1
|
Harmon DM, Liu K, Dugan J, Jentzer JC, Attia ZI, Friedman PA, Dillon JJ. Validation of Noninvasive Detection of Hyperkalemia by Artificial Intelligence-Enhanced Electrocardiography in High Acuity Settings. Clin J Am Soc Nephrol 2024; 19:952-958. [PMID: 39116276 PMCID: PMC11321728 DOI: 10.2215/cjn.0000000000000483] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2023] [Accepted: 06/11/2024] [Indexed: 06/23/2024]
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 to August 2021) and a mixed intensive care unit (ICU) cohort (August 2017 to February 2018) were identified and analyzed separately. For each group, pairs of laboratory-collected potassium and 12 lead ECGs obtained within 4 hours of each other were identified. The previously developed AI ECG algorithm was subsequently applied to leads 1 and 2 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-enhanced ECG (AI-ECG) to detect hyperkalemia was 0.88, with sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and positive likelihood ratio (LR+) of 80%, 80%, 3%, 99.8%, and 4.0, respectively, in the ED cohort. Low-eGFR (<30 ml/min) subanalysis yielded AUC, sensitivity, specificity, PPV, NPV, and LR+ of 0.83, 86%, 60%, 15%, 98%, and 2.2, respectively, in the ED cohort. The ICU cohort (N=2636) 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, PPV, NPV, and LR+ of 82%, 82%, 14%, 99%, and 4.6, respectively in the ICU cohort. Low-eGFR subanalysis yielded AUC, sensitivity, specificity, PPV, NPV, and LR+ of 0.85, 88%, 67%, 29%, 97%, and 2.7, respectively in the ICU cohort. Conclusions The AI-ECG algorithm demonstrated a high NPV, suggesting that it is useful for ruling out hyperkalemia, but a low PPV, suggesting that it is insufficient for treating hyperkalemia.
Collapse
Affiliation(s)
- David M. Harmon
- Department of Internal Medicine, Mayo Clinic, Rochester, Minnesota
- Department of Cardiovascular Disease, Mayo Clinic, Rochester, Minnesota
| | - Kan Liu
- Department of Cardiovascular Disease, Mayo Clinic, Rochester, Minnesota
| | - Jennifer Dugan
- Department of Cardiovascular Disease, Mayo Clinic, Rochester, Minnesota
| | - Jacob C. Jentzer
- Department of Cardiovascular Disease, Mayo Clinic, Rochester, Minnesota
| | - Zachi I. Attia
- Department of Cardiovascular Disease, Mayo Clinic, Rochester, Minnesota
| | - Paul A. Friedman
- Department of Cardiovascular Disease, Mayo Clinic, Rochester, Minnesota
| | - John J. Dillon
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
| |
Collapse
|
2
|
Development and validation of a deep learning model to screen hypokalemia from electrocardiogram in emergency patients. Chin Med J (Engl) 2021; 134:2333-2339. [PMID: 34483253 PMCID: PMC8509898 DOI: 10.1097/cm9.0000000000001650] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/05/2022] Open
Abstract
Background: A deep learning model (DLM) that enables non-invasive hypokalemia screening from an electrocardiogram (ECG) may improve the detection of this life-threatening condition. This study aimed to develop and evaluate the performance of a DLM for the detection of hypokalemia from the ECGs of emergency patients. Methods: We used a total of 9908 ECG data from emergency patients who were admitted at the Second Affiliated Hospital of Nanchang University, Jiangxi, China, from September 2017 to October 2020. The DLM was trained using 12 ECG leads (lead I, II, III, aVR, aVL, aVF, and V1–6) to detect patients with serum potassium concentrations <3.5 mmol/L and was validated using retrospective data from the Jiangling branch of the Second Affiliated Hospital of Nanchang University. The blood draw was completed within 10 min before and after the ECG examination, and there was no new or ongoing infusion during this period. Results: We used 6904 ECGs and 1726 ECGs as development and internal validation data sets, respectively. In addition, 1278 ECGs from the Jiangling branch of the Second Affiliated Hospital of Nanchang University were used as external validation data sets. Using 12 ECG leads (leads I, II, III, aVR, aVL, aVF, and V1–6), the area under the receiver operating characteristic curve (AUC) of the DLM was 0.80 (95% confidence interval [CI]: 0.77–0.82) for the internal validation data set. Using an optimal operating point yielded a sensitivity of 71.4% and a specificity of 77.1%. Using the same 12 ECG leads, the external validation data set resulted in an AUC for the DLM of 0.77 (95% CI: 0.75–0.79). Using an optimal operating point yielded a sensitivity of 70.0% and a specificity of 69.1%. Conclusions: In this study, using 12 ECG leads, a DLM detected hypokalemia in emergency patients with an AUC of 0.77 to 0.80. Artificial intelligence could be used to analyze an ECG to quickly screen for hypokalemia.
