Decompression Illness in Divers With or Without Patent Foramen Ovale : A Cohort Study.

BACKGROUND: In previous studies, the prevalence of patent foramen ovale (PFO) has been reported to be higher in scuba divers who experienced decompression illness (DCI) than in those who did not. OBJECTIVE: To assess the association between PFO and DCI in scuba divers. DESIGN: Prospective cohort study. SETTING: Tertiary cardiac center in South Korea. PARTICIPANTS: One hundred experienced divers from 13 diving organizations who did more than 50 dives per year. MEASUREMENTS: Participants had transesophageal echocardiography with a saline bubble test to determine the presence of a PFO and were subsequently divided into high- and low-risk groups. They were followed using a self-reported questionnaire while blinded to their PFO status. All of the reported symptoms were adjudicated in a blinded manner. The primary end point of this study was PFO-related DCI. Logistic regression analysis was done to determine the odds ratio of PFO-related DCI. RESULTS: Patent foramen ovale was seen in 68 divers (37 at high risk and 31 at low risk). Patent foramen ovale-related DCI occurred in 12 divers in the PFO group (non-PFO vs. high-risk PFO vs. low-risk PFO: 0 vs. 8.4 vs. 2.0 incidences per 10 000 person-dives; P = 0.001) during a mean follow-up of 28.7 months. Multivariable analysis showed that high-risk PFO was independently associated with an increased risk for PFO-related DCI (odds ratio, 9.34 [95% CI, 1.95 to 44.88]). LIMITATION: The sample size was insufficient to assess the association between low-risk PFO and DCI. CONCLUSION: High-risk PFO was associated with an increased risk for DCI in scuba divers. This finding indicates that divers with high-risk PFO are more susceptible to DCI than what has been previously reported and should consider either refraining from diving or adhering to a conservative diving protocol. PRIMARY FUNDING SOURCE: Sejong Medical Research Institute.

A novel repeat sequence-based PCR (rep-PCR) using specific repeat sequences of Mycobacterium intracellulare as a DNA fingerprinting.

Repetitive sequence-based PCR (rep-PCR) is a potential epidemiological technique that can provide high-throughput genotype fingerprints of heterogeneous Mycobacterium strains rapidly. Previously published rep-PCR primers, which are based on nucleotide sequences of Gram-negative bacteria may have low specificity for mycobacteria. Moreover, it was difficult to ensure the continuity of the study after the commercial rep-PCR kit was discontinued. Here, we designed a novel rep-PCR for Mycobacterium intracellulare, a major cause of nontuberculous mycobacterial pulmonary disease with frequent recurrence. We screened the 7,645 repeat sequences for 200 fragments from the genome of M. intracellulare ATCC 13950 in silico, finally generating five primers with more than 90% identity for a total of 226 loci in the genome. The five primers could make different band patterns depending on the genome of three different M. intracellulare strains using an in silico test. The novel rep-PCR with the five primers was conducted using 34 bacterial samples of 7 species containing 25 M. intracellulare clinical isolates, compared with previous published rep-PCRs. This shows distinguished patterns depending on species and blotting assay for 6 species implied the sequence specificity of the five primers. The Designed rep-PCR had a 95-98% of similarity value in the reproducibility test and showed 7 groups of fingerprints in M. intracellulare strains. Designed rep-PCR had a correlation value of 0.814 with VNTR, reference epidemiological method. This study provides a promising genotype fingerprinting method for tracing the recurrence of heterogeneous M. intracellulare.

Antigenic Determinant of Helicobacter pylori FlaA for Developing Serological Diagnostic Methods in Children.

The early diagnosis of Helicobacter pylori infection is important for gastric cancer prevention and treatment. Although endoscopic biopsy is widely used for H. pylori diagnosis, an accurate biopsy cannot be performed until a lesion becomes clear, especially in pediatric patients. Therefore, it is necessary to develop convenient and accurate methods for early diagnosis. FlaA, an essential factor for H. pylori survival, shows high antigenicity and can be used as a diagnostic marker. We attempted to identify effective antigens containing epitopes of high diagnostic value in FlaA. Full-sized FlaA was divided into several fragments and cloned, and its antigenicity was investigated using Western blotting. The FlaA fragment of 1345-1395 bp had strong immunogenicity. ELISA was performed with serum samples from children by using the 1345-1395 bp recombinant antigen fragment. IgG reactivity showed 90.0% sensitivity and 90.5% specificity, and IgM reactivity showed 100% sensitivity and specificity. The FlaA fragment of 1345-1395 bp discovered in the present study has antigenicity and is of high value as a candidate antigen for serological diagnosis. The FlaA 1345-1395 bp epitope can be used as a diagnostic marker for H. pylori infection, thereby controlling various gastric diseases such as gastric cancer and peptic ulcers caused by H. pylori.

