International journal of cardiology · 2026
Relationship between the diagnostic probability of chronic kidney disease calculated using artificial intelligence-enhanced electrocardiography and the incidence of cardiovascular events.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Arai Motohiro, Suzuki Shinya, Hirota Naomi, Motogi Jun, Takayanagi Tsuneo, Umemoto Takuya, Nakai Hiroshi, Arita Takuto, Yagi Naoharu, Kishi Mikio, Kano Hiroto, Matsuno Shunsuke, Kato Yuko, Otsuka Takayuki, Yajima Junji, Uejima Tokuhisa, Okumura Yasuo, Oikawa Yuji, Yamashita Takeshi
Аннотация
AIMS: A low estimated glomerular filtration rate (eGFR) is the primary diagnostic criterion for chronic kidney disease (CKD), a known risk factor for cardiovascular disease (CVD). Artificial intelligence-enhanced electrocardiography (AI-ECG) has demonstrated high diagnostic performance for CKD. However, it remains unclear whether the diagnostic probability derived from AI-ECG for CKD (AIECG-CKD-DP) can also predict future cardiovascular events.
METHODS AND RESULTS: We analysed data from 16,984 patients in the Shinken Database who underwent AI-ECG and were followed up. Based on their baseline AIECG-CKD-DP, they were divided into two groups, Low-DP (<0.6, n = 10,031) and High-DP (≥0.6, n = 6953) groups, and we compared their clinical characteristics and the incidence of cardiovascular events. Patients in the High-DP group were more likely to be male (65.4% vs. 62.4%), older (69.1 vs. 55.2 years), and had lower eGFR (60.5 vs. 74.5 mL/min/1.73m2). AIECG-CKD-DP inversely correlated with eGFR (r = -0.461, P < 0.001). During the follow-up period, 894 cardiovascular events were recorded. The incidences of cardiovascular events were 1.14% and 4.73% per year for the Low-DP and High-DP groups, respectively. Multivariable Cox regression analysis generated hazard ratios (HRs) for the High-DP and Low-DP groups of 1.802 (95% confidence interval (CI), 1.512-2.148) and 1.292 (95% CI, 1.114-1.499) for CKD, respectively. When analysed as continuous variables, the HRs per standard deviation were 1.523 (95% CI, 1.368-1.695) for AIECG-CKD-DP and 0.979 (95% CI, 0.910-1.052) for eGFR.
CONCLUSION: AIECG-CKD-DP is independently associated with future cardiovascular events and outperforms eGFR and CKD classification as a predictor in a specialist cardiovascular cohort.
METHODS AND RESULTS: We analysed data from 16,984 patients in the Shinken Database who underwent AI-ECG and were followed up. Based on their baseline AIECG-CKD-DP, they were divided into two groups, Low-DP (<0.6, n = 10,031) and High-DP (≥0.6, n = 6953) groups, and we compared their clinical characteristics and the incidence of cardiovascular events. Patients in the High-DP group were more likely to be male (65.4% vs. 62.4%), older (69.1 vs. 55.2 years), and had lower eGFR (60.5 vs. 74.5 mL/min/1.73m2). AIECG-CKD-DP inversely correlated with eGFR (r = -0.461, P < 0.001). During the follow-up period, 894 cardiovascular events were recorded. The incidences of cardiovascular events were 1.14% and 4.73% per year for the Low-DP and High-DP groups, respectively. Multivariable Cox regression analysis generated hazard ratios (HRs) for the High-DP and Low-DP groups of 1.802 (95% confidence interval (CI), 1.512-2.148) and 1.292 (95% CI, 1.114-1.499) for CKD, respectively. When analysed as continuous variables, the HRs per standard deviation were 1.523 (95% CI, 1.368-1.695) for AIECG-CKD-DP and 0.979 (95% CI, 0.910-1.052) for eGFR.
CONCLUSION: AIECG-CKD-DP is independently associated with future cardiovascular events and outperforms eGFR and CKD classification as a predictor in a specialist cardiovascular cohort.