Blind ECG Restoration by Operational Cycle-GANs.

OBJECTIVE: ECG recordings often suffer from a set of artifacts with varying types, severities, and durations, and this makes an accurate diagnosis by machines or medical doctors difficult and unreliable. Numerous studies have proposed ECG denoising; however, they naturally fail to restore the actual ECG signal corrupted with such artifacts due to their simple and naive noise model. In this pilot study, we propose a novel approach for blind ECG restoration using cycle-consistent generative adversarial networks (Cycle-GANs) where the quality of the signal can be improved to a clinical level ECG regardless of the type and severity of the artifacts corrupting the signal. METHODS: To further boost the restoration performance, we propose 1D operational Cycle-GANs with the generative neuron model. RESULTS: The proposed approach has been evaluated extensively using one of the largest benchmark ECG datasets from the China Physiological Signal Challenge (CPSC-2020) with more than one million beats. Besides the quantitative and qualitative evaluations, a group of cardiologists performed medical evaluations to validate the quality and usability of the restored ECG, especially for an accurate arrhythmia diagnosis. SIGNIFICANCE: As a pioneer study in ECG restoration, the corrupted ECG signals can be restored to clinical level quality. CONCLUSION: By means of the proposed ECG restoration, the ECG diagnosis accuracy and performance can significantly improve.

Acute ST-Elevation Myocardial Infarction in Patient with Severe Uncontrolled Hyperthyroidism Complicated by Thyroid Storm.

Acute ST-elevation myocardial infarction is a life-threatening medical emergency that needs to be recognized early and treated properly to prevent deleterious complications, including death. A thyroid storm (TS) is a rare but severe manifestation of uncontrolled hyperthyroidism that might present with serious cardiovascular or neurological problems. We described a case of a 40-year-old male patient, known to have uncontrolled hyperthyroidism, who presented with acute onset of central chest pain, agitation, tachycardia, and pulmonary congestion. Fast atrial fibrillation with ST-segment elevation in anterior leads was detected on electrocardiogram. Thyroxin level (T4) was very high with undetectable thyroid stimulating hormone. Initially, the patient refused any type of coronary revascularization; therefore, he was admitted to the cardiology intensive care unit, and medical treatment was commenced for both TS and acute coronary syndrome. High-risk coronary angiography was done 2 h later because he had worsening persistent chest pain and started to develop signs of heart failure. It showed embolic occlusion of the distal left anterior descending artery that was treated medically with anti-coagulation. There were no complications. Chest pain and thyroid function tests settled down during his hospital stay with close cardiology and endocrinology follow-up.

COVID-19 infection localization and severity grading from chest X-ray images.

The immense spread of coronavirus disease 2019 (COVID-19) has left healthcare systems incapable to diagnose and test patients at the required rate. Given the effects of COVID-19 on pulmonary tissues, chest radiographic imaging has become a necessity for screening and monitoring the disease. Numerous studies have proposed Deep Learning approaches for the automatic diagnosis of COVID-19. Although these methods achieved outstanding performance in detection, they have used limited chest X-ray (CXR) repositories for evaluation, usually with a few hundred COVID-19 CXR images only. Thus, such data scarcity prevents reliable evaluation of Deep Learning models with the potential of overfitting. In addition, most studies showed no or limited capability in infection localization and severity grading of COVID-19 pneumonia. In this study, we address this urgent need by proposing a systematic and unified approach for lung segmentation and COVID-19 localization with infection quantification from CXR images. To accomplish this, we have constructed the largest benchmark dataset with 33,920 CXR images, including 11,956 COVID-19 samples, where the annotation of ground-truth lung segmentation masks is performed on CXRs by an elegant human-machine collaborative approach. An extensive set of experiments was performed using the state-of-the-art segmentation networks, U-Net, U-Net++, and Feature Pyramid Networks (FPN). The developed network, after an iterative process, reached a superior performance for lung region segmentation with Intersection over Union (IoU) of 96.11% and Dice Similarity Coefficient (DSC) of 97.99%. Furthermore, COVID-19 infections of various shapes and types were reliably localized with 83.05% IoU and 88.21% DSC. Finally, the proposed approach has achieved an outstanding COVID-19 detection performance with both sensitivity and specificity values above 99%.

COVID-19 infection map generation and detection from chest X-ray images.

