Medical Research Team, Medical AI, co., Seoul, South Korea.
Artificial Intelligence and Big Data Research Center, Sejong Medical Research Institute, Bucheon, South Korea.
Int Urol Nephrol. 2022 Oct;54(10):2733-2744. doi: 10.1007/s11255-022-03165-w. Epub 2022 Apr 11.
Although renal failure is a major healthcare burden globally and the cornerstone for preventing its irreversible progression is an early diagnosis, an adequate and noninvasive tool to screen renal impairment (RI) reliably and economically does not exist. We developed an interpretable deep learning model (DLM) using electrocardiography (ECG) and validated its performance.
This retrospective cohort study included two hospitals. We included 115,361 patients who had at least one ECG taken with an estimated glomerular filtration rate measurement within 30 min of the index ECG. A DLM was developed using 96,549 ECGs of 55,222 patients. The internal validation included 22,949 ECGs of 22,949 patients. Furthermore, we conducted an external validation with 37,190 ECGs of 37,190 patients from another hospital. The endpoint was to detect a moderate to severe RI (estimated glomerular filtration rate < 45 ml/min/1.73m).
The area under the receiver operating characteristic curve (AUC) of a DLM using a 12-lead ECG for detecting RI during the internal and external validation was 0.858 (95% confidence interval 0.851-0.866) and 0.906 (0.900-0.912), respectively. In the initial evaluation of 25,536 individuals without RI patients whose DLM was defined as having a higher risk had a significantly higher chance of developing RI than those in the low-risk group (17.2% vs. 2.4%, p < 0.001). The sensitivity map indicated that the DLM focused on the QRS complex and T-wave for detecting RI.
The DLM demonstrated high performance for RI detection and prediction using 12-, 6-, single-lead ECGs.
尽管肾衰竭是全球范围内的一个主要医疗保健负担，而早期诊断是防止其不可逆转进展的基石，但目前仍缺乏一种足够且非侵入性的工具，能够可靠且经济地筛查肾功能损害（RI）。我们开发了一种使用心电图（ECG）的可解释深度学习模型（DLM），并验证了其性能。
这是一项回顾性队列研究，包括两家医院。我们纳入了 115361 例至少有一次心电图检查且在索引心电图检查后 30 分钟内有估计肾小球滤过率测量值的患者。使用来自 55222 例患者的 96549 份心电图数据开发了一个 DLM。内部验证包括 22949 例患者的 22949 份心电图。此外，我们还使用来自另一家医院的 37190 例患者的 37190 份心电图进行了外部验证。终点是检测中重度 RI（估计肾小球滤过率＜45ml/min/1.73m）。
在内部和外部验证中，使用 12 导联心电图的 DLM 检测 RI 的受试者工作特征曲线下面积（AUC）分别为 0.858（95%置信区间 0.851-0.866）和 0.906（0.900-0.912）。在对 25536 例无 RI 患者的初步评估中，其 DLM 定义为高风险的患者发生 RI 的几率明显高于低风险组（17.2% vs. 2.4%，p<0.001）。敏感性图表明，DLM 侧重于 QRS 复合体和 T 波来检测 RI。
该 DLM 采用 12 导联、6 导联和单导联 ECG 进行 RI 检测和预测，具有较高的性能。
