The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index; none of the 26 sources its claims cite is checked for support yet.
Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram
Open accessAbstract
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.
Overview
AI snapshot
Written from the paper’s full text.
TL;DR
A deep-learning model using 2 or 4 ECG leads detected hyperkalemia in patients with chronic kidney disease, with 2-lead AUCs of 0.853 to 0.883 across three Mayo Clinic validation sets. At a 90% sensitivity operating point, specificity was 54.7% to 63.2% and negative predictive value was 99.0% to 99.6%.
Key findings
- For 2-lead ECG (leads I and II), the model achieved AUCs of 0.883 (95% CI, 0.873-0.893) in Minnesota, 0.860 (95% CI, 0.837-0.883) in Florida, and 0.853 (95% CI, 0.830-0.877) in Arizona; 4-lead AUCs were 0.880 to 0.901.
- At the high-sensitivity operating point, 2-lead sensitivity/specificity were 90.2%/63.2% in Minnesota, 91.3%/54.7% in Florida, and 88.9%/55.0% in Arizona, corresponding to negative predictive values of 99.0% to 99.6%.
- At the equal sensitivity/specificity operating point, 2-lead sensitivity/specificity were 79.9%/81.3% in Minnesota, 80.5%/75.2% in Florida, and 78.1%/75.3% in Arizona, with negative predictive values of 98.6% to 99.4%.
- False-positive results reached up to 42% at the high-sensitivity point, while false-negative results were less than 1% of all test results; among 58 false-negative patients reviewed, median blood potassium was 5.9 mEq/L and 52% had a subsequent potassium measurement below 5.5 mEq/L within 8 hours.
Methods
- Retrospective study using a deep convolutional neural network with 11 layers (10 convolutional plus a fully connected softmax layer), trained on 1,576,581 ECGs from 449,380 patients at Mayo Clinic, Rochester, Minnesota, from 1994 to 2017.
- The model was trained with 2 leads (I and II) or 4 leads (I, II, V3, and V5) to detect serum potassium ≥5.5 mEq/L and validated on 61,965 ECG-potassium pairs from patients with stage 3 or greater CKD across Mayo Clinic sites in Minnesota, Florida, and Arizona; serum potassium was drawn within 4 hours after the ECG.
- Performance was assessed by AUC and by sensitivity and specificity at two operating points—equal sensitivity and specificity, and 90% sensitivity—with serum potassium as the reference standard; validation focused on ECGs with potassium ≤5.3 mEq/L or ≥5.7 mEq/L.
Limitations
- The paper states that data were retrospective and lacked clinical data such as medication use and medical history; the model was developed and validated using 12-lead ECG data in clinic/hospital settings, so prospective testing is needed for home or ambulatory ECG inputs and to determine whether it improves detection, care, and outcomes.
- The paper states that the DLM does not analyze renal function, that false-negative results may cause false reassurance, and that low specificity with up to 42% false-positive results may cause anxiety and inconvenience, with risk increasing over repeated testing; it also notes insufficient repeated measures to develop a personalized model.
- Evident from the text: validation excluded ECGs with potassium levels between 5.3 and 5.7 mEq/L to avoid misclassification near the threshold, and a sensitivity analysis including all potassium values decreased AUC by 0.02 to 0.04, suggesting performance may be lower in an unselected screening population.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
34 Own result · 17 Sources not found · 15 Own interpretation · 8 Own method · 4 No basis given
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Using the operating point with equal sensitivity and specificity, for ECG leads I and II, the DLM's sensitivity and specificity were 79.9% (95% CI, 77.6%-82.0%)and 81.3% (95% CI, 80.9%-81.6%) in Minnesota; 80.5% (95% CI, 75.4%-84.9%)and 75.2% (95% CI, 74.0%-76.3%) in Florida; and 78.1% (95% CI, 72.7%-82.9%)and 75.3% (95% CI, 74.1%-76.4%) in Arizona.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The algorithm's sensitivity and specificity for validation were 90.2% (95% CI, 88.4%-91.7%)and 63.2% (95% CI, 62.7%-63.6%) in Minnesota; 91.3% (95% CI, 87.4%-94.3%)and 54.7% (95% CI, 53.4%-56.0%) in Florida; and 88.9% (95% CI, 84.5%-92.4%)and 55.0% (95% CI, 53.7%-56.3%) in Arizona.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Given the less than 5% prevalence of hyperkalemia, these findings correspond to a negative predictive value of 98.6% to 99.4% across the validation data sets.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Between 50% and 70% of patients in the validation data sets did not have hyperkalemia predicted by the DLM, with less than 1% of all test results being false-negative; on the other hand, up to 42% of all test results were false-positive.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Using the operating point with equal sensitivity and specificity, for ECG leads I and II, the DLM's sensitivity and specificity were 79.9% (95% CI, 77.6%-82.0%)and 81.3% (95% CI, 80.9%-81.6%) in Minnesota; 80.5% (95% CI, 75.4%-84.9%)and 75.2% (95% CI, 74.0%-76.3%) in Florida; and 78.1% (95% CI, 72.7%-82.9%)and 75.3% (95% CI, 74.1%-76.4%) in Arizona.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Using the operating point with equal sensitivity and specificity, for ECG leads I and II, the DLM's sensitivity and specificity were 79.9% (95% CI, 77.6%-82.0%)and 81.3% (95% CI, 80.9%-81.6%) in Minnesota; 80.5% (95% CI, 75.4%-84.9%)and 75.2% (95% CI, 74.0%-76.3%) in Florida; and 78.1% (95% CI, 72.7%-82.9%)and 75.3% (95% CI, 74.1%-76.4%) in Arizona.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For detection of hyperkalemia using ECG leads I and II, the DLM achieved an AUC of 0.883 (95% CI, 0.873-0.893) in Minnesota; 0.860 (95% CI, 0.837-0.883) in Florida; and 0.853 (95% CI, 0.830-0.877) in Arizona (Figure 2).”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The inclusion of all ECGs and serum potassium values decreased the AUC across all models by 0.02 to 0.04; with a higher prevalence of hyperkalemia, the positive predictive value increased by 3 to 5 percentage points.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The algorithm's sensitivity and specificity for validation were 90.2% (95% CI, 88.4%-91.7%)and 63.2% (95% CI, 62.7%-63.6%) in Minnesota; 91.3% (95% CI, 87.4%-94.3%)and 54.7% (95% CI, 53.4%-56.0%) in Florida; and 88.9% (95% CI, 84.5%-92.4%)and 55.0% (95% CI, 53.7%-56.3%) in Arizona.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The algorithm's sensitivity and specificity for validation were 90.2% (95% CI, 88.4%-91.7%)and 63.2% (95% CI, 62.7%-63.6%) in Minnesota; 91.3% (95% CI, 87.4%-94.3%)and 54.7% (95% CI, 53.4%-56.0%) in Florida; and 88.9% (95% CI, 84.5%-92.4%)and 55.0% (95% CI, 53.7%-56.3%) in Arizona.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Probably not a substantial claim. 20
- The quote only partly states this claim. 1
- It may state two separate claims as one. 16
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“To try to understand how the DNN builds up its understanding of images for hyperkalemia over many layers, we performed feature visualization on the mean ECG beat [33][34][35] (eFigure 3 in the Supplement); sometimes, expected changes in QRS and T-wave morphology were seen.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
What the sources say
- Not matchedcites [33]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [34]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [35]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The AUC was 0.02 to 0.03 higher using ECG leads I, II, V3, and V5.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The quote only partly states this claim.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Finally, the DLM is a screening test with low specificity, with upwards of 42% false-positive results”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Limitations
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Fewer than 3% in Minnesota had hyperkalemia (n = 1282 of 50 099) compared with 4.6% (n = 270 of 5855) to 4.8% (n = 287 of 6011) in Florida and Arizona, respectively.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plainn = 270- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Fewer than 3% in Minnesota had hyperkalemia (n = 1282 of 50 099) compared with 4.6% (n = 270 of 5855) to 4.8% (n = 287 of 6011) in Florida and Arizona, respectively.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plainn = 1,282- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Fewer than 3% in Minnesota had hyperkalemia (n = 1282 of 50 099) compared with 4.6% (n = 270 of 5855) to 4.8% (n = 287 of 6011) in Florida and Arizona, respectively.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plainn = 287- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Hyperkalemia ECGs were more likely to be recorded in patients who were older and men and who had stage 3 or greater CKD.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Between 50% and 70% of patients in the validation data sets did not have hyperkalemia predicted by the DLM, with less than 1% of all test results being false-negative; on the other hand, up to 42% of all test results were false-positive.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