Fetuin as a potential serum biomarker to detect subclinical shedder of bovine paratuberculosis.

Paratuberculosis (PTB) is a chronic contagious granulomatous enteritis of wild and domestic ruminants caused by Mycobacterium avium subsp. paratuberculosis (MAP). PTB causes considerable economic losses to the dairy industry through decreased milk production and premature culling. PTB-affected cattle undergo a subclinical stage without clinical signs and initiate fecal shedding of MAP into the environment. Current diagnostic tools have low sensitivity for the detection of subclinical PTB infection. Therefore, alternative diagnostic tools are required to improve the diagnostic sensitivity of subclinical PTB infection. In this study, we performed ELISA for three previously identified host biomarkers (fetuin, alpha-1-acid glycoprotein, and apolipoprotein) and analyzed their diagnostic performance with conventional PTB diagnostic methods. We observed that serum fetuin levels were significantly lowered in the subclinical shedder and clinical shedder groups than in the healthy control group, indicating its potential utility as a diagnostic biomarker for bovine PTB. Also, fetuin showed an excellent discriminatory power with an AUC = 0.949, a sensitivity of 92.6%, and a specificity of 94.4% for the detection of subclinical MAP infection. In conclusion, our results demonstrated that fetuin could be used as a diagnostic biomarker for enhancing the diagnostic sensitivity for the detection of subclinical MAP infections that are difficult to detect based on current diagnostic methods.

Quick Sequential Organ Failure Assessment Score and the Modified Early Warning Score for Predicting Clinical Deterioration in General Ward Patients Regardless of Suspected Infection.

BACKGROUND: The quick sequential organ failure assessment (qSOFA) score is suggested to use for screening patients with a high risk of clinical deterioration in the general wards, which could simply be regarded as a general early warning score. However, comparison of unselected admissions to highlight the benefits of introducing qSOFA in hospitals already using Modified Early Warning Score (MEWS) remains unclear. We sought to compare qSOFA with MEWS for predicting clinical deterioration in general ward patients regardless of suspected infection. METHODS: The predictive performance of qSOFA and MEWS for in-hospital cardiac arrest (IHCA) or unexpected intensive care unit (ICU) transfer was compared with the areas under the receiver operating characteristic curve (AUC) analysis using the databases of vital signs collected from consecutive hospitalized adult patients over 12 months in five participating hospitals in Korea. RESULTS: Of 173,057 hospitalized patients included for analysis, 668 (0.39%) experienced the composite outcome. The discrimination for the composite outcome for MEWS (AUC, 0.777; 95% confidence interval [CI], 0.770-0.781) was higher than that for qSOFA (AUC, 0.684; 95% CI, 0.676-0.686; P < 0.001). In addition, MEWS was better for prediction of IHCA (AUC, 0.792; 95% CI, 0.781-0.795 vs. AUC, 0.640; 95% CI, 0.625-0.645; P < 0.001) and unexpected ICU transfer (AUC, 0.767; 95% CI, 0.760-0.773 vs. AUC, 0.716; 95% CI, 0.707-0.718; P < 0.001) than qSOFA. Using the MEWS at a cutoff of ≥ 5 would correctly reclassify 3.7% of patients from qSOFA score ≥ 2. Most patients met MEWS ≥ 5 criteria 13 hours before the composite outcome compared with 11 hours for qSOFA score ≥ 2. CONCLUSION: MEWS is more accurate that qSOFA score for predicting IHCA or unexpected ICU transfer in patients outside the ICU. Our study suggests that qSOFA should not replace MEWS for identifying patients in the general wards at risk of poor outcome.

Artificial intelligence assessment for early detection and prediction of renal impairment using electrocardiography.

