networks, to analyse 12-lead, 10-s ECG tracings to detect CAN in patients with diabetes. The performance of these methods with the support vector machine classification model was evaluated using 10-fold cross validation with the following metrics: accuracy, precision, recall, F1 score, and area under the receiver-operating characteristic curve (AUC).
RESULTS: Among 205 patients (mean age 54 ± 17 years, 54% female), 100 were diagnosed with CAN, including 38 with definite or severe CAN (dsCAN) and 62 with early CAN (eCAN). The best model performance for dsCAN classification was achieved using both motifs and discords, with an accuracy of 0.92, an F1 score of 0.92, a recall at 0.94, a precision of 0.91, and an excellent AUC of 0.93 (95% confidence interval [CI] 0.91-0.94). For the detection of any stage of CAN, the approach combining motifs and discords yielded the best results, with an accuracy of 0.65, F1 score of 0.68, a recall of 0.75, a precision of 0.68, and an AUC of 0.68 (95% CI 0.54-0.81).
CONCLUSIONS: Our study highlights the potential of using ML techniques, particularly motifs and discords, to effectively detect dsCAN in patients with diabetes. This approach could be applied in large-scale screening of CAN, particularly to identify definite/severe CAN where cardiovascular risk factor modification may be initiated.
摘要：
目的：开发并使用机器学习（ML）算法分析心电图（ECG）以诊断心脏自主神经病变（CAN）。
方法：我们使用基序和不和谐提取技术，除了长期短期记忆网络，分析12导联，10-s心电图描记以检测糖尿病患者的CAN。这些方法与支持向量机分类模型的性能进行了评估，使用10倍交叉验证，具有以下指标：准确性，精度,召回，F1得分,和接受者工作特征曲线下面积(AUC)。
结果：在205名患者中（平均年龄54±17岁，54%女性），100人被诊断患有CAN，包括38个明确或严重的CAN(dsCAN)和62个早期CAN(ECAN)。dsCAN分类的最佳模型性能是使用基序和不一致实现的，准确率为0.92,F1评分为0.92,召回率为0.94,准确率为0.91,AUC为0.93(95%置信区间[CI]0.91-0.94).对于CAN的任何阶段的检测，结合主题和不一致的方法产生了最好的结果，准确率为0.65，F1评分为0.68，召回率为0.75，准确率为0.68，AUC为0.68（95％CI0.54-0.81）。
结论：我们的研究强调了使用ML技术的潜力，特别是主题和不和谐，有效检测糖尿病患者的dsCAN。这种方法可以应用于大规模的CAN筛查，特别是确定明确的/严重的CAN，其中心血管危险因素的修改可能开始。
方法：我们使用基序和不和谐提取技术，除了长期短期记忆网络，分析12导联，10-s心电图描记以检测糖尿病患者的CAN。这些方法与支持向量机分类模型的性能进行了评估，使用10倍交叉验证，具有以下指标：准确性，精度,召回，F1得分,和接受者工作特征曲线下面积(AUC)。
结果：在205名患者中（平均年龄54±17岁，54%女性），100人被诊断患有CAN，包括38个明确或严重的CAN(dsCAN)和62个早期CAN(ECAN)。dsCAN分类的最佳模型性能是使用基序和不一致实现的，准确率为0.92,F1评分为0.92,召回率为0.94,准确率为0.91,AUC为0.93(95%置信区间[CI]0.91-0.94).对于CAN的任何阶段的检测，结合主题和不一致的方法产生了最好的结果，准确率为0.65，F1评分为0.68，召回率为0.75，准确率为0.68，AUC为0.68（95％CI0.54-0.81）。
结论：我们的研究强调了使用ML技术的潜力，特别是主题和不和谐，有效检测糖尿病患者的dsCAN。这种方法可以应用于大规模的CAN筛查，特别是确定明确的/严重的CAN，其中心血管危险因素的修改可能开始。
