Prediction of breath-holding spells based on electrocardiographic parameters using machine-learning model.

BACKGROUND: Breath-holding spells (BHS) are common in infancy and early childhood and may appear like seizures. Factors such as autonomic dysfunction and iron deficiency anemia are thought to contribute to the incidence of BHS. In this study, electrocardiographic (ECG) parameters of patients with BHS were compared to those of healthy, normal children. Logistic regression and machine-learning (ML) models were then created to predict these spells based on ECG characteristics. METHODS: In this case-control study, 52 BHS children have included as the case and 150 healthy children as the control group. ECG was taken from all children along with clinical examinations. Multivariate logistic regression model was used to predict BHS occurrence based on ECG parameters. ML model was trained and validated using the Gradient-Boosting algorithm, in the R programming language. RESULTS: In BHS and control groups, the average age was 11.90 ± 6.63 and 11.33 ± 6.17 months, respectively (p = .58). Mean heart rate, PR interval, and QRS interval on ECGs did not differ significantly between the two groups. BHS patients had significantly higher QTc, QTd, TpTe, and TpTe/QT (all p-values < .001). Evaluation of the ML model for prediction of BHS, fitting on the testing data showed AUC, specificity, and sensitivity of 0.94, 0.90, and 0.94 respectively. CONCLUSION: There are repolarization changes in patients with BHS, as the QTc, QTd, TpTe, and TpTe/QT ratio were significantly higher in these patients, which might be noticeable for future arrhythmia occurrence. In this regard, we developed a successful ML model to predict the possibility of BHS in suspected subjects.

Comparison of machine-learning models for the prediction of 1-year adverse outcomes of patients undergoing primary percutaneous coronary intervention for acute ST-elevation myocardial infarction.

BACKGROUND: Acute ST-elevation myocardial infarction (STEMI) is a leading cause of mortality and morbidity worldwide, and primary percutaneous coronary intervention (PCI) is the preferred treatment option. HYPOTHESIS: Machine learning (ML) models have the potential to predict adverse clinical outcomes in STEMI patients treated with primary PCI. However, the comparative performance of different ML models for this purpose is unclear. METHODS: This study used a retrospective registry-based design to recruit consecutive hospitalized patients diagnosed with acute STEMI and treated with primary PCI from 2011 to 2019, at Tehran Heart Center, Tehran, Iran. Four ML models, namely Gradient Boosting Machine (GBM), Distributed Random Forest (DRF), Logistic Regression (LR), and Deep Learning (DL), were used to predict major adverse cardiovascular events (MACE) during 1-year follow-up. RESULTS: A total of 4514 patients (3498 men and 1016 women) were enrolled, with MACE occurring in 610 (13.5%) subjects during follow-up. The mean age of the population was 62.1 years, and the MACE group was significantly older than the non-MACE group (66.2 vs. 61.5 years, p < .001). The learning process utilized 70% (n = 3160) of the total population, and the remaining 30% (n = 1354) served as the testing data set. DRF and GBM models demonstrated the best performance in predicting MACE, with an area under the curve of 0.92 and 0.91, respectively. CONCLUSION: ML-based models, such as DRF and GBM, can effectively identify high-risk STEMI patients for adverse events during follow-up. These models can be useful for personalized treatment strategies, ultimately improving clinical outcomes and reducing the burden of disease.

Case report: Thoracic endovascular aortic repair using a non-touch exclusion technique with a custom-made device for the treatment of a large patent ductus arteriosus.

Patent ductus arteriosus (PDA) is a common congenital heart disease affecting roughly one in every 2,000 term births. Although most of the patients are diagnosed and treated during childhood, few cases may persist into adulthood. We presented a 27-year-old male patient with a 20.2 mm diameter PDA who was referred to our hospital with progressive fatigue and exertional dyspnea. Given the potential complications, usual techniques such as coil occlusion and duct occluders were deemed inappropriate for this patient. Thoracic endovascular aortic repair (TEVAR) using a non-touch exclusion technique was successfully performed for this patient. The patient was discharged with no major post-surgical complications. TEVAR could be a new, safe, and effective alternative treatment to other transcatheter procedures for complicated PDAs in some patients.