PURPOSE: Although renal failure is a major healthcare burden globally and the cornerstone for preventing its irreversible progression is an early diagnosis, an adequate and noninvasive tool to screen renal impairment (RI) reliably and economically does not exist. We developed an interpretable deep learning model (DLM) using electrocardiography (ECG) and validated its performance. METHODS: This retrospective cohort study included two hospitals. We included 115,361 patients who had at least one ECG taken with an estimated glomerular filtration rate measurement within 30 min of the index ECG. A DLM was developed using 96,549 ECGs of 55,222 patients. The internal validation included 22,949 ECGs of 22,949 patients. Furthermore, we conducted an external validation with 37,190 ECGs of 37,190 patients from another hospital. The endpoint was to detect a moderate to severe RI (estimated glomerular filtration rate < 45 ml/min/1.73m2). RESULTS: The area under the receiver operating characteristic curve (AUC) of a DLM using a 12-lead ECG for detecting RI during the internal and external validation was 0.858 (95% confidence interval 0.851-0.866) and 0.906 (0.900-0.912), respectively. In the initial evaluation of 25,536 individuals without RI patients whose DLM was defined as having a higher risk had a significantly higher chance of developing RI than those in the low-risk group (17.2% vs. 2.4%, p < 0.001). The sensitivity map indicated that the DLM focused on the QRS complex and T-wave for detecting RI. CONCLUSION: The DLM demonstrated high performance for RI detection and prediction using 12-, 6-, single-lead ECGs.

Detection and classification of arrhythmia using an explainable deep learning model.

BACKGROUND: Early detection and intervention is the cornerstone for appropriate treatment of arrhythmia and prevention of complications and mortality. Although diverse deep learning models have been developed to detect arrhythmia, they have been criticized due to their unexplainable nature. In this study, we developed an explainable deep learning model (XDM) to classify arrhythmia, and validated its performance using diverse external validation data. METHODS: In this retrospective study, the Sejong dataset comprising 86,802 electrocardiograms (ECGs) was used to develop and internally variate the XDM. The XDM based on a neural network-backed ensemble tree was developed with six feature modules that are able to explain the reasons for its decisions. The model was externally validated using data from 36,961 ECGs from four non-restricted datasets. RESULTS: During internal and external validation of the XDM, the average area under the receiver operating characteristic curves (AUCs) using a 12­lead ECG for arrhythmia classification were 0.976 and 0.966, respectively. The XDM outperformed a previous simple multi-classification deep learning model that used the same method. During internal and external validation, the AUCs of explainability were 0.925-0.991. CONCLUSION: Our XDM successfully classified arrhythmia using diverse formats of ECGs and could effectively describe the reason for the decisions. Therefore, an explainable deep learning methodology could improve accuracy compared to conventional deep learning methods, and that the transparency of XDM can be enhanced for its application in clinical practice.

A multicentre validation study of the deep learning-based early warning score for predicting in-hospital cardiac arrest in patients admitted to general wards.

BACKGROUND: The recently developed deep learning (DL)-based early warning score (DEWS) has shown potential in predicting deteriorating patients. We aimed to validate DEWS in multiple centres and compare the prediction, alarming and timeliness performance with the modified early warning score (MEWS) to identify patients at risk for in-hospital cardiac arrest (IHCA). METHOD/RESEARCH DESIGN: This retrospective cohort study included adult patients admitted to the general wards of five hospitals during a 12-month period. The occurrence of IHCA within 24 h of vital sign observation was the outcome of interest. We assessed the discrimination using the area under the receiver operating characteristic curve (AUROC). RESULTS: The study population consists of 173,368 patients (224 IHCAs). The predictive performance of DEWS was superior to that of MEWS in both the internal (AUROC: 0.860 vs. 0.754, respectively) and external (AUROC: 0.905 vs. 0.785, respectively) validation cohorts. At the same specificity, DEWS had a higher sensitivity than MEWS, and at the same sensitivity, DEWS reduced the mean alarm count by nearly half of MEWS. Additionally, DEWS was able to predict more IHCA patients in the 24-0.5 h before the outcome, and DEWS was reasonably calibrated. CONCLUSION: Our study showed that DEWS was superior to MEWS in three key aspects (IHCA predictive, alarming, and timeliness performance). This study demonstrates the potential of DEWS as an effective, efficient screening tool in rapid response systems (RRSs) to identify high-risk patients.