In the paper
“H yperkalemia is potentially life threatening for the 35 million American adults with chronic kidney disease (CKD). 1”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Abstract
What the sources say
- Not matchedcites [1]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“However, guidelinedirected potassium monitoring 5,6 is severely underused: up to one-third of patients taking RAAS inhibitors receive no monitoring, and only 10% receive potassium monitoring before and after RAAS inhibitors are started.7,8”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Abstract
What the sources say
- Not matchedcites [7]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [8]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“A heightened fear of MRA-associated hyperkalemia and hyperkalemia-associated mortality 31 and the complex potassium monitoring requirements for MRA initiation and titration 6 are 2 potential reasons for underuse.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
What the sources say
- Not matchedcites [31]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [6]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The DLM does not offer an analysis of renal function.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Limitations
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the diagnosis of hyperkalemia, particularly outside of the hospital or clinic, is challenging because patients are often asymptomatic, and guideline-directed blood potassium monitoring is severely underperformed.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In other high-probability visualizations, QRS and T-wave features were not present because there are features the DNN extracts that surpass human visualization.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The sample size for each validation data set was determined to be 6133 ECGs and was based on the maximal sample size needs of the area under the receiving operating characteristic curve (AUC) (eMethods in the Supplement).”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Statistical Analysis
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“Previous approaches have used standard regression models to estimate potassium and have highlighted the importance of T-wave width, T-wave amplitude, and descending T-wave slope as predictors of hyperkalemia.16,32”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
What the sources say
- Not matchedcites [16]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [32]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“In patients with CKD, hyperkalemia is common and life threatening.23,24”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
What the sources say
- Not matchedcites [23]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [24]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“an ECG-derived potassium level may be more germane to health and arrhythmia risk than the blood test.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Limitations
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, the patients who most likely require an assessment of renal function are those patients with possible hyperkalemia, for whom the envisioned screening test would require a confirmatory blood test that typically includes renal function in addition to potassium level.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Limitations
hedgedcorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Rests on an assumption: Hyperkalemia is often present in the setting of acute CKD.
In the paper
“Hyperkalemia causes cardiotoxic effects and has been associated with a defined series of ECG abnormalities, including peaking of T waves, QRS prolongation, and PR shortening.9”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Abstract
What the sources say
- Not matchedcites [9]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
In the paper
“In patients with heart failure, MRAs reduce cardiovascular mortality, but only a small fraction (less than one-third of eligible patients) receive them at hospital discharge.30”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
What the sources say
- Not matchedcites [30]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“which may cause anxiety and inconvenience for patients.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Limitations
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim could be matched to a paper in Crossref, so there is nothing to check it against.
In the paper
“Although treatments for hyperkalemia are effective and readily available, 2 5 including the US Food and Drug Administration-approved potassium binders patiromer 26 and zirconium cyclosilicate, 27”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
What the sources say
- Not matchedcites [25]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [26]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [27]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“A DLM that enables noninvasive potassium monitoring could assuage the fears of health care clinicians and enable more patients with CKD with heart failure to receive target doses of MRAs and other guideline-recommended medications, potentially improving care and outcomes.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
hedgedconditional- Asserted: passes — The authors put it forward as true.
- Checkable: fails — It may be too vague to check against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. It may be too vague to check against evidence. It may state two separate claims as one.
In the paper
“Owing to the effects of kidney dysfunction on potassium homeostasis, as well as the recommendation that these patients be treated with renin-angiotensin-aldosterone system (RAAS) inhibitors that preserve renal and cardiac function but also inhibit renal potassium secretion, the risk of hyperkalemia in CKD is substantially elevated.2”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Abstract
What the sources say
- Not matchedcites [2]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“To our knowledge, this is the first deep-learning approach to evaluation of potassium levels from the ECG.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: fails — The paper may give no reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The risk of falsepositive results will also increase over time with repeated testing.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Limitations
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“The 1-day odds of mortality are up to 13 times higher for patients with CKD with outpatient serum potassium levels of at least 6.0 mEq/L compared with patients without CKD with potassium levels of less than 5.5 mEq/L.3”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
What the sources say
- Not matchedcites [3]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“On average, patients with CKD spend up to 9% of their time with serum potassium levels 5.5 mEq/L or greater. 2”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Discussion
What the sources say
- Not matchedcites [2]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably not a substantial claim. The paper’s conclusions may not depend on it.
- Not matched
In the paper
“When present, hyperkalemia is often asymptomatic and associated with cardiac arrhythmias and death.3”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Abstract
What the sources say
- Not matchedcites [3]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plaincorrelational- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It may state two separate claims as one.
- Not matched
The paper relies on this without support.
The serum potassium level measured within 4 hours after the ECG reflects the potassium level at the time of the ECG.
“All ECGs within 4 hours before a serum potassium draw were identified.16”
The paper relies on this without support.
The Gaussian process used to estimate potassium level at the time of ECG in the development data set accurately estimates the true potassium level.
“Gaussian process to estimate potassium level at time of ECG”
The paper relies on this without support.
Hyperkalemia is often present in the setting of acute CKD.
“Hyperkalemia is often present in the setting of acute CKD.”
The paper relies on this without support.
ECG-based tests are not susceptible to mechanical, temperature, contamination, or other potential errors associated with processing blood.
