Severe, symptomatic aortic stenosis (AS) is associated with poor prognoses. However, early detection of AS is difficult because of the long asymptomatic period experienced by many patients, during which screening tools are ineffective. The aim of this study was to develop and validate a deep learning-based algorithm, combining a multilayer perceptron and convolutional neural network, for detecting significant AS using ECGs. This retrospective cohort study included adult patients who had undergone both ECG and echocardiography. A deep learning-based algorithm was developed using 39 371 ECGs. Internal validation of the algorithm was performed with 6453 ECGs from one hospital, and external validation was performed with 10 865 ECGs from another hospital. The end point was significant AS (beyond moderate). We used demographic information, features, and 500-Hz, 12-lead ECG raw data as predictive variables. In addition, we identified which region had the most significant effect on the decision-making of the algorithm using a sensitivity map. During internal and external validation, the areas under the receiver operating characteristic curve of the deep learning-based algorithm using 12-lead ECG for detecting significant AS were 0.884 (95% CI, 0.880-0.887) and 0.861 (95% CI, 0.858-0.863), respectively; those using a single-lead ECG signal were 0.845 (95% CI, 0.841-0.848) and 0.821 (95% CI, 0.816-0.825), respectively. The sensitivity map showed the algorithm focused on the T wave of the precordial lead to determine the presence of significant AS. The deep learning-based algorithm demonstrated high accuracy for significant AS detection using both 12-lead and single-lead ECGs.

Screening and early diagnosis of pulmonary hypertension (PH) are critical for managing progression and preventing associated mortality; however, there are no tools for this purpose. We developed and validated an artificial intelligence (AI) algorithm for predicting PH using electrocardiography (ECG). This historical cohort study included data from consecutive patients from 2 hospitals. The patients in one hospital were divided into derivation (56,670 ECGs from 24,202 patients) and internal validation (3,174 ECGs from 3,174 patients) datasets, whereas the patients in the other hospital were included in only an external validation (10,865 ECGs from 10,865 patients) dataset. An AI algorithm based on an ensemble neural network was developed using 12-lead ECG signal and demographic information from the derivation dataset. The end-point was the diagnosis of PH. In addition, the interpretable AI algorithm identified which region had the most significant effect on decision making using a sensitivity map. During the internal and external validation, the area under the receiver operating characteristic curve of the AI algorithm for detecting PH was 0.859 and 0.902, respectively. In the 2,939 individuals without PH at initial echocardiography, those patients that the AI defined as having a higher risk had a significantly higher chance of developing PH than those in the low-risk group (31.5% vs 5.9%, p < 0.001) during the follow-up period. The sensitivity map showed that the AI algorithm focused on the S-wave, P-wave, and T-wave for each patient by QRS complex characteristics. The AI algorithm demonstrated high accuracy for PH prediction using 12-lead and single-lead ECGs.