Beneficial Effect of Left Ventricular Remodeling after Early Change of Sacubitril/Valsartan in Patients with Nonischemic Dilated Cardiomyopathy.

Background and Objectives: Evidence for effectiveness of early change from angiotensin II receptor blockers (ARBs) or angiotensin-converting enzyme inhibitors (ACEIs) to sacubitril/valsartan is lacking. We aimed to investigate whether early changes to sacubitril/valsartan could improve outcomes in patients with nonischemic dilated cardiomyopathy (DCM) in real-world practice. Materials and Methods: A total of 296 patients with nonischemic DCM who were treated with ARB or ACEI continuously (group A, n = 150) or had their medication switched to sacubitril/valsartan (group S, n = 146) were included. The sacubitril/valsartan group was divided into early change (within 60 days, group S/E, n = 59) and late change (group S/L, n = 87) groups. Changes in echocardiographic parameters from the time of initial diagnosis to the last follow-up were analyzed. Results: Patients in group S showed greater left ventricular (LV) end-diastolic dimension (EDD) (group A vs. S, 61.7 ± 7.4 vs. 66.5 ± 8.0, p < 0.001) and lower LV ejection fraction (LVEF) (28.9 ± 8.2% vs. 23.9 ± 7.5%, p < 0.001) than those in group A at initial diagnosis. During a median follow-up of 76 months, patients in group S/E, ∆ LVEF (%) and ∆ LVESD (mm) were significantly improved compared with those in patients in group A (group A vs. S/E, ∆ LVEF, p = 0.036; ∆ LVESD, p = 0.023) or S/L (group S/E vs. S/L, ∆ LVEF, p = 0.05; ∆ LVESD, p = 0.005). Among patients whose medications were switched to sacubitril/valsartan, those with an earlier change showed a significant correlation with greater LVEF improvement (r = -0.367, p < 0.001) and LV reverse remodeling (r = 0.277, p < 0.001). Conclusions: in patients with nonischemic DCM, an early switch to sacubitril/valsartan was associated with greater improvement in LV function. Patients might benefit in terms of LV function by early switching to sacubitril/valsartan.

Artificial intelligence for detecting electrolyte imbalance using electrocardiography.

INTRODUCTION: The detection and monitoring of electrolyte imbalance is essential for appropriate management of many metabolic diseases; however, there is no tool that detects such imbalances reliably and noninvasively. In this study, we developed a deep learning model (DLM) using electrocardiography (ECG) for detecting electrolyte imbalance and validated its performance in a multicenter study. METHODS AND RESULTS: This retrospective cohort study included two hospitals: 92,140 patients who underwent a laboratory electrolyte examination and an ECG within 30 min were included in this study. A DLM was developed using 83,449 ECGs of 48,356 patients; the internal validation included 12,091 ECGs of 12,091 patients. We conducted an external validation with 31,693 ECGs of 31,693 patients from another hospital, and the result was electrolyte imbalance detection. During internal, the area under the receiving operating characteristic curve (AUC) of a DLM using a 12-lead ECG for detecting hyperkalemia, hypokalemia, hypernatremia, hyponatremia, hypercalcemia, and hypocalcemia were 0.945, 0.866, 0.944, 0.885, 0.905, and 0.901, respectively. The values during external validation of the AUC of hyperkalemia, hypokalemia, hypernatremia, hyponatremia, hypercalcemia, and hypocalcemia were 0.873, 0.857, 0.839, 0.856, 0.831, and 0.813 respectively. The DLM helped to visualize the important ECG region for detecting each electrolyte imbalance, and it showed how the P wave, QRS complex, or T wave differs in importance in detecting each electrolyte imbalance. CONCLUSION: The proposed DLM demonstrated high performance in detecting electrolyte imbalance. These results suggest that a DLM can be used for detecting and monitoring electrolyte imbalance using ECG on a daily basis.

Alpha-2-Macroglobulin as a New Promising Biomarker Improving the Diagnostic Sensitivity of Bovine Paratuberculosis.