“The ECGbased tests are not susceptible to mechanical, temperature, contamination, or the other potential errors associated with processing blood.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“potassium models may prioritize urgent laboratory testing without replacing serum measurement [6,15].”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [6]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Emerging evidence suggests that ECG waveforms contain latent signatures of ventricular dysfunction [4], structural heart disease [5], metabolic abnormalities [6], and broader physiologic characteristics such as biological age [7] and future mortality risk [8].”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [6]
The cited source says what the claim attributes to it.
In the citing paper
“This study expanded AI-ECG by suggesting that ECG waveforms could support noninvasive screening for a metabolic abnormality ordinarily diagnosed through laboratory testing.”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [6]
The cited source says what the claim attributes to it.
In the citing paper
“The model was trained on more than 1.5 million ECGs from over 449,000 patients and, using only leads I and II, detected hyperkalemia with AUC values ranging from 0.853 to 0.883 across validation sites [6].”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [6]
The cited source says what the claim attributes to it.
In the citing paper
“The reduced-lead hyperkalemia model discussed earlier demonstrated that clinically relevant metabolic information can be retained using only two or four ECG leads [6].”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [6]
In the citing paper
“Hyperkalaemia detection via wearable ECG is feasible but has high false-positive rates”
From Smart wearable devices in cardiovascular care: Where we are and how to move forward (2021) · cites this paper as [82]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“The remaining 10% of patients (n = 109 860 of 787 661) were reserved for future analysis.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Development and Validation Data sets
Reported 10 · recomputed 13.947625
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“with 60% of patients used for DLM development (n = 449 380 of 787 661; development dataset)”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Development and Validation Data sets
Reported 60 · recomputed 57.052463
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Abstract
“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”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Hyperkalemia
“We defined hyperkalemia as a serum potassium value of at least 5.5 mEq/L”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“| White | NA | 5077 (84.5) | 5271 (9.0) | NA |”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Conclusions
Reported 9 · recomputed 90.025619
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“| Black | NA | 650 (1.8) | 193 (3.3) | NA |”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Conclusions
Reported 1.8 · recomputed 10.813509
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Results
“4.6% (n = 270 of 5855) to 4.8% (n = 287 of 6011) in Florida and Arizona, respectively.”
§ Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram > Conclusions
“| Potassium ≥5.7 mEq/L, No. (%) g | 1282 (2.6) | 287 (4.8) | 270 (4.6) | NA |”
Citations
Cites
pROC: an open-source package for R and S+ to analyze and compare ROC curves
Robin, X., Turck, N., Hainard, A., Tiberti, N., Lisacek, F., Sanchez, J.-C., & Müller, M. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-77 · Cited by 13,697
2013 ACCF/AHA Guideline for the Management of Heart Failure
Yancy, C. W., Jessup, M., Bozkurt, B., Butler, J., Casey, D. E., Drazner, M. H., Fonarow, G. C., Geraci, S. A., Horwich, T., Januzzi, J. L., et al. (2013) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2013.05.019 · Cited by 12,536
Ahmed, A., Jorna, T., & Bhandari, S. (2016) · The Nephron journals/Nephron journals · doi:10.1159/000447068 · Cited by 11,782
Ting, D. S. W., Cheung, C. Y.-L., Lim, G., Tan, G. S. W., Quang, N. D., Gan, A., Hamzah, H., Garcia-Franco, R., San Yeo, I. Y., Lee, S. Y., et al. (2017) · JAMA · doi:10.1001/jama.2017.18152 · Cited by 2,402
Diagnostic Performance of Digital versus Film Mammography for Breast-Cancer Screening
Pisano, E. D., Gatsonis, C. A., Hendrick, E. R., Yaffe, M. J., Baum, J. K., Acharyya, S., Conant, E. F., Fajardo, L. L., Bassett, L. W., D'Orsi, C. J., et al. (2005) · New England Journal of Medicine · doi:10.1056/nejmoa052911 · Cited by 1,937
Multitarget Stool DNA Testing for Colorectal-Cancer Screening
Imperiale, T. F., Ransohoff, D. F., Itzkowitz, S. H., Levin, T. R., Lavin, P., Lidgard, G. P., Ahlquist, D. A., & Berger, B. M. (2014) · New England Journal of Medicine · doi:10.1056/nejmoa1311194 · Cited by 1,900
Rates of hyperkalemia after publication of the Randomized Aldactone Evaluation Study
Juurlink, D. N., Mamdani, M. M., Lee, D. S., Kopp, A., Austin, P. C., Laupacis, A., & Redelmeier, D. A. (2004) · New England Journal of Medicine · doi:10.1056/nejmoa040135 · Cited by 1,761
Phases of Biomarker Development for Early Detection of Cancer
Pepe, M. S., Etzioni, R., Feng, Z., Potter, J. D., Thompson, M. L., Thornquist, M., Winget, M., & Yasui, Y. (2001) · JNCI Journal of the National Cancer Institute · doi:10.1093/jnci/93.14.1054 · Cited by 1,686
(2004) · American Journal of Kidney Diseases · doi:10.1053/j.ajkd.2004.03.003 · Cited by 1,236
Olah, C., Mordvintsev, A., & Schubert, L. (2017) · Distill · doi:10.23915/distill.00007 · Cited by 880
Research works printed but not linked: 1
- Erhan, 2009, Visualizing Higher-Layer Features of a Deep Network: Technical Report 1341
Cited by
Sorted by citations
Key challenges for delivering clinical impact with artificial intelligence
Kelly, C. J., Karthikesalingam, A., Suleyman, M., Corrado, G., & King, D. (2019) · BMC Medicine · doi:10.1186/s12916-019-1426-2 · Cited by 3,136
“Applications have also been shown in pathology [18], identifying cancerous skin lesions [19 – 22], interpreting retinal imaging [23, 24], detecting arrhythmias [25, 26], and even identifying hyperkalaemia from electrocardiograms [27].”
BackgroundSmart wearable devices in cardiovascular care: Where we are and how to move forward
Bayoumy, K., Gaber, M., Elshafeey, A., Mhaimeed, O., Dineen, E. H., Marvel, F. A., Martin, S. S., Muse, E. D., Turakhia, M. P., Tarakji, K. G., et al. (2021) · Nature Reviews Cardiology · doi:10.1038/s41569-021-00522-7 · Cited by 829
Artificial intelligence in clinical and genomic diagnostics
Dias, R., & Torkamani, A. (2019) · Genome Medicine · doi:10.1186/s13073-019-0689-8 · Cited by 499
“AI applied to electrocardiograms can detect and classify arrythmias [22], especially atrial fibrillation [23], as well as cardiac contractile dysfunction [24], and blood chemistries linked to cardiac rhythm abnormalities [25].”
BackgroundRETRACTED ARTICLE: Artificial intelligence and machine learning in precision and genomic medicine
Quazi, S. (2022) · Medical Oncology · doi:10.1007/s12032-022-01711-1 · Cited by 466
“[165] ML to screen for hyperkalemia in severe renal disease patients using ECG from three Mayo Clinic facilities in Florida, Minnesota, and Arizona.”
