Recent guidelines propose N-terminal pro-B-type natriuretic peptide (NT-proBNP) for recognition of asymptomatic left ventricular (LV) dysfunction (Stage B Heart Failure, SBHF) in type 2 diabetes mellitus (T2DM). Wavelet Transform based signal-processing transforms electrocardiogram (ECG) waveforms into an energy distribution waveform (ew)ECG, providing frequency and energy features that machine learning can use as additional inputs to improve the identification of SBHF. Accordingly, we sought whether machine learning model based on ewECG features was superior to NT-proBNP, as well as a conventional screening tool—the Atherosclerosis Risk in Communities (ARIC) HF risk score, in SBHF screening among patients with T2DM. Participants in two clinical trials of SBHF (defined as diastolic dysfunction [DD], reduced global longitudinal strain [GLS ≤ 18%] or LV hypertrophy [LVH]) in T2DM underwent 12-lead ECG with additional ewECG feature and echocardiography. Supervised machine learning was adopted to identify the optimal combination of ewECG extracted features for SBHF screening in 178 participants in one trial and tested in 97 participants in the other trial. The accuracy of the ewECG model in SBHF screening was compared with NT-proBNP and ARIC HF. SBHF was identified in 128 (72%) participants in the training dataset (median 72 years, 41% female) and 64 (66%) in the validation dataset (median 70 years, 43% female). Fifteen ewECG features showed an area under the curve (AUC) of 0.81 (95% CI 0.787–0.794) in identifying SBHF, significantly better than both NT-proBNP (AUC 0.56, 95% CI 0.44–0.68, p < 0.001) and ARIC HF (AUC 0.67, 95%CI 0.56–0.79, p = 0.002). ewECG features were also led to robust models screening for DD (AUC 0.74, 95% CI 0.73–0.74), reduced GLS (AUC 0.76, 95% CI 0.73–0.74) and LVH (AUC 0.90, 95% CI 0.88–0.89). Machine learning based modelling using additional ewECG extracted features are superior to NT-proBNP and ARIC HF in SBHF screening among patients with T2DM, providing an alternative HF screening strategy for asymptomatic patients and potentially act as a guidance tool to determine those who required echocardiogram to confirm diagnosis. Trial registration LEAVE-DM, ACTRN 12619001393145 and Vic-ELF, ACTRN 12617000116325

中文翻译：

---

利用能量波形心电图检测2型糖尿病患者亚临床左心功能不全

最近的指南建议使用 N 末端 B 型利钠肽原 (NT-proBNP) 来识别 2 型糖尿病 (T2DM) 中的无症状左心室 (LV) 功能障碍（B 期心力衰竭，SBHF）。基于小波变换的信号处理将心电图 (ECG) 波形转换为能量分布波形 (ew)ECG，提供机器学习可用作附加输入的频率和能量特征，以改进 SBHF 的识别。因此，我们探讨基于 ewECG 特征的机器学习模型在 T2DM 患者 SBHF 筛查中是否优于 NT-proBNP 以及传统筛查工具——社区动脉粥样硬化风险 (ARIC) HF 风险评分。两项 T2DM SBHF（定义为舒张功能障碍 [DD]、整体纵向应变减少 [GLS ≤ 18%] 或左心室肥厚 [LVH]）临床试验的参与者接受了 12 导联心电图检查，并附加了 ewECG 特征和超声心动图检查。采用监督式机器学习来确定 ewECG 提取特征的最佳组合，以便在一项试验中对 178 名参与者进行 SBHF 筛查，并在另一项试验中对 97 名参与者进行测试。将 ewECG 模型在 SBHF 筛查中的准确性与 NT-proBNP 和 ARIC HF 进行了比较。训练数据集中有 128 名（72%）参与者（中位年龄 72 岁，41% 女性）和验证数据集中有 64 名（66%）参与者（中位年龄 70 岁，43% 女性）存在 SBHF。15 个 ewECG 特征显示识别 SBHF 的曲线下面积 (AUC) 为 0.81 (95% CI 0.787–0.794)，显着优于 NT-proBNP (AUC 0.56，95% CI 0.44–0.68，p < 0.001) 和 ARIC HF（AUC 0.67，95%CI 0.56–0.79，p = 0.002）。ewECG 特征还导致了 DD（AUC 0.74，95% CI 0.73-0.74）、降低 GLS（AUC 0.76，95% CI 0.73-0.74）和 LVH（AUC 0.90，95% CI 0.88-0.89）的稳健模型筛查。使用额外的 ewECG 提取特征进行的基于机器学习的建模在 T2DM 患者的 SBHF 筛查中优于 NT-proBNP 和 ARIC HF，为无症状患者提供了替代的 HF 筛查策略，并可能作为指导工具来确定需要超声心动图确认的患者诊断。试用注册 LEAVE-DM，ACTRN 12619001393145 和 Vic-ELF，ACTRN 12617000116325