Johne's disease (JD) is a chronic granulomatous enteritis of ruminants caused by Mycobacterium avium subsp. paratuberculosis (MAP), which induces persistent diarrhea and cachexia. JD causes huge economic losses to the dairy industry due to reduced milk production and premature culling. Infected animals excrete MAP via feces during the prolonged subclinical stage without exhibiting any clinical signs. Therefore, accurate detection of subclinical stage animals is crucial for successful eradication of JD in the herd. In the current study, we analyzed serum samples of MAP-infected and non-infected cattle to identify potential biomarker candidates. First, we identified 12 differentially expressed serum proteins in subclinical and clinical shedder groups compared to the healthy control group. Second, we conducted ELISA for three selected biomarkers (alpha-2-macroglobulin (A2M), alpha-1-beta glycoprotein, and transthyretin) and compared their diagnostic performance with that of two commercial ELISA diagnostic kits. Serum A2M levels were significantly higher in the MAP-exposed, subclinical shedder, subclinical non-shedder, and clinical shedder groups than in the healthy control group, suggesting its possible use as a diagnostic biomarker for MAP infection. Furthermore, A2M demonstrated a sensitivity of 90.4%, and a specificity of 100% while the two commercial ELISA kits demonstrated a sensitivity of 67.83 and 73.04% and a specificity of 100%, respectively. In conclusion, our results suggest that measuring A2M by ELISA can be used as a diagnostic tool to detect MAP infection, considerably improving the detection rate of subclinical shedders and MAP-exposed animals that are undetectable using current diagnostic tools.

Identification of Nontuberculous Mycobacteria in Patients with Pulmonary Diseases in Gyeongnam, Korea, Using Multiplex PCR and Multigene Sequence-Based Analysis.

BACKGROUND: Nontuberculous mycobacteria (NTM) are widely present in environments, such as soil and water, and have recently been recognized as important pathogenic bacteria. The incidence of NTM-related infections is steadily increasing. As the diagnosis and treatment of NTM infection should be distinguished from tuberculosis, and the treatment should be specific to the species of NTM acquired, accurate species identification is required. METHODS: In this study, two-step multiplex PCR (mPCR) and multigene sequence-based analysis were used to accurately identify NTM species in 320 clinical isolates from Gyeongsang National University Hospital (GNUH). In particular, major mycobacterial strains with a high isolation frequency as well as coinfections with multiple species were diagnosed through two-step mPCR. Multigene sequencing was performed to accurately identify other NTM species not detected by mPCR. Variable regions of the genes 16S rRNA, rpoB, hsp65, and 16S-23S rRNA internal transcribed spacer were included in the analysis. RESULTS: Two-step mPCR identified 234 (73.1%) cases of M. intracellulare, 26 (8.1%) cases of M. avium subsp. avium, and 13 (4.1%) cases of M. avium subsp. hominissuis infection. Additionally, 9 (2.8%) M. fortuitum, 9 (2.8%) M. massiliense, 2 (0.6%) M. abscessus, and 4 (1.2%) M. kansasii isolates were identified. Coinfection was identified in 7 (2.2%) samples. The sixteen samples not classified by two-step mPCR included 6 (1.9%) cases of M. chimaera, 4 (1.3%) M. gordonae, 1 (0.3%) M. colombiense, 1 (0.3%) M. mageritense, and 1 (0.3%) M. persicum identified by sequence analysis. CONCLUSIONS: The results of this study suggest a strategy for rapid detection and accurate identification of species using two-step mPCR and multigene sequence-based analysis. To the best of our knowledge, this study is the first to report the identification of NTM species isolated from patients in Gyeongnam/Korea.

Artificial Intelligence Algorithm for Screening Heart Failure with Reduced Ejection Fraction Using Electrocardiography.

Although heart failure with reduced ejection fraction (HFrEF) is a common clinical syndrome and can be modified by the administration of appropriate medical therapy, there is no adequate tool available to perform reliable, economical, early-stage screening. To meet this need, we developed an interpretable artificial intelligence (AI) algorithm for HFrEF screening using electrocardiography (ECG) and validated its performance. This retrospective cohort study included two hospitals. An AI algorithm based on a convolutional neural network was developed using 39,371 ECG results from 17,127 patients. The internal validation included 3,470 ECGs from 2,908 patients. Furthermore, we conducted external validation using 4,362 ECGs from 4,176 patients from another hospital to verify the applicability of the algorithm across different centers. The end-point was to detect HFrEF, defined as an ejection fraction <40%. We also visualized the regions in 12 lead ECG that affected HFrEF detection in the AI algorithm and compared this to the previously documented literature. During the internal and external validation, the areas under the curves of the AI algorithm using a 12 lead ECG for detecting HFrEF were 0.913 (95% confidence interval, 0.902-0.925) and 0.961 (0.951-0.971), respectively, and the areas under the curves of the AI algorithm using a single-lead ECG were 0.874 (0.859-0.890) and 0.929 (0.911-0.946), respectively. The deep learning-based AI algorithm performed HFrEF detection well using not only a 12 lead but also a single-lead ECG. These results suggest that HFrEF can be screened not only using a 12 lead ECG, as is typical of a conventional ECG machine, but also with a single-lead ECG performed by a wearable device employing the AI algorithm, thereby preventing irreversible disease progression and mortality.