MethodRetractedApplication of artificial intelligence to the electrocardiogram
Attia, Z. I., Harmon, D., Behr, E. R., & Friedman, P. A. (2021) · European Heart Journal · doi:10.1093/eurheartj/ehab649 · Cited by 337
Self-citationUse of Machine Learning Models to Predict Death After Acute Myocardial Infarction
Khera, R., Haimovich, J. S., Hurley, N. C., McNamara, R. L., Spertus, J. A., Desai, N. R., Rumsfeld, J. S., Masoudi, F. A., Huang, C., Normand, S. T., et al. (2021) · JAMA Cardiology · doi:10.1001/jamacardio.2021.0122 · Cited by 302
Deep learning and the electrocardiogram: review of the current state-of-the-art
Somani, S. S., Russak, A. J., Richter, F., Zhao, S., Vaid, A., Chaudhry, F. F., Freitas, J. K. D., Naik, N., Miotto, R., Nadkarni, G. N., et al. (2020) · EP Europace · doi:10.1093/europace/euaa377 · Cited by 276
“64,65 conducted a multi-centre study on patients from various Mayo Clinic sites in the US to identify the presence of hyper-kalaemia in chronic kidney disease patients using 2-and 4-lead ECGs.”
How useful is the smartwatch ECG?
Isakadze, N., & Martin, S. S. (2019) · Trends in Cardiovascular Medicine · doi:10.1016/j.tcm.2019.10.010 · Cited by 234
CURATE.AI: Optimizing Personalized Medicine with Artificial Intelligence
Blasiak, A., Khong, J., & Kee, T. W. (2019) · SLAS TECHNOLOGY · doi:10.1177/2472630319890316 · Cited by 234
Artificial Intelligence and Machine Learning in Arrhythmias and Cardiac Electrophysiology
Feeny, A. K., Chung, M. K., Madabhushi, A., Attia, Z. I., Čikeš, M., Firouznia, M., Friedman, P. A., Kalscheur, M. M., Kapa, S., Narayan, S. M., et al. (2020) · Circulation Arrhythmia and Electrophysiology · doi:10.1161/circep.119.007952 · Cited by 215
Self-citationAbnormalities of Potassium in Heart Failure
Ferreira, J. P., Butler, J., Rossignol, P., Pitt, B., Anker, S. D., Kosiborod, M., Lund, L. H., Bakris, G. L., Weir, M. R., & Zannad, F. M. (2020) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2020.04.021 · Cited by 208
Clinical Management of Hyperkalemia
Palmer, B. F., Carrero, J. J., Clegg, D. J., Colbert, G. B., Emmett, M., Fishbane, S. N., Hain, D. J., Lerma, E. V., Onuigbo, M. A. C., Rastogi, A., et al. (2020) · Mayo Clinic Proceedings · doi:10.1016/j.mayocp.2020.06.014 · Cited by 204
Prospective evaluation of smartwatch-enabled detection of left ventricular dysfunction
Attia, Z. I., Harmon, D. M., Dugan, J., Manka, L., Lopez-Jimenez, F., Lerman, A., Siontis, K. C., Noseworthy, P. A., Yao, X., Klavetter, E. W., et al. (2022) · Nature Medicine · doi:10.1038/s41591-022-02053-1 · Cited by 154
Self-citationCho, Y., Kwon, J., Kim, K., Medina‐Inojosa, J. R., Jeon, K., Cho, S., Lee, S. Y., Park, J., & Oh, B. (2020) · Scientific Reports · doi:10.1038/s41598-020-77599-6 · Cited by 148
“Attia et al. developed deep-learning algorithms for screening cardiac contractile dysfunction, predicting the occurrence of atrial fibrillation during sinus rhythm, approximating age and sex, and detecting hyperkalemia using raw ECG data and demonstrated its feasibility 11,12,24,25 .”
MethodDeep learning models for electrocardiograms are susceptible to adversarial attack
Han, X., Hu, Y., Foschini, L., Chinitz, L. A., Jankelson, L., & Ranganath, R. (2020) · Nature Medicine · doi:10.1038/s41591-020-0791-x · Cited by 146
Artificial intelligence in the diagnosis and management of arrhythmias
Nagarajan, V. D., Su-Lin, L., Robertus, J. L., Nienaber, C. A., Trayanova, N. A., & Ernst, S. (2021) · European Heart Journal · doi:10.1093/eurheartj/ehab544 · Cited by 139
Artificial Intelligence for Cardiovascular Care—Part 1: Advances
Elias, P. A., Jain, S. S., Poterucha, T. J., Randazzo, M. J., Jimenez, F. L., Khera, R., Perez, M. V., Ouyang, D., Pirruccello, J. P., Salerno, M., et al. (2024) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2024.03.400 · Cited by 141
Giudicessi, J. R., Schram, M. C., Bos, J. M., Galloway, C. D., Shreibati, J. B., Johnson, P. W., Carter, R. E., Disrud, L. W., Kleiman, R., Attia, Z. I., et al. (2021) · Circulation · doi:10.1161/circulationaha.120.050231 · Cited by 130
Self-citationSanmarchi, F., Fanconi, C., Golinelli, D., Gori, D., Hernandez‐Boussard, T., & Capodici, A. (2023) · Journal of Nephrology · doi:10.1007/s40620-023-01573-4 · Cited by 151
Explainable artificial intelligence to detect atrial fibrillation using electrocardiogram
Jo, Y., Cho, Y., Lee, S. Y., Kwon, J., Kim, K., Jeon, K., Cho, S., Park, J., & Oh, B. (2020) · International Journal of Cardiology · doi:10.1016/j.ijcard.2020.11.053 · Cited by 129
Machine Learning in Arrhythmia and Electrophysiology
Trayanova, N. A., Popescu, D. M., & Shade, J. K. (2021) · Circulation Research · doi:10.1161/circresaha.120.317872 · Cited by 128
“…ECG, signatures (often hidden from the human eye) of many diseased states, such as contractile and relaxation dysfunction 143,144,155 , PVCs 156 , hyperkalemia 145 , and nocturnal hypoglycemic events 147 , and to estimate blood pressure 152 , and “physical age” (vs. chronological) and sex 153 .”
BackgroundAkter, S., Habib, A., Islam, M. A., Hossen, M. S., Fahim, W. A., Sarkar, P. R., & Ahmed, M. (2021) · IEEE Access · doi:10.1109/access.2021.3129491 · Cited by 113
Current applications of big data and machine learning in cardiology.
Cuocolo, R., Perillo, T., Rosa, E. D., Ugga, L., & Petretta, M. (2019) · PubMed Central · doi:10.11909/j.issn.1671-5411.2019.08.002 · Cited by 97
“[32] used ML for the screening of hyperkalemia in patients with chronic kidney disease from ECG retrieved from three Mayo Clinic centers in Minnesota, Florida, and Arizona.”