Single-center experience with catheter-directed thrombolysis and balloon angioplasty for acute upper-extremity deep vein thrombosis: a case series study.

BACKGROUND: Effective treatment of upper extremity deep vein thrombosis (UEDVT) is crucial to prevent further complications. Various treatments, including percutaneous mechanical thrombectomy (PMT), catheter-directed thrombolysis (CDT), decompression surgery, and venoplasty are suggested for UEDVT. However, no prospective study has yet favored any of these treatments. This study presents a review of our experience with CDT followed by balloon venoplasty in patients with acute primary UEDVT. METHODS: We enrolled all patients diagnosed with acute UEDVT from January 2020 to June 2021. Subjects with UEDVT due to secondary causes like malignancies, indwelling catheters, or leads were excluded. CDT was performed through brachial vein access, using a perfusion catheter, and rt-PA administration. Balloon venoplasty was performed if the treated segment had remaining stenosis after CDT. Patients were followed up at the vein clinic for any signs and symptoms in the upper extremity and lifestyle changes. Follow-up ultrasonography was done 12 months after discharge. RESULTS: Twelve patients with a mean age of 41.08 ± 14.0 years were included in the study. The mean duration of CDT was 25.00 ± 10.56 h. After CDT, all patients had remaining occlusions, with seven having more than 50% remaining stenosis. However, after balloon venoplasty, no patient had significant (more than 50%) stenosis. There was no serious complication after both procedures. Patients were followed up for a mean duration of twelve months after their admission, with a mean time of maintenance anticoagulation was 10.73 ± 5.77 months. Only one patient had recurrent symptoms in his target limb which required a decompression surgery, while the rest were free of symptoms in their treated extremity. No subject developed pulmonary emboli (PE) during admission or the follow-up period. There was no evidence of hospital readmission for any reason. Upper extremity color-doppler sonography of the patients at twelve months after their procedure showed normal venous flow without any significant stenosis in 8 (66.7%), and partially normal flow with patent target vein in 4 (33.3%) patients. CONCLUSIONS: CDT followed by balloon venoplasty may be an effective treatment for selected patients with acute primary UEDVT, providing desirable long-term results and potentially avoiding the need for decompression surgery in the short or long term.

Left atrial function evaluation by 2D speckle-tracking echocardiography in patients with vasovagal syncope.

OBJECTIVES: Evidence indicates left atrial (LA) involvement in vasovagal syncope (VVS). The LA regulates left ventricular filling during the cardiac cycle. We aimed to assess LA function in patients with VVS by 2D speckle-tracking echocardiography. METHODS: Sixty-nine consecutive patients with VVS were recruited. Based on the head-up tilt test (HUTT) results, the study population was divided into two groups: HUTT+ (n = 45) and HUTT- (n = 24). Fifty-one consecutive subjects were enrolled as the control group. LA myocardial deformation parameters were measured by 2D speckle-tracking echocardiography to evaluate LA function. RESULTS: Maximal, minimal, and pre-P LA volumes were lower in patients with VVS. Strain and strain rate during reservoir, conduit, and contraction phases in VVS patients with HUTT+ or HUTT- were not statistically significantly different from those in the control group. Additionally, the volumetric parameters of LA function showed no difference in statistical significance between the three study groups. CONCLUSIONS: While LA phasic function was not different between the two groups of VVS patients with HUTT+ or HUTT- and the control group, LA size during the three LA phases was smaller in patients with VVS.

Prediction of in-hospital adverse clinical outcomes in patients with pulmonary thromboembolism, machine learning based models.