Anaemia is an important health-care burden globally, and screening for anaemia is crucial to prevent multi-organ injury, irreversible complications, and life-threatening adverse events. We aimed to establish whether a deep learning algorithm (DLA) that enables non-invasive anaemia screening from electrocardiograms (ECGs) might improve the detection of anaemia. We did a retrospective, multicentre, diagnostic study in which a DLA was developed using ECGs and then internally and externally validated. We used data from two hospitals, Sejong General Hospital (hospital A) and Mediplex Sejong Hospital (hospital B), in South Korea. Data from hospital A was for DLA development and internal validation, and data from hospital B was for external validation. We included individuals who had at least one ECG with a haemoglobin measurement within 1 h of the index ECG and excluded individuals with missing demographic, electrocardiographic, or haemoglobin information. Three types of DLA were developed with 12-lead, 6-lead (limb lead), and single-lead (lead I) ECGs to detect haemoglobin concentrations of 10 g/dL or less. The DLA was built by a convolutional neural network and used 500-Hz raw ECG, age, and sex as input data. The study period ran from Oct 1, 2016, to Sept 30, 2019, in hospital A and March 1, 2017, to Sept 30, 2019, in hospital B. 40 513 patients at hospital A and 4737 patients at hospital B were eligible for inclusion. We excluded 281 patients at hospital A and 72 patients at hospital B because of missing values for clinical information and ECG data. The development dataset comprised 57 435 ECGs from 31 898 patients, and the algorithm was internally validated with 7974 ECGs from 7974 patients. The external validation dataset included 4665 ECGs from 4665 patients. 586 (internal) and 194 (external) patients within the combined dataset were found to be anaemic. During internal and external validation, the area under the receiver operating characteristics curve (AUROC) of the DLA using a 12-lead ECG for detecting anaemia was 0·923 for internal validation and 0·901 for external validation. Using a 90% sensitivity operating point for the development data, the sensitivity, specificity, negative predictive value, and positive predictive value of internal validation were 89·8%, 81·5%, 99·4%, and 20·0%, respectively, and those of external validation were 86·1%, 76·2%, 99·2%, and 13·5%, respectively. The DLA focused on the QRS complex for deciding the presence of anaemia in a sensitivity map. The AUROCs of DLAs using 6 leads and a single lead were in the range of 0·841–0·890. Interpretation In this study, using raw ECG data, a DLA accurately

In-hospital cardiac arrest is a major burden in health care. Although several track-and-trigger systems are used to predict cardiac arrest, they often have unsatisfactory performances. We hypothesized that a deeplearning-based artificial intelligence algorithm (DLA) could effectively predict cardiac arrest using electrocardiography (ECG). We developed and validated a DLA for predicting cardiac arrest using ECG. We conducted a retrospective study that included 47,505 ECGs of 25,672 adult patients admitted to two hospitals, who underwent at least one ECG from October 2016 to September 2019. The endpoint was occurrence of cardiac arrest within 24 h from ECG. Using subgroup analyses in patients who were initially classified as non-event, we confirmed the delayed occurrence of cardiac arrest and unexpected intensive care unit transfer over 14 days. We used 32,294 ECGs of 10,461 patients and 4483 ECGs of 4483 patients from a hospital were used as development and internal validation data, respectively. Additionally, 10,728 ECGs of 10,728 patients from another hospital were used as external validation data, which confirmed the robustness of the developed DLA. During internal and external validation, the areas under the receiver operating characteristic curves of the DLA in predicting cardiac arrest within 24 h were 0.913 and 0.948, respectively. The high risk group of the DLA showed a significantly higher hazard for delayed cardiac arrest (5.74% vs. 0.33%, P < 0.001) and unexpected intensive care unit transfer (4.23% vs. 0.82%, P < 0.001). A sensitivity map of the DLA displayed the ECG regions used to predict cardiac arrest, with the DLA focused most on the QRS complex. Our DLA successfully predicted cardiac arrest using diverse formats of ECG. The results indicate that cardiac arrest could be screened and predicted not only with a conventional 12-lead ECG, but also with a single-lead ECG using a wearable device that employs our DLA.

Rapid diagnosis of myocardial infarction (MI) using electrocardiography (ECG) is the cornerstone of effective treatment and prevention of mortality; however, conventional interpretation methods has low reliability for detecting MI and is difficulty to apply to limb 6-lead ECG based life type or wearable devices. We developed and validated a deep learning-based artificial intelligence algorithm (DLA) for detecting MI using 6-lead ECG. A total of 412,461 ECGs were used to develop a variational autoencoder (VAE) that reconstructed precordial 6-lead ECG using limb 6-lead ECG. Data from 9536, 1301, and 1768 ECGs of adult patients who underwent coronary angiography within 24 h from each ECG were used for development, internal and external validation, respectively. During internal and external validation, the area under the receiver operating characteristic curves of the DLA with VAE using a 6-lead ECG were 0.880 and 0.854, respectively, and the performances were preserved by the territory of the coronary lesion. Our DLA successfully detected MI using a 12-lead ECG or a 6-lead ECG. The results indicate that MI could be detected not only with a conventional 12 lead ECG but also with a life type 6-lead ECG device that employs our DLA.