BackgroundMethodInfluentialDeep learning models for the prediction of intraoperative hypotension
Lee, S., Lee, H., Chu, Y., Song, S. W., Ahn, G. J., Lee, H., Yang, S., & Koh, S. B. (2021) · British Journal of Anaesthesia · doi:10.1016/j.bja.2020.12.035 · Cited by 102
Chang, C., Lin, C., Luo, Y., Lee, Y., & Lin, C. (2022) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2022.754909 · Cited by 96
“Previous studies have also developed a series of ECG-based DLMs on arrhythmia (8), acute myocardial infarction (9, 10), aortic dissection (11), dyskalemia (12–14), left ventricular dysfunction (15, 16), mitral regurgitation (17), aortic stenosis (18), glycemic profile (19, 20), etc.”
BackgroundRole of Artificial Intelligence in Kidney Disease
Yuan, Q., Zhang, H., Deng, T., Tang, S., Yuan, X., Tang, W., Xie, Y., Ge, H., Wang, X., Zhou, Q., et al. (2020) · International Journal of Medical Sciences · doi:10.7150/ijms.42078 · Cited by 81
Ketogenic diet reshapes cancer metabolism through lysine β-hydroxybutyrylation
Qin, J., Huang, X., Gou, S., Zhang, S., Gou, Y., Zhang, Q., Chen, H., Sun, L., Chen, M., Liu, D., et al. (2024) · Nature Metabolism · doi:10.1038/s42255-024-01093-w · Cited by 85
Chen, S. W., Wang, S. L., Qi, X. Z., et al. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103493 · Cited by 75
An ECG-based artificial intelligence model for assessment of sudden cardiac death risk
Holmström, L. T. A., Chugh, H. S., Nakamura, K., Bhanji, Z., Seifer, M., Uy‐Evanado, A., Reinier, K., Ouyang, D., & Chugh, S. S. (2024) · Communications Medicine · doi:10.1038/s43856-024-00451-9 · Cited by 77
Automatic Triage of 12‐Lead ECGs Using Deep Convolutional Neural Networks
van de Leur, R. R., Blom, L. J., Gavves, E., Hof, I. E., van der Heijden, J. F., Clappers, N., Doevendans, P. A., Hassink, R. J., & van Es, R. (2020) · Journal of the American Heart Association · doi:10.1161/jaha.119.015138 · Cited by 70
“18,19 This study aims to develop and validate a DNN for comprehensive automated ECG triage that could support daily clinical practice.”
BackgroundOuyang, D., Theurer, J., Stein, N. R., Hughes, J. W., Elias, P., He, B., Yuan, N., Duffy, G., Sandhu, R. K., Ebinger, J., et al. (2024) · The Lancet Digital Health · doi:10.1016/s2589-7500(23)00220-0 · Cited by 64
Ahn, J. C., Attia, Z. I., Rattan, P., Mullan, A. F., Buryska, S. M., Allen, A. M., Kamath, P. S., Friedman, P. A., Shah, V. H., Noseworthy, P. A., et al. (2021) · The American Journal of Gastroenterology · doi:10.14309/ajg.0000000000001617 · Cited by 68
“…studies which successfully demonstrate the ability of AI-ECG models to predict a variety of cardiac and noncardiac conditions, including left ventricular dysfunction (27), hypertrophic cardiomyopathy (28), paroxysmal atrial fi brillation (29), as well as hyperkalemia (30), sex, and age (31).”
BackgroundSelf-citationArtificial Intelligence Interpretation of the Electrocardiogram: A State-of-the-Art Review
Ose, B. M., Sattar, Z., Gupta, A., Gahona, C. C. T., Harvey, C., & Noheria, A. (2024) · Current Cardiology Reports · doi:10.1007/s11886-024-02062-1 · Cited by 73
Artificial intelligence for detecting electrolyte imbalance using electrocardiography
Kwon, J., Jung, M., Kim, K., Jo, Y., Shin, J. H., Cho, Y., Lee, Y., Ban, J., Jeon, K., Lee, S. Y., et al. (2021) · Annals of Noninvasive Electrocardiology · doi:10.1111/anec.12839 · Cited by 63
“…valvular heart disease, left ventricular hypertrophy, and anemia (Attia, Friedman, et al., 2019; Attia, Kapa, et al., 2019; Attia, Noseworthy, et al., 2019; Cho et al., 2020; Galloway et al., 2019; Jo et al., 2020; Kwon, Cho, et al., 2020; Kwon, Kim, et al., 2020; Kwon, Lee, et al., 2020).”
BackgroundMethodInfluentialHa, A. C. T., Doumouras, B. S., Wang, C., Tranmer, J. E., & Lee, D. S. (2022) · Canadian Journal of Cardiology · doi:10.1016/j.cjca.2022.01.007 · Cited by 74
JCS/JHRS 2022 Guideline on Diagnosis and Risk Assessment of Arrhythmia
Takase, B., Ikeda, T., Shimizu, W., Abe, H., Aiba, T., Chinushi, M., Koba, S., KUSANO, K. F., Niwano, S., Takahashi, N., et al. (2023) · Circulation Journal · doi:10.1253/circj.cj-22-0827 · Cited by 68
Wearing Your Heart on Your Sleeve: the Future of Cardiac Rhythm Monitoring
Al‐Alusi, M. A., Ding, E., McManus, D. D., & Lubitz, S. A. (2019) · Current Cardiology Reports · doi:10.1007/s11886-019-1223-8 · Cited by 59
Artificial intelligence in personalized cardiovascular medicine and cardiovascular imaging
Haq, I.-U., Haq, I., & Xu, B. (2021) · Cardiovascular Diagnosis and Therapy · doi:10.21037/cdt.2020.03.09 · Cited by 62
“The democratisation of AI into every day wearable technology is further adding a new wave of lower cost, more accurate and easily accessible screening tools (15,16).”
BackgroundArtificial Intelligence Technologies in Cardiology
Ledziński, Ł., & Grześk, G. (2023) · Journal of Cardiovascular Development and Disease · doi:10.3390/jcdd10050202 · Cited by 72
“Galloway et al. [43] reported the possibility of enabling the usage of a trained CNN model to screen hyperkalemia in patients with renal disease from electrocardiograms, achieving an AUC above 0.85.”
InfluentialMulti-label correlation guided feature fusion network for abnormal ECG diagnosis
Ge, Z., Jiang, X., Tong, Z., Feng, P., Zhou, B., Xu, M., Wang, Z., & Pang, Y. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107508 · Cited by 58
Chen, H., Lin, C., Fang, W., Lou, Y.-S., Cheng, C., Cheng, C., & Lee, C. (2022) · Journal of Personalized Medicine · doi:10.3390/jpm12030455 · Cited by 53
The year in cardiovascular medicine 2021: digital health and innovation
Vardas, P. E., Asselbergs, F. W., van Smeden, M., & Friedman, P. A. (2021) · European Heart Journal · doi:10.1093/eurheartj/ehab874 · Cited by 52
Self-citationA fully-automated paper ECG digitisation algorithm using deep learning
Wu, H., Patel, K. H. K., Li, X., Zhang, B., Galazis, C., Bajaj, N., Sau, A., Shi, X., Sun, L., Tao, Y., et al. (2022) · Scientific Reports · doi:10.1038/s41598-022-25284-1 · Cited by 57
Hinai, G. A., Jammoul, S., Vajihi, Z., & Afilalo, J. (2021) · European Heart Journal - Digital Health · doi:10.1093/ehjdh/ztab048 · Cited by 56
“10 techniques to enable (to some extent) the interpretation of model predictions (34-36) .”
