Validation of Non-invasive Detection of Hyperkalemia by Artificial Intelligence Enhanced Electrocardiography in High Acuity Settings.

IF 8.5 1区医学 Q1 UROLOGY & NEPHROLOGY

Clinical Journal of the American Society of Nephrology Pub Date : 2024-06-21 DOI:10.2215/CJN.0000000000000483

David M Harmon, Kan Liu, Jennifer Dugan, Jacob C Jentzer, Zachi I Attia, Paul A Friedman, John J Dillon

{"title":"Validation of Non-invasive Detection of Hyperkalemia by Artificial Intelligence Enhanced Electrocardiography in High Acuity Settings.","authors":"David M Harmon, Kan Liu, Jennifer Dugan, Jacob C Jentzer, Zachi I Attia, Paul A Friedman, John J Dillon","doi":"10.2215/CJN.0000000000000483","DOIUrl":null,"url":null,"abstract":"Background: Artificial intelligence (AI) electrocardiogram (ECG) analysis can enable detection of hyperkalemia. In this validation, we assessed the algorithm's performance in two high acuity settings.Methods: An emergency department (ED) cohort (February-August 2021) and a mixed intensive care unit (ICU) cohort (August 2017-February 2018) were identified and analyzed separately. For each group, pairs of laboratory-collected potassium and 12 lead ECGs obtained within four hours of each other were identified. The previously developed AI ECG algorithm was subsequently applied to leads I and II of the 12 lead ECGs to screen for hyperkalemia (potassium > 6.0 mEq/L).Results: The ED cohort (N=40,128) had a mean age of 60 years, 48% were male, and 1% (N=351) had hyperkalemia. The area under the curve (AUC) of the AI-ECG to detect hyperkalemia was 0.88, with sensitivity, specificity, positive predictive value, negative predictive value and positive likelihood ratio of, 80%, 80%, 3%, 99.8% and 4.0, respectively, in the ED cohort. Low-eGFR (<30 ml/min) subanalysis yielded AUC, sensitivity, specificity, positive predictive value, negative predictive value and positive likelihood ratio of 0.83, 86%, 60%, 15%, 98% and 2.2, respectively, in the ED cohort. The ICU cohort (N=2,636) had a mean age of 65 years, 60% were male, and 3% (N=87) had hyperkalemia. The AUC for the AI-ECG was 0.88 and yielded sensitivity, specificity, positive predictive value, negative predictive value and positive likelihood ratio of 82%, 82%, 14%, 99% and 4.6, respectively in the ICU cohort. Low-eGFR subanalysis yielded AUC, sensitivity, specificity, positive predictive value, negative predictive value and positive likelihood ratio of 0.85, 88%, 67%, 29%, 97% and 2.7, respectively in the ICU cohort.Conclusion: The AI-ECG algorithm demonstrated a high negative predictive value, suggesting that it is useful for ruling out hyperkalemia, but a low positive predictive value, suggesting that it is insufficient for treating hyperkalemia.","PeriodicalId":50681,"journal":{"name":"Clinical Journal of the American Society of Nephrology","volume":null,"pages":null},"PeriodicalIF":8.5000,"publicationDate":"2024-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Journal of the American Society of Nephrology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2215/CJN.0000000000000483","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"UROLOGY & NEPHROLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Artificial intelligence (AI) electrocardiogram (ECG) analysis can enable detection of hyperkalemia. In this validation, we assessed the algorithm's performance in two high acuity settings.

Methods: An emergency department (ED) cohort (February-August 2021) and a mixed intensive care unit (ICU) cohort (August 2017-February 2018) were identified and analyzed separately. For each group, pairs of laboratory-collected potassium and 12 lead ECGs obtained within four hours of each other were identified. The previously developed AI ECG algorithm was subsequently applied to leads I and II of the 12 lead ECGs to screen for hyperkalemia (potassium > 6.0 mEq/L).

Results: The ED cohort (N=40,128) had a mean age of 60 years, 48% were male, and 1% (N=351) had hyperkalemia. The area under the curve (AUC) of the AI-ECG to detect hyperkalemia was 0.88, with sensitivity, specificity, positive predictive value, negative predictive value and positive likelihood ratio of, 80%, 80%, 3%, 99.8% and 4.0, respectively, in the ED cohort. Low-eGFR (<30 ml/min) subanalysis yielded AUC, sensitivity, specificity, positive predictive value, negative predictive value and positive likelihood ratio of 0.83, 86%, 60%, 15%, 98% and 2.2, respectively, in the ED cohort. The ICU cohort (N=2,636) had a mean age of 65 years, 60% were male, and 3% (N=87) had hyperkalemia. The AUC for the AI-ECG was 0.88 and yielded sensitivity, specificity, positive predictive value, negative predictive value and positive likelihood ratio of 82%, 82%, 14%, 99% and 4.6, respectively in the ICU cohort. Low-eGFR subanalysis yielded AUC, sensitivity, specificity, positive predictive value, negative predictive value and positive likelihood ratio of 0.85, 88%, 67%, 29%, 97% and 2.7, respectively in the ICU cohort.

Conclusion: The AI-ECG algorithm demonstrated a high negative predictive value, suggesting that it is useful for ruling out hyperkalemia, but a low positive predictive value, suggesting that it is insufficient for treating hyperkalemia.

查看原文本刊更多论文

人工智能增强型心电图对高危情况下无创检测高钾血症的验证。

背景：人工智能（AI）心电图（ECG）分析可以检测高钾血症。在此次验证中，我们评估了该算法在两种高危情况下的性能：确定并分别分析了急诊科（ED）队列（2021 年 2 月至 8 月）和重症监护室（ICU）混合队列（2017 年 8 月至 2018 年 2 月）。每组都确定了实验室收集的钾和 12 导联心电图对，这两组心电图是在四小时内获得的。随后将先前开发的人工智能心电图算法应用于 12 导联心电图的 I 和 II 导联，以筛查高钾血症（血钾 > 6.0 mEq/L）：急诊室队列（N=40,128）的平均年龄为 60 岁，48% 为男性，1%（N=351）患有高钾血症。在急诊室队列中，AI-ECG 检测高钾血症的曲线下面积（AUC）为 0.88，灵敏度、特异性、阳性预测值、阴性预测值和阳性似然比分别为 80%、80%、3%、99.8% 和 4.0。低表皮生长因子受体（结论：AI-ECG 算法显示出较高的阴性预测值，表明它有助于排除高钾血症，但阳性预测值较低，表明它不足以治疗高钾血症。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Clinical Journal of the American Society of Nephrology 医学-泌尿学与肾脏学

CiteScore

12.20

自引率

3.10%

发文量

514

审稿时长

3-6 weeks

期刊介绍： The Clinical Journal of the American Society of Nephrology strives to establish itself as the foremost authority in communicating and influencing advances in clinical nephrology by (1) swiftly and effectively disseminating pivotal developments in clinical and translational research in nephrology, encompassing innovations in research methods and care delivery; (2) providing context for these advances in relation to future research directions and patient care; and (3) becoming a key voice on issues with potential implications for the clinical practice of nephrology, particularly within the United States. Original manuscript topics cover a range of areas, including Acid/Base and Electrolyte Disorders, Acute Kidney Injury and ICU Nephrology, Chronic Kidney Disease, Clinical Nephrology, Cystic Kidney Disease, Diabetes and the Kidney, Genetics, Geriatric and Palliative Nephrology, Glomerular and Tubulointerstitial Diseases, Hypertension, Maintenance Dialysis, Mineral Metabolism, Nephrolithiasis, and Transplantation.