Heart disease (HD) is the leading cause of global death; there are several mortality prediction models of HD for identifying critically-ill patients and for guiding decision making. The existing models, however, cannot be used during initial treatment or screening. This study aimed to derive and validate an echocardiography-based mortality prediction model for HD using deep learning (DL). In this multicenter retrospective cohort study, the subjects were admitted adult (age ≥ 18 years) HD patients who underwent echocardiography. The outcome was in-hospital mortality. We extracted predictor variables from echocardiography reports using text mining. We developed deep learning-based prediction model using derivation data of a hospital A. And we conducted external validation using echocardiography report of hospital B. We conducted subgroup analysis of coronary heart disease (CHD) and heart failure (HF) patients of hospital B and compared DL with the currently used predictive models (eg, Global Registry of Acute Coronary Events (GRACE) score, Thrombolysis in Myocardial Infarction score (TIMI), Meta-Analysis Global Group in Chronic Heart Failure (MAGGIC) score, and Get With The Guidelines-Heart Failure (GWTG-HF) score). The study subjects comprised 25 776 patients with 1026 mortalities. The areas under the receiver operating characteristic curve (AUROC) of the DL model were 0.912, 0.898, 0.958, and 0.913 for internal validation, external validation, CHD, and HF, respectively, and these results significantly outperformed other comparison models. This echocardiography-based deep learning model predicted in-hospital mortality among HD patients more accurately than existing prediction models and other machine learning models.

Out-of-hospital cardiac arrest (OHCA) is a major healthcare burden, and prognosis is critical in decision-making for treatment and the withdrawal of life-sustaining therapy. This study aimed to develop and validate a deep-learning-based out-of-hospital cardiac arrest prognostic system (DCAPS) for predicting neurologic recovery and survival to discharge. The study subjects were patients from the Korea OHCA registry who experienced return of spontaneous circulation (ROSC) after OHCA. A total of 36,190 patients were exclusively divided into a set of 28,045 subjects for derivation data and 8,145 subjects for validation data. We used information available for the time of ROSC as predictor variables, and the endpoints were neurologic recovery (cerebral performance category 1 or 2) and survival to discharge. The DCAPS was developed using the derivation data and represented the favorability of prognosis with a score between 0 and 100. The area under the receiver operating characteristic curve (AUROC) of DCAPS for predicting neurologic recovery for the validation data was 0.953 [95% confidence interval 0.952-0.954]; these results significantly outperformed those of logistic regression (0.947 [0.943-0.948]), random forest (0.943 [0.942-0.945]), support vector machine (0.930 [0.929-0.932]), and conventional methods of a previous study (0.817 [0.815-0.820]). The AUROC of the DCAPS for survival to discharge was 0.901 [0.900-0.903], and this result significantly outperformed those of other models as well. The DCAPS predicted neurologic recovery and survival to discharge of OHCA patients accurately and outperformed the conventional method and other machine-learning methods.