BackgroundArtificial Intelligence in Cardiovascular Medicine: Current Insights and Future Prospects
Haq, I. U., Chhatwal, K., SANAKA, K. O., & Xu, B. (2022) · Vascular Health and Risk Management · doi:10.2147/vhrm.s279337 · Cited by 65
Ding, C., Yao, T., Wu, C., & Ni, J. (2024) · Biosensors and Bioelectronics · doi:10.1016/j.bios.2024.117073 · Cited by 78
The application of deep learning in electrocardiogram: Where we came from and where we should go?
Sun, J.-Y., Shen, H., Qu, Q., Sun, W., & Kong, X.-Q. (2021) · International Journal of Cardiology · doi:10.1016/j.ijcard.2021.05.017 · Cited by 50
Attia, Z. I., Dugan, J., Rideout, A., Maidens, J. N., Venkatraman, S., Guo, L., Noseworthy, P. A., Pellikka, P. A., Pham, S. L., Kapa, S., et al. (2022) · European Heart Journal - Digital Health · doi:10.1093/ehjdh/ztac030 · Cited by 46
Self-citationDeep learning-based electrocardiographic screening for chronic kidney disease
Holmström, L. T. A., Christensen, M., Yuan, N., Hughes, J. W., Theurer, J., Jujjavarapu, M., Fatehi, P., Kwan, A. C., Sandhu, R. K., Ebinger, J. E., et al. (2023) · Communications Medicine · doi:10.1038/s43856-023-00278-w · Cited by 50
“Prior work has shown such patterns are detectable on ECG waveforms, contributing to the AI-ECG detection of hyperkalemia, which might augment a model ’ s ability to detect CKD 19,20 .”
Costanzo, A. D., Spaccarotella, C., Esposito, G., & Indolfi, C. (2024) · Journal of Clinical Medicine · doi:10.3390/jcm13041033 · Cited by 49
Feeny, A. K., Rickard, J., Trulock, K. M., Patel, D. R., Toro, S., Moennich, L. A., Varma, N., Niebauer, M. J., Gorodeski, E. Z., Grimm, R. A., et al. (2020) · Circulation Arrhythmia and Electrophysiology · doi:10.1161/circep.119.008210 · Cited by 43
“27 Unsupervised machine learning of ECG morphology identified phenotypes of hypertrophic cardiomyopathy.”
BackgroundArtificial Intelligence-Enabled ECG: a Modern Lens on an Old Technology
Kashou, A. H., May, A. M., & Noseworthy, P. A. (2020) · Current Cardiology Reports · doi:10.1007/s11886-020-01317-x · Cited by 55
Self-citationLin, C., Lee, Y., Fang, W., Lou, Y.-S., Kuo, F.-C., Lee, C., & Lin, C. S. (2021) · Journal of Personalized Medicine · doi:10.3390/jpm11080725 · Cited by 42
“The current revolution in artificial intelligence (AI) based on deep learning models (DLMs) is a data-driven technique to learn useful features in an automated fashion [20], which is powerful for detecting myocardial infarction [21], digoxin toxicity [22], arrhythmia [23,24], hyperkalemia [25,26], left ventricular dys…”
BackgroundPrediction of arrhythmia susceptibility through mathematical modeling and machine learning
Varshneya, M., Mei, X., & Sobie, E. A. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2104019118 · Cited by 39
“For example, convolutional neural networks have been applied to electrocardiographic (ECG) traces from tens of thousands of patients to build classifiers that differentiate between different types of arrhythmias (41, 42).”
MethodDiuretic-induced hypokalaemia: an updated review
Lin, Z., Wong, L. Y. F., & Cheung, B. M. Y. (2021) · Postgraduate Medical Journal · doi:10.1136/postgradmedj-2020-139701 · Cited by 39
Machine learning in cardiology: Clinical application and basic research
Komuro, J., Kusumoto, D., Hashimoto, H., & Yuasa, S. (2023) · Journal of Cardiology · doi:10.1016/j.jjcc.2023.04.020 · Cited by 41
Foundation model of ECG diagnosis: Diagnostics and explanations of any form and rhythm on ECG
Tian, Y., Li, Z., Jin, Y., Wang, M., Wei, X., Zhao, L., Liu, Y., Liu, J., & Liu, C. (2024) · Cell Reports Medicine · doi:10.1016/j.xcrm.2024.101875 · Cited by 52
“41 Our future work will focus on developing techniques for more precise alignment between ECG and medical text knowledge by integrating various data types, including tabular data, to further expand our downstream task research.”
Kooman, J. P., Wieringa, F. P., Han, M., Chaudhuri, S., SANDE, F. M. V. D., Usvyat, L. A., & Kotanko, P. (2020) · Nephrology Dialysis Transplantation · doi:10.1093/ndt/gfaa015 · Cited by 42
“In healthy subjects, the ECG quality using this method was found to be acceptable [23].”
MethodInfluentialAdopting artificial intelligence in cardiovascular medicine: a scoping review
Makimoto, H., & Kohro, T. (2023) · Hypertension Research · doi:10.1038/s41440-023-01469-7 · Cited by 38
A method to screen left ventricular dysfunction through ECG based on convolutional neural network
Sun, J., Qiu, Y., Guo, H., Yang, H., Shao, B., Qiao, Y., Guo, J., Ding, H., Zhang, Z., Miao, L., et al. (2021) · Journal of Cardiovascular Electrophysiology · doi:10.1111/jce.14936 · Cited by 36
“For example, a recent AI model proposed by Galloway et al.(21) was able to screen for hyperkalemia from the electrocardiogram with a sensitivity of 88.”
MethodInfluentialIntegration of artificial intelligence and multi-omics in kidney diseases
Zhou, S., Zhong, X., & Duan, L. (2022) · Fundamental Research · doi:10.1016/j.fmre.2022.01.037 · Cited by 37
“It was reported that a deep-learning model based on electro-cardiogram (ECG) data might improve the detection of life-threatening hyperkalemia in CKD, enabling noninvasive screening [145] .”