Collapse
|
3
|
Karaboyas A, Robinson BM, James G, Hedman K, Moreno Quinn CP, De Sequera P, Nitta K, Pecoits-Filho R. Hyperkalemia excursions are associated with an increased risk of mortality and hospitalizations in hemodialysis patients. Clin Kidney J 2021; 14:1760-1769. [PMID: 34221383 PMCID: PMC8243282 DOI: 10.1093/ckj/sfaa208] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2020] [Accepted: 08/31/2020] [Indexed: 12/14/2022] Open
Abstract
BACKGROUND Hyperkalemia is common among hemodialysis (HD) patients and has been associated with adverse clinical outcomes. Previous studies considered a single serum potassium (K) measurement or time-averaged values, but serum K excursions out of the target range may be more reflective of true hyperkalemia events. We assessed whether hyperkalemia excursions lead to an elevated risk of adverse clinical outcomes. METHODS Using data from 21 countries in Phases 4-6 (2009-18) of the Dialysis Outcomes and Practice Patterns Study (DOPPS), we investigated the associations between peak serum K level, measured monthly predialysis, over a 4-month period ('peak K') and clinical outcomes over the subsequent 4 months using Cox regression, adjusted for potential confounders. RESULTS The analysis included 62 070 patients contributing a median of 3 (interquartile range 2-6) 4-month periods. The prevalence of hyperkalemia based on peak K was 58% for >5.0, 30% for >5.5 and 12% for >6.0 mEq/L. The all-cause mortality hazard ratio for peak K (reference ≤5.0 mEq/L) was 1.15 [95% confidence interval (CI) 1.09, 1.21] for 5.1-5.5 mEq/L, 1.19 (1.12, 1.26) for 5.6-6.0 mEq/L and 1.33 (1.23, 1.43) for >6.0 mEq/L. Results were qualitatively consistent when analyzing hospitalizations and a cardiovascular composite outcome. CONCLUSIONS Among HD patients, we identified a lower K threshold (peak K 5.1-5.5 mEq/L) than previously reported for increased risk of hospitalization and mortality, with the implication that a greater proportion (>50%) of the HD population may be at risk. A reassessment of hyperkalemia severity ranges is needed, as well as an exploration of new strategies for effective management of chronic hyperkalemia.
Collapse
Affiliation(s)
| | - Bruce M Robinson
- Arbor Research Collaborative for Health, Ann Arbor, MI, USA
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA
| | - Glen James
- BioPharmaceuticals Medical, AstraZeneca, Cambridge, UK
| | - Katarina Hedman
- BioPharmaceuticals Business Unit, AstraZeneca, Gothenburg, Sweden
| | | | | | - Kosaku Nitta
- Department of Nephrology, Tokyo Women's Medical University, Shinjuku, Tokyo, Japan
| | - Roberto Pecoits-Filho
- Arbor Research Collaborative for Health, Ann Arbor, MI, USA
- School of Medicine, Pontificia Universidade Catolica do Parana, Curitiba, Brazil
| |
Collapse
|
4
|
Brandenburg V, Bauersachs J, Böhm M, Fliser D, Frantz S, Frey N, Hasenfuß G, Kielstein JT. [Symptom control in heart failure patients - how to handle GFR decrease and hyperkalaemia]. Dtsch Med Wochenschr 2021; 146:e47-e55. [PMID: 33482670 PMCID: PMC7972821 DOI: 10.1055/a-1307-8652] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/04/2022]
Abstract
Bei Patienten mit Herzinsuffizienz und reduzierter Ejektionsfraktion wird durch eine optimierte medikamentöse Therapie sowohl die Symptomkontrolle verbessert als auch die Mortalität gesenkt. Eckpfeiler der Herzinsuffizienztherapie sind dabei Medikamente mit Einfluss auf das Renin-Angiotensin-Aldosteron-System, sogenannte RAAS-Inhibitoren. Dieser Artikel stellt einen kardiologisch-nephrologischen Konsens zur praxisorientierten Hilfestellung bei abnehmender glomerulärer Filtrationsrate oder Anstieg des Serum-Kaliumspiegels vor. Dies sind die 2 häufigsten Gründe für eine Dosisreduktion oder das Absetzen von prognoseverbessernden Medikamenten bei Herzinsuffizienzpatienten.