Increased Risk of Severe Gastric Symptoms by Virulence Factors vacAs1c, alpA, babA2, and hopZ in Helicobacter pylori Infection.

Two virulence factors of Helicobacter pylori, cagA and vacA, have been known to play a role in the development of severe gastric symptoms. However, they are not always associated with peptic ulcer or gastric cancer. To predict the disease outcome more accurately, it is necessary to understand the risk of severe symptoms linked to other virulence factors. Several other virulence factors of H. pylori have also been reported to be associated with disease outcomes, although there are many controversial descriptions. H. pylori isolates from Koreans may be useful in evaluating the relevance of other virulence factors to clinical symptoms of gastric diseases because the majority of Koreans are infected by toxigenic strains of H. pylori bearing cagA and vacA. In this study, a total of 116 H. pylori strains from Korean patients with chronic gastritis, peptic ulcers, and gastric cancers were genotyped. The presence of virulence factors vacAs1c, alpA, babA2, hopZ, and the extremely strong vacuolating toxin was found to contribute significantly to the development of severe gastric symptoms. The genotype combination vacAs1c/alpA/babA2 was the most predictable determinant for the development of severe symptoms, and the presence of babA2 was found to be the most critical factor. This study provides important information on the virulence factors that contribute to the development of severe gastric symptoms and will assist in predicting clinical disease outcomes due to H. pylori infection.

Deep Learning Algorithm to Predict Need for Critical Care in Pediatric Emergency Departments.

BACKGROUND AND OBJECTIVES: Emergency department (ED) overcrowding is a national crisis in which pediatric patients are often prioritized at lower levels. Because the prediction of prognosis for pediatric patients is important but difficult, we developed and validated a deep learning algorithm to predict the need for critical care in pediatric EDs. METHODS: We conducted a retrospective observation cohort study using data from the Korean National Emergency Department Information System, which collected data in real time from 151 EDs. The study subjects were pediatric patients who visited EDs from 2014 to 2016. The data were divided by date into derivation and test data. The primary end point was critical care, and the secondary endpoint was hospitalization. We used age, sex, chief complaint, symptom onset to arrival time, arrival mode, trauma, and vital signs as predicted variables. RESULTS: The study subjects consisted of 2,937,078 pediatric patients of which 18,253 were critical care and 375,078 were hospitalizations. For critical care, the area under the receiver operating characteristics curve of the deep learning algorithm was 0.908 (95% confidence interval, 0.903-0.910). This result significantly outperformed that of the pediatric early warning score (0.812 [0.803-0.819]), conventional triage and acuity system (0.782 [0.773-0.790]), random forest (0.881 [0.874-0.890]), and logistic regression (0.851 [0.844-0.858]). For hospitalization, the deep-learning algorithm (0.782 [0.780-0.783]) significantly outperformed the other methods. CONCLUSIONS: The deep learning algorithm predicted the critical care and hospitalization of pediatric ED patients more accurately than the conventional early warning score, triage tool, and machine learning methods.

Artificial intelligence assessment for early detection of heart failure with preserved ejection fraction based on electrocardiographic features.