Computer-aided diagnosis has become a necessity for accurate and immediate coronavirus disease 2019 (COVID-19) detection to aid treatment and prevent the spread of the virus. Numerous studies have proposed to use Deep Learning techniques for COVID-19 diagnosis. However, they have used very limited chest X-ray (CXR) image repositories for evaluation with a small number, a few hundreds, of COVID-19 samples. Moreover, these methods can neither localize nor grade the severity of COVID-19 infection. For this purpose, recent studies proposed to explore the activation maps of deep networks. However, they remain inaccurate for localizing the actual infestation making them unreliable for clinical use. This study proposes a novel method for the joint localization, severity grading, and detection of COVID-19 from CXR images by generating the so-called infection maps. To accomplish this, we have compiled the largest dataset with 119,316 CXR images including 2951 COVID-19 samples, where the annotation of the ground-truth segmentation masks is performed on CXRs by a novel collaborative human-machine approach. Furthermore, we publicly release the first CXR dataset with the ground-truth segmentation masks of the COVID-19 infected regions. A detailed set of experiments show that state-of-the-art segmentation networks can learn to localize COVID-19 infection with an F1-score of 83.20%, which is significantly superior to the activation maps created by the previous methods. Finally, the proposed approach achieved a COVID-19 detection performance with 94.96% sensitivity and 99.88% specificity.

Reversible hypoxic-ischemic encephalopathy post prolonged out-of-hospital cardiac arrest: A case series.

This article highlights the possibility of positive outcomes associated with prolonged CPR and anoxic brain injury contesting the idea that such patients will invariably end up in a persistent vegetative state.

Advance Warning Methodologies for COVID-19 Using Chest X-Ray Images.

Coronavirus disease 2019 (COVID-19) has rapidly become a global health concern after its first known detection in December 2019. As a result, accurate and reliable advance warning system for the early diagnosis of COVID-19 has now become a priority. The detection of COVID-19 in early stages is not a straightforward task from chest X-ray images according to expert medical doctors because the traces of the infection are visible only when the disease has progressed to a moderate or severe stage. In this study, our first aim is to evaluate the ability of recent state-of-the-art Machine Learning techniques for the early detection of COVID-19 from chest X-ray images. Both compact classifiers and deep learning approaches are considered in this study. Furthermore, we propose a recent compact classifier, Convolutional Support Estimator Network (CSEN) approach for this purpose since it is well-suited for a scarce-data classification task. Finally, this study introduces a new benchmark dataset called Early-QaTa-COV19, which consists of 1065 early-stage COVID-19 pneumonia samples (very limited or no infection signs) labeled by the medical doctors and 12544 samples for control (normal) class. A detailed set of experiments shows that the CSEN achieves the top (over 97%) sensitivity with over 95.5% specificity. Moreover, DenseNet-121 network produces the leading performance among other deep networks with 95% sensitivity and 99.74% specificity.

Left Heart Factors in Embolic Stroke of Undetermined Source in a Multiethnic Asian and North African Cohort.

Background Cardiac features diverge in Asians; however, it is not known how these differences relate to embolic stroke of unknown source (ESUS) in Southeast Asian and Eastern Mediterranean regions. Methods and Results A retrospective analysis of prospectively collected acute ischemic stroke data from 2014 to 2018 was performed. Stroke subtypes were noncardioembolic stroke (large-vessel and small-vessel disease; n=1348), cardioembolic stroke (n=532), and ESUS (n=656). Subtypes were compared by demographic, clinical, and echocardiographic factors. In multivariate logistic regression, patients with ESUS in comparison with noncardioembolic stroke were twice as likely to have left ventricular diastolic dysfunction (P=0.001), 3 times the odds of global hypokinesia (P=0.001), and >7 times the odds of left ventricular wall motion abnormalities (P=0.001). In the second model comparing ESUS with cardioembolic stroke, patients with ESUS were 3 times more likely to have left ventricular wall motion abnormalities (P=0.001) and 1.5 times more likely to have left ventricular diastolic dysfunction grade I (P=0.009), and 3 times more likely to have left ventricular diastolic dysfunction grades II and III (P=0.009), whereas age (P=0.001) and left atrial volume index (P=0.004) showed an inverse relation with ESUS. ESUS in patients ≥61 years old had higher levels of traditional risk factors such as coronary artery disease, but the coronary artery disease was not significantly different in ESUS age groups (P=0.80) despite higher left ventricular wall motion abnormalities (P=0.001). Conclusions Patients with ESUS and noncardioembolic stroke were younger than patients with cardioembolic stroke. While a third of the patients with ESUS >45 years old had coronary artery disease, it was unrecognized or underreported in the older ESUS age group (≥61 years old). In patients with ESUS from Southeast Asia and Eastern Mediterranean regions, left ventricular wall motion abnormalities and left ventricular diastolic dysfunction were related to ESUS.