Big Data and Artificial Intelligence: Opportunities and Threats in Electrophysiology
van de Leur, R. R., Boonstra, M., Bagheri, A., Roudijk, R. W., Sammani, A., Taha, K., Doevendans, P. A., van der Harst, P., van Dam, P. M., Hassink, R. J., et al. (2020) · Arrhythmia & Electrophysiology Review · doi:10.15420/aer.2020.26 · Cited by 34
“21,50,59 As a next step, supplementing ECG-based DNNs with body surface mapping data with a high spatial resolution (e.g. more than 12 measurement electrodes), inverse electrocardiography data”
MethodPoint-of-care and self-testing for potassium: recent advances
Hutter, T., Collings, T. S., Kostova, G., & Karet, F. E. (2022) · Sensors & Diagnostics · doi:10.1039/d2sd00062h · Cited by 36
López-Jiménez, F. A., Kapa, S., Friedman, P. A., LeBrasseur, N. K., Klavetter, E. W., Mangold, K. E., & Attia, Z. I. (2024) · JACC. Clinical electrophysiology · doi:10.1016/j.jacep.2024.02.011 · Cited by 38
Self-citationDialysis adequacy predictions using a machine learning method
Kim, H. W., Heo, S., Kim, J. Y., Kim, A., Nam, C. M., & Kim, B. S. (2021) · Scientific Reports · doi:10.1038/s41598-021-94964-1 · Cited by 34
Discovering hidden information in biosignals from patients using artificial intelligence
Yoon, D., Jang, J.-H., Choi, B., Kim, T. Y., & Han, C. (2020) · Korean Journal of Anesthesiology · doi:10.4097/kja.19475 · Cited by 38
“5 mEq/L) among patients with chronic kidney disease based on a 12-electrode ECG [18].”
BackgroundAnalysis on Deep Learning methods for ECG based Cardiovascular Disease prediction
Kusuma, S., & Udayan, J. D. (2020) · Scalable Computing Practice and Experience · doi:10.12694/scpe.v21i1.1640 · Cited by 32
“[22] DNN (Deep Convolutional neural network) 576581 ECGs from 449380 pateints at Mayo clinic, Rochester, Minnesota, from 1994 to 2017 Obtained accuracy of 90.”
MethodLanglais, É. L., Thériault-Lauzier, P., Marquis‐Gravel, G., Kulbay, M., So, D. Y. F., Tanguay, J., Ly, H. Q., Gallo, R., Lesage, F., & Avram, R. (2022) · Journal of Cardiovascular Translational Research · doi:10.1007/s12265-022-10260-x · Cited by 35
“Other applications of deep learning have been developed using 12-lead ECGs, such as screening for hyperkalemia [44], screening for aortic stenosis or mitral regurgitation [45], predicting transthoracic echocardiogram (TTE) parameters of cardiac structure and function [46], or detecting conditions such as left ventricu…”
Predicting Malignant Ventricular Arrhythmias Using Real-Time Remote Monitoring
Ginder, C. R., Li, J., Halperin, J. L., Akar, J. G., Martin, D. T., Chattopadhyay, I., & Upadhyay, G. A. (2023) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2022.12.024 · Cited by 32
Serum Potassium Monitoring Using AI-Enabled Smartwatch Electrocardiograms
Chiu, I.-M., Wu, P.-J., Zhang, H., Hughes, J. W., Rogers, A. J., Jalilian, L., Perez, M., Lin, C.-H. R., Lee, C.-T., Zou, J., et al. (2024) · JACC: Clinical Electrophysiology · doi:10.1016/j.jacep.2024.07.023 · Cited by 31
ECG frequency changes in potassium disorders: a narrative review.
Teymouri, N., Mesbah, S., Navabian, S. M. H., et al. (2022) · PubMed · Cited by 31
Lv, W., Wang, Y., Zhou, C., Huang, S., Pang, M., Xu, Q., Zhang, Q., Huang, C., Li, X., Zhou, Z., et al. (2021) · Lung Cancer · doi:10.1016/j.lungcan.2021.03.008 · Cited by 31
Lin, C. S., Lin, C., Lee, D.-J., Lee, C., Chen, S., Tsai, S., Kuo, F.-C., Chau, T., & Lin, S. (2021) · Journal of the Endocrine Society · doi:10.1210/jendso/bvab120 · Cited by 31
Artificial intelligence using electrocardiography: strengths and pitfalls
Kwon, J., Jo, Y., Lee, S. Y., & Kim, K. (2021) · European Heart Journal · doi:10.1093/eurheartj/ehab090 · Cited by 31
Pasero, E. G. A., Gaïta, F., Randazzo, V., Meynet, P., Cannata, S., Maury, P., & Giustetto, C. (2023) · Sensors · doi:10.3390/s23218900 · Cited by 29
“…pressure estimation [20–24], estimation of age and sex [25], prediction of underlying cardiac contractile dysfunction [26] and of hyperkalemia [27], arrhythmia classification [28–30], detection of hypertrophic cardiomyopathy [31], early detection of cardiovascular autonomic neuropathy [32],…”
BackgroundShibutani, H., Fujii, K., Ueda, D., Kawakami, R., Imanaka, T., Kawai, K., Matsumura, K., Hashimoto, K., Yamamoto, A., Hao, H., et al. (2021) · Atherosclerosis · doi:10.1016/j.atherosclerosis.2021.06.003 · Cited by 29
Ho, C. W.-L., & Caals, K. (2021) · Seminars in Nephrology · doi:10.1016/j.semnephrol.2021.05.009 · Cited by 36
Deep-Learning Model for Screening Sepsis Using Electrocardiography
Kwon, J.-M., Lee, Y. R., Jung, M.-S., Lee, Y.-J., Jo, Y.-Y., Kang, D.-Y., Lee, S. Y., Cho, Y.-H., Shin, J.-H., Ban, J.-H., et al. (2021) · Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine · doi:10.1186/s13049-021-00953-8 · Cited by 28
Mori, M., Durant, T. J. S., Huang, C., Mortazavi, B. J., Coppi, A. C., Jean, R. A., Geirsson, A., Schulz, W. L., & Krumholz, H. M. (2021) · Circulation Cardiovascular Quality and Outcomes · doi:10.1161/circoutcomes.120.007363 · Cited by 28
Potential role of artificial intelligence in craniofacial surgery
Ryu, J. Y., Chung, H. Y., & Choi, K. Y. (2021) · Archives of Craniofacial Surgery · doi:10.7181/acfs.2021.00507 · Cited by 29
Artificial Intelligence in Cardiac Electrophysiology: A Comprehensive Review
Cipollone, P., Pierucci, N., Matteucci, A., Palombi, M., Laviola, D., Bruti, R. M., Vinciullo, S., Bernardi, M., Spadafora, L., Cersosimo, A., et al. (2025) · Journal of Personalized Medicine · doi:10.3390/jpm15110532 · Cited by 30
“Randomized clinical trials involving AI have also been conducted [38], highlighting both the analytical capabilities of AI and its integration into controlled study designs.”
Regolisti, G., Maggiore, U., Greco, P., Maccari, C., Parenti, E., Mario, F. D., Pistolesi, V., Morabito, S., & Fiaccadori, E. (2019) · Internal and Emergency Medicine · doi:10.1007/s11739-019-02217-x · Cited by 27
Yoo, J., Yoo, I., Youn, I., Kim, S.-M., Yu, R., Kim, K., Kim, K., & Lee, S.-B. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.107079 · Cited by 29
Zhou, W., Chan, Y. E., Foo, C.-S., Zhang, J., Teo, J. X., Dávila, S., Huang, W., Yap, J. J. L., Cook, S. A., Tan, P. B. O., et al. (2022) · Journal of Medical Internet Research · doi:10.2196/34669 · Cited by 26
“First, electrocardiogram signals from wearables have been studied in relation to the development of cardiometabolic conditions, such as atrial fibrillation [12-14], hyperkalemia [15,16], and heart failure [17-19].”