Collapse
Affiliation(s)
- Vincent Brandenburg
- Klinik für Kardiologie, Nephrologie und Internistische Intensivmedizin, Rhein-Maas-Klinikum, Würselen
| | - Johann Bauersachs
- Klinik für Kardiologie und Angiologie, Medizinische Hochschule Hannover
| | - Michael Böhm
- Innere Medizin III - Kardiologie, Angiologie und Internistische Intensivmedizin, Universitätsklinikum des Saarlandes, Homburg/Saar
| | - Danilo Fliser
- Innere Medizin IV - Nieren- und Hochdruckkrankheiten, Universitätsklinikum des Saarlandes, Homburg/Saar
| | - Stefan Frantz
- Medizinische Klinik und Poliklinik I (Kardiologie, Endokrinologie, Nephrologie, Pneumologie, Intensiv- und Notfallmedizin) Universitätsklinikum Würzburg
| | - Norbert Frey
- Klinik für Innere Medizin III (Schwerpunkt Kardiologie, Angiologie und Intensivmedizin), Universitätsklinikum Schleswig-Holstein, Kiel
| | - Gerd Hasenfuß
- Herzzentrum, Abt. Kardiologie und Pneumologie, Universitätsmedizin Göttingen
| | - Jan T Kielstein
- Klinik für Nephrologie, Blutreinigung und Rheumatologie, Klinikum Braunschweig
| |
Collapse
|
5
|
Pilia N, Severi S, Raimann JG, Genovesi S, Dössel O, Kotanko P, Corsi C, Loewe A. Quantification and classification of potassium and calcium disorders with the electrocardiogram: What do clinical studies, modeling, and reconstruction tell us? APL Bioeng 2020; 4:041501. [PMID: 33062908 PMCID: PMC7532940 DOI: 10.1063/5.0018504] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2020] [Accepted: 09/13/2020] [Indexed: 11/14/2022] Open
Abstract
Diseases caused by alterations of ionic concentrations are frequently observed challenges and play an important role in clinical practice. The clinically established method for the diagnosis of electrolyte concentration imbalance is blood tests. A rapid and non-invasive point-of-care method is yet needed. The electrocardiogram (ECG) could meet this need and becomes an established diagnostic tool allowing home monitoring of the electrolyte concentration also by wearable devices. In this review, we present the current state of potassium and calcium concentration monitoring using the ECG and summarize results from previous work. Selected clinical studies are presented, supporting or questioning the use of the ECG for the monitoring of electrolyte concentration imbalances. Differences in the findings from automatic monitoring studies are discussed, and current studies utilizing machine learning are presented demonstrating the potential of the deep learning approach. Furthermore, we demonstrate the potential of computational modeling approaches to gain insight into the mechanisms of relevant clinical findings and as a tool to obtain synthetic data for methodical improvements in monitoring approaches.
Collapse
Affiliation(s)
- N Pilia
- Institute of Biomedical Engineering, Karlsruhe Institute of Technology (KIT), 76131 Karlsruhe, Germany
| | - S Severi
- Department of Electrical, Electronic, and Information Engineering "Guglielmo Marconi," University of Bologna, 47522 Cesena, Italy
| | - J G Raimann
- Renal Research Institute, New York, New York 10065, USA
| | - S Genovesi
- Department of Medicine and Surgery, University of Milan-Bicocca, 20100 Milan, Italy
| | - O Dössel
- Institute of Biomedical Engineering, Karlsruhe Institute of Technology (KIT), 76131 Karlsruhe, Germany
| | | | - C Corsi
- Department of Electrical, Electronic, and Information Engineering "Guglielmo Marconi," University of Bologna, 47522 Cesena, Italy
| | - A Loewe
- Institute of Biomedical Engineering, Karlsruhe Institute of Technology (KIT), 76131 Karlsruhe, Germany
| |
Collapse
|
6
|
Galloway CD, Valys AV, Shreibati JB, Treiman DL, Petterson FL, Gundotra VP, Albert DE, Attia ZI, Carter RE, Asirvatham SJ, Ackerman MJ, Noseworthy PA, Dillon JJ, Friedman PA. Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram. JAMA Cardiol 2020; 4:428-436. [PMID: 30942845 DOI: 10.1001/jamacardio.2019.0640] [Citation(s) in RCA: 172] [Impact Index Per Article: 43.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/17/2023]
Abstract