Aims: Although heart failure with preserved ejection fraction (HFpEF) is a rapidly emerging global health problem, an adequate tool to screen it reliably and economically does not exist. We developed an interpretable deep learning model (DLM) using electrocardiography (ECG) and validated its performance. Methods and results: This retrospective cohort study included two hospitals. 34 103 patients who underwent echocardiography and ECG within 1 week and indicated normal left ventricular systolic function were included in this study. A DLM based on an ensemble neural network was developed using 32 671 ECGs of 20 169 patients. The internal validation included 1979 ECGs of 1979 patients. Furthermore, we conducted an external validation with 11 955 ECGs of 11 955 patients from another hospital. The endpoint was to detect HFpEF. During the internal and external validation, the area under the receiver operating characteristic curves of a DLM using 12-lead ECG for detecting HFpEF were 0.866 (95% confidence interval 0.850-0.883) and 0.869 (0.860-0.877), respectively. In the 1412 individuals without HFpEF at initial echocardiography, patients whose DLM was defined as having a higher risk had a significantly higher chance of developing HFpEF than those in the low-risk group (33.6% vs. 8.4%, P < 0.001). Sensitivity map showed that the DLM focused on the QRS complex and T-wave. Conclusion: The DLM demonstrated high performance for HFpEF detection using not only a 12-lead ECG but also 6- single-lead ECG. These results suggest that HFpEF can be screened using conventional ECG devices and diverse life-type ECG machines employing the DLM, thereby preventing disease progression.

Artificial intelligence to diagnose paroxysmal supraventricular tachycardia using electrocardiography during normal sinus rhythm.

Aims: Paroxysmal supraventricular tachycardia (PSVT) is not detected owing to its paroxysmal nature, but it is associated with the risk of cardiovascular disease and worsens the patient quality of life. A deep learning model (DLM) was developed and validated to identify patients with PSVT during normal sinus rhythm in this multicentre retrospective study. Methods and results: This study included 12 955 patients with normal sinus rhythm, confirmed by a cardiologist. A DLM was developed using 31 147 electrocardiograms (ECGs) of 9069 patients from one hospital. We conducted an accuracy test with 13 753 ECGs of 3886 patients from another hospital. The DLM was developed based on residual neural network. Digitally stored ECG were used as predictor variables and the outcome of the study was ability of the DLM to identify patients with PSVT using an ECG during sinus rhythm. We employed a sensitivity map method to identify an ECG region that had a significant effect on developing PSVT. During accuracy test, the area under the receiver operating characteristic curve of a DLM using a 12-lead ECG for identifying PSVT patients during sinus rhythm was 0.966 (0.948-0.984). The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of DLM were 0.970, 0.868, 0.972, 0.255, and 0.998, respectively. The DLM showed delta wave and QT interval were important to identify the PSVT. Conclusion: The proposed DLM demonstrated a high performance in identifying PSVT during normal sinus rhythm. Thus, it can be used as a rapid, inexpensive, point-of-care means of identifying PSVT in patients.

Explainable artificial intelligence to detect atrial fibrillation using electrocardiogram.

INTRODUCTION: Early detection and intervention of atrial fibrillation (AF) is a cornerstone for effective treatment and prevention of mortality. Diverse deep learning models (DLMs) have been developed, but they could not be applied in clinical practice owing to their lack of interpretability. We developed an explainable DLM to detect AF using ECG and validated its performance using diverse formats of ECG. METHODS: We conducted a retrospective study. The Sejong ECG dataset comprising 128,399 ECGs was used to develop and internally validated the explainable DLM. DLM was developed with two feature modules, which could describe the reason for DLM decisions. DLM was external validated using data from 21,837, 10,605, and 8528 ECGs from PTB-XL, Chapman, and PhysioNet non-restricted datasets, respectively. The predictor variables were digitally stored ECGs, and the endpoints were AFs. RESULTS: During internal and external validation of the DLM, the area under the receiver operating characteristic curves (AUCs) of the DLM using a 12­lead ECG in detecting AF were 0.997-0.999. The AUCs of the DLM with VAE using a 6­lead and single­lead ECG were 0.990-0.999. The AUCs of explainability about features such as rhythm irregularity and absence of P-wave were 0.961-0.993 and 0.983-0.993, respectively. CONCLUSIONS: Our DLM successfully detected AF using diverse ECGs and described the reason for this decision. The results indicated that an explainable artificial intelligence methodology could be adopted to the DLM using ECG and enhance the transparency of the DLM for its application in clinical practice.

A deep learning algorithm to detect anaemia with ECGs: a retrospective, multicentre study.

BACKGROUND: 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. METHODS: 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. FINDINGS: 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 detected anaemia. The application of artificial intelligence to ECGs could enable screening for anaemia. FUNDING: None.

Artificial intelligence algorithm for detecting myocardial infarction using six-lead electrocardiography.

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.