High precision ECG digitization using artificial intelligence
Demolder, A., Krešňáková, V., Hojcka, M., Boža, V., Iring, A., Rafajdus, A., Rovder, S., Palus, T., Herman, M., Bauer, F., et al. (2025) · Journal of Electrocardiology · doi:10.1016/j.jelectrocard.2025.153900 · Cited by 29
Next Generation ECG: The Impact of Artificial Intelligence and Machine Learning
Adasuriya, G., & Haldar, S. (2023) · Current Cardiovascular Risk Reports · doi:10.1007/s12170-023-00723-4 · Cited by 28
Avula, V. R., Wu, K. C., & Carrick, R. T. (2023) · JACC Advances · doi:10.1016/j.jacadv.2023.100686 · Cited by 30
“The most common clinical applications of these models were identification of cardiomyopathies (14/53 [26%]), prediction of abnormal clinical, laboratory, or imaging findings (11/53 [21%]), and arrhythmia detection (9/53 [17%]).”
BackgroundDeepa, R., Sadu, V. B., C, P. G., & Sivasamy, A. (2024) · AIP Advances · doi:10.1063/5.0191990 · Cited by 30
Park, H., Kwon, O., Shim, J., Kim, D., Park, J., Kim, Y.-G., Yu, H. T., Kim, T., Uhm, J., Choi, J., et al. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01234-1 · Cited by 25
Unsupervised deep learning of electrocardiograms enables scalable human disease profiling
Friedman, S. F., Khurshid, S. S., Venn, R. A., Wang, X., Diamant, N., Achille, P. D., Weng, L.-C. C., Choi, S. H., Reeder, C., Pirruccello, J. P., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-024-01418-9 · Cited by 30
“…asso-ciatedwithECG fi ndingsbuteachindependentlysupportedbypriorstudies (e.g., type 2 diabetes 40,41 , sleep apnea 42 – 46 , chronic liver disease/cirrhosis 15,47 , and renal failure 48 ), as well as diseases with previously undescribed associations(e.g.,feverofunknownorigin,tobaccousedisorder).”
The Role of Artificial Intelligence and Machine Learning in Clinical Cardiac Electrophysiology
Ng, B., Nayyar, S., & Chauhan, V. S. (2021) · Canadian Journal of Cardiology · doi:10.1016/j.cjca.2021.07.016 · Cited by 25
García‐Escobar, A., Vera, S., y, A. J.-R., Jiménez‐Valero, S., Galeote, G., & Moreno, R. (2022) · Annals of Noninvasive Electrocardiology · doi:10.1111/anec.12998 · Cited by 23
“The application of artificial intelligence to the ECG may enable screening for rule out hyperkalemia (Galloway et al., 2019 ).”
BackgroundArtificial Intelligence in Cardiology: Applications and Obstacles
Danilov, A., & Aronow, W. S. (2023) · Current Problems in Cardiology · doi:10.1016/j.cpcardiol.2023.101750 · Cited by 28
Tang, P., Wang, Q., Ouyang, H., Yang, S., & Hua, P. (2023) · Aging · doi:10.18632/aging.204688 · Cited by 25
Kim, D. S., Jeong, J., Kim, J., Cho, Y., Park, I., Lee, S.-M., Oh, Y. T., Baek, S., Kang, D., Lee, E., et al. (2023) · Journal of Korean Medical Science · doi:10.3346/jkms.2023.38.e322 · Cited by 23
“9 Lin et al. 8 utilized a hierarchical attention network architecture (ECG12Net) and reported superior accuracy in detecting dyskalemia compared to emergency physicians and cardiologists.”
ResultChiu, I.-M., Cheng, C.-Y., Chang, P.-K., Li, C.-J., Cheng, F., & Lin, C. R. (2022) · Biosensors · doi:10.3390/bios13010023 · Cited by 24
Artificial Intelligence: A Review of Progress and Prospects in Medicine and Healthcare
Mishra, S. (2022) · Journal of Electronics Electromedical Engineering and Medical Informatics · doi:10.35882/jeeemi.v4i1.1 · Cited by 27
“, [108] develop a deep learning model to detect the condition of hyperkalemia from the ECG signatures.”
BackgroundPilia, N., Severi, S., Raimann, J. G., Genovesi, S., Dössel, O., Kotanko, P., Corsi, C., & Loewe, A. (2020) · APL Bioengineering · doi:10.1063/5.0018504 · Cited by 20
Artificial Intelligence in Pediatric Electrocardiography: A Comprehensive Review
Leone, D. M., O’Sullivan, D. M., & Jaimes, K. B. (2024) · Children · doi:10.3390/children12010025 · Cited by 24
Randomized Controlled Trials Evaluating Artificial Intelligence in Cardiovascular Care
Barzilai, D. H., Sudri, K., Goshen, G., Klang, E., Zimlichman, E., Barbash, I. M., & Cohen, M. S. (2025) · JACC Advances · doi:10.1016/j.jacadv.2025.102152 · Cited by 23
Metadata
- Authors
- Galloway, C. D., Valys, A. V., Shreibati, J. B., Treiman, D. L., Petterson, F. L., Gundotra, V. P., Albert, D. E., Attia, Z. I., Carter, R. E., Asirvatham, S. J., Ackerman, M. J., Noseworthy, P. A., Dillon, J. J., & Friedman, P. A.
- Affiliations
- AliveCor Inc, Mountain View, California
- Mayo Clinic (US)
- Corresponding author
- Friedman, Paul A.
- ORCID
- Venue
- JAMA Cardiology
- Publisher
- American Medical Association (AMA)
- Published
- 2019-05-01
- Volume
- 4
- Issue
- 5
- Pages
- 428
- ISSN
- 2380-6583 (ISSN-L)
- PMC
- PMC6537816
- OpenAlex
- W2928542791
- Cited by
- 318
- References
- 37
- Citations by year
- 2026: 23 · 2025: 45 · 2024: 53 · 2023: 53 · 2022: 54 · 2021: 45 · 2020: 34 · 2019: 10
- FWCI
- 23.27
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- JAMA Cardiology (publishedVersion)
- PubMed (publishedVersion)
- Europe PMC (PubMed Central) (submittedVersion)
- PubMed Central (submittedVersion)
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Health Sciences › Medicine › Nephrology › Potassium and Related Disorders
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- hyperkalemia, electrocardiogram, deep convolutional neural networks, chronic kidney disease, serum potassium, non-invasive screening, arrhythmia risk, model validation, sensitivity and specificity, clinical decision support, arrhythmia prevention
- MeSH terms
- Deep Learning, Aged, Aged, 80 and over, Algorithms, Arrhythmias, Cardiac, Artificial Intelligence, Electrocardiography, Female, Humans, Hyperkalemia, Male, Mass Screening, Middle Aged, Retrospective Studies, Sensitivity and Specificity, Prevalence, Neural Networks, Computer, Renal Insufficiency, Chronic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-27, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-27 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