Importance For patients with chronic kidney disease (CKD), hyperkalemia is common, associated with fatal arrhythmias, and often asymptomatic, while guideline-directed monitoring of serum potassium is underused. A deep-learning model that enables noninvasive hyperkalemia screening from the electrocardiogram (ECG) may improve detection of this life-threatening condition. Objective To evaluate the performance of a deep-learning model in detection of hyperkalemia from the ECG in patients with CKD. Design, Setting, and Participants A deep convolutional neural network (DNN) was trained using 1 576 581 ECGs from 449 380 patients seen at Mayo Clinic, Rochester, Minnesota, from 1994 to 2017. The DNN was trained using 2 (leads I and II) or 4 (leads I, II, V3, and V5) ECG leads to detect serum potassium levels of 5.5 mEq/L or less (to convert to millimoles per liter, multiply by 1) and was validated using retrospective data from the Mayo Clinic in Minnesota, Florida, and Arizona. The validation included 61 965 patients with stage 3 or greater CKD. Each patient had a serum potassium count drawn within 4 hours after their ECG was recorded. Data were analyzed between April 12, 2018, and June 25, 2018. Exposures Use of a deep-learning model. Main Outcomes and Measures Area under the receiver operating characteristic curve (AUC) and sensitivity and specificity, with serum potassium level as the reference standard. The model was evaluated at 2 operating points, 1 for equal specificity and sensitivity and another for high (90%) sensitivity. Results Of the total 1 638 546 ECGs, 908 000 (55%) were from men. The prevalence of hyperkalemia in the 3 validation data sets ranged from 2.6% (n = 1282 of 50 099; Minnesota) to 4.8% (n = 287 of 6011; Florida). Using ECG leads I and II, the AUC of the deep-learning model was 0.883 (95% CI, 0.873-0.893) for Minnesota, 0.860 (95% CI, 0.837-0.883) for Florida, and 0.853 (95% CI, 0.830-0.877) for Arizona. Using a 90% sensitivity operating point, the sensitivity was 90.2% (95% CI, 88.4%-91.7%) and specificity was 63.2% (95% CI, 62.7%-63.6%) for Minnesota; the sensitivity was 91.3% (95% CI, 87.4%-94.3%) and specificity was 54.7% (95% CI, 53.4%-56.0%) for Florida; and the sensitivity was 88.9% (95% CI, 84.5%-92.4%) and specificity was 55.0% (95% CI, 53.7%-56.3%) for Arizona. Conclusions and Relevance In this study, using only 2 ECG leads, a deep-learning model detected hyperkalemia in patients with renal disease with an AUC of 0.853 to 0.883. The application of artificial intelligence to the ECG may enable screening for hyperkalemia. Prospective studies are warranted.
Collapse
Affiliation(s)
| | | | | | | | | | | | | | - Zachi I Attia
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota
| | - Rickey E Carter
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota.,Department of Health Sciences Research, Mayo Clinic, Jacksonville, Florida
| | | | - Michael J Ackerman
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota
| | - Peter A Noseworthy
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota
| | - John J Dillon
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
| | - Paul A Friedman
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota
| |
Collapse
|
7
|
Potassium homeostasis and management of dyskalemia in kidney diseases: conclusions from a Kidney Disease: Improving Global Outcomes (KDIGO) Controversies Conference. Kidney Int 2020; 97:42-61. [DOI: 10.1016/j.kint.2019.09.018] [Citation(s) in RCA: 141] [Impact Index Per Article: 35.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2019] [Revised: 09/13/2019] [Accepted: 09/30/2019] [Indexed: 12/19/2022]
|
8
|
Ucal Y, Coskun A, Ozpinar A. Quality will determine the future of mass spectrometry imaging in clinical laboratories: the need for standardization. Expert Rev Proteomics 2019; 16:521-532. [DOI: 10.1080/14789450.2019.1624165] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/03/2023]
Affiliation(s)
- Yasemin Ucal
- School of Medicine, Department of Medical Biochemistry, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey
| | - Abdurrahman Coskun
- School of Medicine, Department of Medical Biochemistry, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey
| | - Aysel Ozpinar
- School of Medicine, Department of Medical Biochemistry, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey
| |
Collapse
|
9
|
Dylewski JF, Linas S. Variability of Potassium Blood Testing: Imprecise Nature of Blood Testing or Normal Physiologic Changes? Mayo Clin Proc 2018; 93:551-554. [PMID: 29728197 DOI: 10.1016/j.mayocp.2018.03.019] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/03/2018] [Accepted: 03/20/2018] [Indexed: 11/30/2022]
Affiliation(s)
- James F Dylewski
- Division of Renal Disease and Hypertension, Department of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO; Division of Nephrology, Department of Medicine, Denver Health and Hospitals, Denver, CO.
| | - Stuart Linas
- Division of Renal Disease and Hypertension, Department of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO; Division of Nephrology, Department of Medicine, Denver Health and Hospitals, Denver, CO
| |
Collapse
|