Acute ST-Segment Elevation: Don't Rush me to the Catheter Laboratory- Please Wait.

We report a case of a young woman with no cardiac history who presented with out-of-hospital cardiac arrest and ST-segment elevation on the electrocardiogram. The cardiac arrest initially was suspected to be secondary to coronary artery disease. Further history was taken from a relative who said that the patient had a severe headache before the cardiac arrest. It was subsequenly found on computed tomography of the head that the patient had infratentorial subarachnoid hemorrhage and diffurse brain edema. The management of course was totally different from what was contemplated initially. This case illustrates that ST-segment elevation can be caused by other conditions besides on occlusive thrombus in the coronary arteries.

The Impact of SARS-CoV-2 on ST-Elevation Myocardial Infarction Volume, Time to Presentation, and Door-to-Balloon Time: A Report from a High-Volume Statewide Primary Percutaneous Intervention Program.

BACKGROUND: The novel severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2) outbreak has affected ST-elevation myocardial infarction (STEMI) care worldwide. Reports from China, Europa, and North America showed a significant decline in STEMI volume with a simultaneous increase in time from symptoms to hospital presentation. AIM: The aim of the study was to study the effect of the SARS-CoV-2 outbreak on primary percutaneous coronary intervention (PPCI) volume performed for STEMI, symptom onset to hospital presentation time (symptom-to-door [S2D]), and door-to-balloon time (D2B) at the main nationwide PPCI center in Qatar. METHODS: A retrospective evaluation of prospectively collected quality improvement cardiac catheterization data in Qatar was performed. PPCI volume and S2D and D2B time during the outbreak from March 9, 2020, to May 14, 2020, were compared with that of the same period from the prior year and the period immediately preceding the outbreak. RESULTS: Since the SARS-CoV-2 outbreak in Qatar, 137 PPCI procedures were performed. There was a 40% reduction in the volume of PPCI when compared with the period immediately preceding the outbreak and 16% reduction in volume when compared with that of the same period in 2019. The median S2D time was 115 min (interquartile range [IQR: 124]), which was not statistically different from that of the preceding period or the same period in 2019. D2B time during the outbreak increased by an average of 7 min when compared with that of the same period preceding the outbreak (median: 47 min [IQR: 28] during the outbreak vs. median: 40 min [IQR: 21] during the preceding period, P = 0.016). CONCLUSION: In a statewide PPCI program in Qatar, we observed a mild reduction in PPCI cases during the SARS-CoV-2 outbreak (16% when compared with the same period in 2019), with a modest increase in D2B time. PPCI can be performed effectively during the SARS-CoV-2 outbreak at very high-volume centers with the adoption of strict infection control measures. With proper training and monitoring, both target D2B and hospital staff safety can be achieved.

Embolic Pattern of Stroke Associated with Cardiac Wall Motion Abnormalities; Narrowing the Embolic Stroke of Undetermined Source Category.

BACKGROUND: There is ambiguity regarding the role of left ventricle wall motion abnormalities (LVWMAs) as a potential cardioembolic source in patients, who satisfy embolic stroke of undetermined source (ESUS) criteria. METHODS AND RESULTS: We analyzed prospectively collected data in 345 acute stroke patients, 185 (53.6%) stroke with atrial fibrillation (SwAF), and 160 (46.4%) stroke with LVWMA. LVWMA were younger (P = .003), had significantly higher frequency of stroke risk factors and lower ejection fraction (P < .001). No significant difference was found between the stroke pattern in SwAF and LVWMA except focal cortical, cortical-subcortical lesions were more frequent in LVWMA (P = .002). Mean wall motion score index (WMSI) was 1.523 (range 1.05-2.71) without any correlation between the severity of WMSI and multiple strokes (P = .976). In subgroup analyses vertical basal WMSI (P = .030) and vertical mid cavity WMSI (P = .010) was significantly related to branch arterial stroke. LVWMA 94 (65%) patients were on antiplatelet/anticoagulation compared to 47 (52.4%) with atrial fibrillation (AF), with no significant difference in stroke recurrence during 4 years follow-up (P = .15). CONCLUSIONS: Patients with LVWMA who satisfy ESUS criteria, have stroke pattern on diffusion-weighted magnetic resonance imaging and risk of stroke recurrence similar to AF-related stroke despite being on appropriate antiplatelet medications. Further studies with anticoagulation therapy may be required in this group of patients to improve the high risk of recurrent stroke.