Screening and early diagnosis for heart failure (HF) are critical. However, conventional screening diagnostic methods have limitations, and electrocardiography (ECG)-based HF identification may be helpful. This study aimed to develop and validate a deep-learning algorithm for ECG-based HF identification (DEHF). The study involved 2 hospitals and 55,163 ECGs of 22,765 patients who performed echocardiography within 4 weeks were study subjects. ECGs were divided into derivation and validation data. Demographic and ECG features were used as predictive variables. The primary endpoint was detection of HF with reduced ejection fraction (HFrEF; ejection fraction [EF]≤40%), and the secondary endpoint was HF with mid-range to reduced EF (≤50%). We developed the DEHF using derivation data and the algorithm representing the risk of HF between 0 and 1. We confirmed accuracy and compared logistic regression (LR) and random forest (RF) analyses using validation data. The area under the receiver operating characteristic curves (AUROCs) of DEHF for identification of HFrEF were 0.843 (95% confidence interval, 0.840–0.845) and 0.889 (0.887–0.891) for internal and external validation, respectively, and these results significantly outperformed those of LR (0.800 [0.797–0.803], 0.847 [0.844–0.850]) and RF (0.807 [0.804–0.810], 0.853 [0.850–0.855]) analyses. The AUROCs of deep learning for identification of the secondary endpoint was 0.821 (0.819–0.823) and 0.850 (0.848–0.852) for internal and external validation, respectively, and these results significantly outperformed those of LR and RF. The deep-learning algorithm accurately identified HF using ECG features and outperformed other machine-learning methods.

This study aimed to develop and validate deep-learning-based artificial intelligence algorithm for predicting mortality of AHF (DAHF). 12,654 dataset from 2165 patients with AHF in two hospitals were used as train data for DAHF development, and 4759 dataset from 4759 patients with AHF in 10 hospitals enrolled to the Korean AHF registry were used as performance test data. The endpoints were in-hospital, 12-month, and 36-month mortality. We compared the DAHF performance with the Get with the Guidelines–Heart Failure (GWTG-HF) score, Meta-Analysis Global Group in Chronic Heart Failure (MAGGIC) score, and other machine-learning models by using the test data. Area under the receiver operating characteristic curve of the DAHF were 0.880 (95% confidence interval, 0.876–0.884) for predicting in-hospital mortality; these results significantly outperformed those of the GWTG-HF (0.728 [0.720–0.737]) and other machine-learning models. For predicting 12- and 36-month endpoints, DAHF (0.782 and 0.813) significantly outperformed MAGGIC score (0.718 and 0.729). During the 36-month follow-up, the high-risk group, defined by the DAHF, had a significantly higher mortality rate than the low-risk group(p<0.001). DAHF predicted the in-hospital and long-term mortality of patients with AHF more accurately than the existing risk scores and other machine-learning models.

Conventional risk stratification models for mortality of acute myocardial infarction (AMI) have potential limitations. This study aimed to develop and validate deep-learning-based risk stratification for the mortality of patients with AMI (DAMI). The data of 22,875 AMI patients from the Korean working group of the myocardial infarction (KorMI) registry were exclusively divided into 12,152 derivation data of 36 hospitals and 10,723 validation data of 23 hospitals. The predictor variables were the initial demographic and laboratory data. The endpoints were in-hospital mortality and 12-months mortality. We compared the DAMI performance with the global registry of acute coronary event (GRACE) score, acute coronary treatment and intervention outcomes network (ACTION) score, and the thrombolysis in myocardial infarction (TIMI) score using the validation data. In-hospital mortality for the study subjects was 4.4% and 6-month mortality after survival upon discharge was 2.2%. The areas under the receiver operating characteristic curves (AUCs) of the DAMI were 0.905 [95% confidence interval 0.902–0.909] and 0.870 [0.865–0.876] for the ST elevation myocardial infarction (STEMI) and non ST elevation myocardial infarction (NSTEMI) patients, respectively; these results significantly outperformed those of the GRACE (0.851 [0.846–0.856], 0.810 [0.803–0.819]), ACTION (0.852 [0.847–0.857], 0.806 [0.799–0.814] and TIMI score (0.781 [0.775–0.787], 0.593[0.585–0.603]). DAMI predicted 30.9% of patients more accurately than the GRACE score. As secondary outcome, during the 6-month follow-up, the high risk group, defined by the DAMI, has a significantly higher mortality rate than the low risk group (17.1% vs. 0.5%, p < 0.001). The DAMI predicted in-hospital mortality and 12-month mortality of AMI patients more accurately than the existing risk scores and other machine-learning methods.