Resistant Ventricular Arrhythmia and the Role of Overdrive Pacing in the Suppression of the Electrical Storm.

Ventricular arrhythmia storm is a state of cardiac instability characterized by multiple ventricular arrhythmias or multiple ICD therapies within a 24-hour duration. Management of this life-threatening state depends on the reversal of the cause besides either electrical or medical management of the arrhythmia. We report a case of a 54-year-old male who underwent a percutaneous coronary intervention following massive acute myocardial infarction. Afterwards, he developed frequent life-threatening ventricular arrhythmias that required multiple shocks and antiarrhythmic medications. Despite all these interventions, it was very difficult to control the electrical instability, but after overdrive ventricular pacing, the storm subsided and within a few days the case was stabilized. Overdrive pacing is an easy temporary modality to control the resistant arrhythmia following myocardial infarction.

STEMI after Dobutamine Stress Echocardiography in Hyperthyroid State.

Uncontrolled hyperthyroidism has been associated with significant changes in cardiovascular hemodynamics. We report a case of a 39-year-old male who has been recently diagnosed with severe hyperthyroidism. He was undergoing dobutamine stress echocardiography (DSE) for evaluation of symptoms suggestive of stable angina. The exam was complicated by ST-segment elevation myocardial infarction- (STEMI-) required coronary angiography that showed mild coronary artery disease.

Annular sizing using real-time three-dimensional intracardiac echocardiography-guided trans-catheter aortic valve replacement.

OBJECTIVE: Transcatheter aortic valve replacement (TAVR) has been established as an alternative therapy for patients with severe aortic stenosis who are unfit for the surgical aortic valve replacements. Pre and periprocedural imaging for the TAVR procedure is the key to procedural success. Currently transesophageal echocardiography (TOE), including real-time three-dimensional (RT-3D) imaging TOE, has been used for peri-interventional monitoring and guidance for TAVR. We describe our initial experience with real-time three-dimensional intracardiac echocardiography (RT-3DICE), imaging technology for the use in the TAVR procedure. METHODS: We used RT-3DICE using an ACUSON SC2000 2.0v (Siemens Medical Solution), and a 10F AcuNav V catheter (Siemens-Acuson, Inc, Mountain View, California, USA) in addition to preoperative multislice CT (MSCT) in total of five patients undergoing TAVR procedure. RESULTS: Aortic annulus and sinus of valsalva diameters were measured using RT-3DICE. Aortic valve measurements obtained using RT-3DICE are comparable to those obtained using MSCT with no significant difference in our patients. CONCLUSIONS: This small study of five patients shows the safe use of RT-3DICE in TAVR Procedure and may help the procedures performed under local anaesthesia without the need for TOE.

Prescription errors in the National Health Services, time to change practice.

INTRODUCTION: Medication error is a major source of iatrogenic illness. Error in prescription is the most common form of avoidable medication error. We present our study, performed at two, UK, National Health Services Hospitals. MATERIAL AND METHODS: The prescription practice of junior doctor's working on general medical and surgical wards in National Health Service District General and University Teaching Hospitals in the UK was reviewed. Practice was assessed against standard hospital prescription charts, developed in accordance with local pharmacy guidance. RESULTS: A total of 407 prescription charts were reviewed in both initial audit and re-audit one year later. In the District General Hospital, documentation of allergy, weight and capital-letter prescription was achieved in 31, 5 and 40% of charts, respectively. Forty-nine per cent of discontinued prescriptions were properly deleted and signed for. In re-audit significant improvement was noted in documentation of the patient's name 100%, gender 54%, allergy status 51% and use of generic drug name 71%. Similarly, in the University Teaching Hospital, 82, 63 and 65% compliance was achieved in documentation of age, generic drug name prescription and capital-letter prescription, respectively. Prescription practice was reassessed one year later after recommendations and changes in the prescription practice, leading to significant improvement in documentation of unit number, generic drug name prescription, insulin prescription and documentation of the patient's ward. CONCLUSION: Prescription error remains an important, modifiable form of medical error, which may be rectified by introducing multidisciplinary assessment of practice, nationwide standardised prescription charts and revision of current prescribing clinical training.

Myocardial blush and microvascular reperfusion following manual thrombectomy during percutaneous coronary intervention for ST elevation myocardial infarction: insights from the TOTAL trial.

AIMS: Thrombectomy during primary percutaneous coronary intervention (PPCI) for ST elevation myocardial infarction (STEMI) has been thought to be an effective therapy to prevent distal embolization and improve microvascular perfusion. The TOTAL trial (N = 10 732), a randomized trial of routine manual thrombectomy vs. PCI alone in STEMI, showed no difference in the primary efficacy outcome. This angiographic sub-study was performed to determine if thrombectomy improved microvascular perfusion as measured by myocardial blush grade (MBG). METHODS AND RESULTS: Of the 10 732 patients randomized, 1610 randomly selected angiograms were analysable by the angiographic core laboratory. Primary outcomes included MBG and post-PCI thrombolysis in myocardial infarction (TIMI) flow grade. Secondary outcomes included distal embolization, PPCI complications, and each component of the complications. The primary end point of final myocardial blush (221 [28%] 0/1 for thrombectomy vs. 246 {30%} 0/1 for PCI alone group, P = 0.38) and TIMI flow (712 [90%] TIMI 3 for thrombectomy vs. 733 [89.5%] TIMI 3 for PCI alone arm, P = 0.73) was similar in the two groups. Thrombectomy was associated with a significantly reduced incidence of distal embolization compared with PCI alone (56 [7.1%] vs. 87 [10.7%], P = 0.01). In multivariable analysis, distal embolization was an independent predictor of mortality (HR 3.00, 95% CI 1.19-7.58) while MBG was not (HR 2.73, 95% CI 0.94-5.3). CONCLUSIONS: Routine thrombectomy during PPCI did not result in improved MBG or post-PCI TIMI flow grade but did reduce distal embolization compared with PCI alone. Distal embolization and not blush grade is independently associated with mortality.

Benefit of endovascular stenting for aortic coarctation on systemic hypertension in adults.

BACKGROUND: Endovascular stenting is a recognised treatment strategy for aortic coarctation (CoA) in adults. We assessed systemic hypertension control and the need for antihypertensive therapy after CoA stenting in adults. METHODS: Data were collected prospectively on 54 patients (36 men; mean age: 34 ± 16 years) who underwent endovascular stenting for CoA over a 7-year period. Five patients were excluded as they did not attend follow-up appointments. Patients underwent clinical examination, including right arm systolic blood pressure (SBP) and 24-hour ambulatory blood pressure monitoring at baseline, 6-12 weeks and 9-12 months. RESULTS: There was a significant fall in mean peak-to-peak systolic gradient (PG) across the CoA after stenting (26 ± 11 mmHg vs. 5 ± 4 mmHg; P<0.01). There were successive reductions in right arm SBP and ambulatory SBP at baseline, 6-12 weeks and 9-12 months post-procedure (right arm: 155 ± 18 mmHg vs. 137 ± 17 mmHg vs. 142 ± 16 mmHg, respectively; all P-values <0.01; ambulatory: 142 ± 14 mmHg vs. 132 ± 16 mmHg vs. 131 ± 15 mmHg, respectively; all P-values <0.01). Twenty-four patients had severe CoA (PG >25 mmHg before stenting); baseline SBP was significantly higher in severe versus non-severe patients (160 mmHg vs. 148 mmHg; P=0.02). The absolute reduction in PG after stenting was significantly higher in the severe group (31 ± 7 mmHg vs. 14 ± 5 mmHg; P<0.0001), but there was no significant difference in SBP between groups at 6-12 weeks (141 mmHg vs. 135 mmHg; P=0.21) or 9-12 months (139 mmHg vs. 139 mmHg; P=0.96). CONCLUSION: Endovascular stenting of CoA results in a significant reduction in SBP at 6-12 weeks, which is sustained at 9-12 months, with similar outcomes in severe and non-severe CoA groups.

Does the CHA2DS2-Vasc score predict procedural and short-term outcomes in patients undergoing transcatheter aortic valve implantation?

BACKGROUND: Transcatheter aortic valve implantation (TAVI) is associated with periprocedural and postprocedural morbidity and mortality. Currently, there is a paucity of risk stratification models for potential TAVI candidates. We employed the CHA2DS2-Vasc score to quantify the risk of 30-day mortality and morbidity in patients undergoing TAVI. METHODS AND RESULTS: A retrospective analysis of registry data for consecutive patients undergoing TAVI at 3 tertiary centres in Northwest England between 2008 and 2013. The CHA2DS2-Vasc score and its modification-the R2CHA2DS2-Vasc score, which includes pre-existing renal impairment and pre-existing conduction abnormality (right bundle branch block/left bundle branch block, RBBB/LBBB)-were calculated for all patients. A total of 313 patients with a mean age of 80 (79.1-80.8) years underwent TAVI. The implanted devices were either the CoreValve or the Edwards-SAPIEN prosthesis. The 30-day mortality was 14.3% in those with a CHA2DS2-Vasc score ≥6, whereas it was only 6.2% in those with a score <6 (p=0.04). Using the R2-CHA2DS2-Vasc score, the difference was more pronounced with a 30-day mortality of 22.6% in those patients with an R2-CHA2DS2-Vasc score ≥7 compared to 6.0% in those with a R2-CHA2DS2-Vasc score <7 (p=0.001). In multivariable Cox regression analyses, there was a significant and independent relationship between the CHA2DS2-Vasc score (hazard ratio (HR)= 2.71, (1.01 to 7.31); p<0.05) and the modified R2CHA2DS2-Vasc score (HR=4.27 (1.51 to 12.07); p=0.006) with 30-day mortality. CONCLUSIONS: Our study demonstrates the potential use of the CHA2DS2-Vasc or the R2CHA2DS2-Vasc score to quantify the risk of mortality in patients undergoing TAVI. This could have significant implications in terms of clinical as well as patients' decision-making.

Dual Arterial Access for Stenting of Aortic Coarctation in Patients with Near-Total Descending Aortic Interruption.

Endovascular stenting is a recognized treatment strategy for the treatment of coarctation of aorta (COA) in adults. The aortic coarctation is usually crossed retrogradely from the descending aorta via the femoral approach. We report three patients who had near-total descending aortic interruption and underwent successful stenting of severe COA using a combined radial/brachial and femoral approach due to difficulty in crossing the lesion retrogradely via a femoral approach. There were no procedural complications and no adverse events during 6 months of follow-up.

Pre-closure of Large-Sized Arterial Access Sites in Adults Undergoing Transcatheter Structural Interventions.

INTRODUCTION: Patients undergoing structural heart interventions often require large-sized sheath insertion into femoral arteries and veins. Clinical outcome data on the use of suture-mediated devices for large femoral arterial access in structural heart interventions is limited. We assessed the efficacy of the Perclose™ (Abbott Vascular Devices, Santa Clara, CA, USA) suture-mediated device using the pre-closure technique in achieving hemostasis in femoral arterial access sites following large sheath insertion (≥8 Fr). METHODS: One hundred consecutive patients underwent 101 femoral artery access sites closures with the Perclose device using the pre-closure technique. Sixty-two percent of the patients were male and their mean (SD) age was 52 (±26) years. All patients received heparin. RESULTS: Mean arterial access site sheath diameter was 13 ± 2 Fr. Immediate hemostasis was achieved in 96/101 (96%) procedures (≤2 min). Two patients (2%) had access site-related complications requiring further interventions. On clinical follow up [mean (SD) follow-up of 24 (±12) months and median follow-up of 8.5 months], no complications were seen in the arterial access sites. CONCLUSION: Pre-closure of large-size femoral arterial access sheath sites using the suture-mediated Perclose device is efficacious in achieving rapid hemostasis in patients undergoing structural interventions. On 1-year follow-up, there were no arterial access site complications requiring further investigations or interventions.