Background: Pulmonary thromboembolism (PE) is the third leading cause of cardiovascular events. The conventional modeling methods and severity risk scores lack multiple laboratories, paraclinical and imaging data. Data science and machine learning (ML) based prediction models may help better predict outcomes. Materials and methods: In this retrospective registry-based design, all consecutive hospitalized patients diagnosed with pulmonary thromboembolism (based on pulmonary CT angiography) from 2011 to 2019 were recruited. ML based algorithms [Gradient Boosting (GB) and Deep Learning (DL)] were applied and compared with logistic regression (LR) to predict hemodynamic instability and/or all-cause mortality. Results: A total number of 1,017 patients were finally enrolled in the study, including 465 women and 552 men. Overall incidence of study main endpoint was 9.6%, (7.2% in men and 12.4% in women; p-value = 0.05). The overall performance of the GB model is better than the other two models (AUC: 0.94 for GB vs. 0.88 and 0.90 for DL and LR models respectively). Based on GB model, lower O2 saturation and right ventricle dilation and dysfunction were among the strongest adverse event predictors. Conclusion: ML-based models have notable prediction ability in PE patients. These algorithms may help physicians to detect high-risk patients earlier and take appropriate preventive measures.

Hematuria during the right heart catheterization procedure: Renal perforation as a very rare complication.

The occurrence of hematuria during a right heart catheterization can be a sign of renal perforation, a rare but life-threatening complication that could be developed due to the misdirection of wire into the abdominopelvic venous plexus. We showed this complication could be managed with venoplasty of the common iliac vein.

Comparison of Angiographic and Clinical Outcomes After Primary Percutaneous Coronary Intervention for ST-elevation Myocardial Infarction Between Patients With and Without Concomitant COVID-19 Infection.

OBJECTIVE: COVID-19 infection can involve the cardiovascular system and worsen the prognosis of the patients. This study aimed to investigate the adverse effects of COVID-19 on angiographic and clinical outcomes of primary percutaneous coronary intervention (PCI) in patients with acute ST-elevation MI and compare results with those patients without COVID-19 disease. METHODS: The study was a retrospective observational cohort, in which patients presented with ST-elevation MI from February 2020 to April 2021, treated with primary PCI were divided into 2 groups based on the COVID-19 infection. Then, the procedural and angiographic indices and also clinical outcomes were compared between the 2 groups. RESULTS: A total of 1150 patients were enrolled in the study. Those with established COVID-19 infection had worse baseline thrombolysis in myocardial infarction flow grade and also were at higher risk for worse procedural outcomes such as lower thrombolysis in myocardial infarction frame count, myocardial blush grade, and slow-flow coronary disease, after the primary PCI. Additionally, the presence of COVID-19 at the time of primary PCI was related to a significantly higher duration of hospitalization and in-hospital mortality. Given the potential impact of other factors on outcomes, analysis for all of the primary endpoints was done again after adjustment of these factors and the results were the same as before, suggesting the independent effect of COVID-19 infection. CONCLUSIONS: The concomitant COVID-19 infection in the patients undergoing primary PCI is associated with significantly worse angiographic, procedural and clinical outcomes. Surprisingly, this finding is regardless of patients' baseline risk factors and demographical characteristics.

Nightmare after iliac vein stenting: Spinal epidural hematoma.

Spinal epidural hematoma is a rare but devastating complication of iliac vein stenting. Radicular back pain during and after procedure is an alarming sign for this complication.

Atomoxetine as an adjunct to nonpharmacological treatments for preventing vasovagal attacks in patients with recurrent vasovagal syncope: A pilot randomized-controlled trial.

BACKGROUND: Despite the reduced quality of life in patients with recurrent vasovagal syncope (VVS), pharmacologic treatment options remain limited. Studies indicate that norepinephrine reuptake inhibition reduces tilt-induced syncope/pre-syncope. This study aimed to evaluate the effects of atomoxetine on syncopal/pre-syncopal episodes in patients with recurrent VVS. METHODS: In a placebo-controlled trial, we randomized patients with newly diagnosed VVS who experienced ≥3 syncopal episodes in the past three months to receive either atomoxetine (20 mg daily for two weeks followed by 40 mg daily for two weeks) or placebo. The primary endpoint was the combined number of syncopal and pre-syncopal episodes. RESULTS: Among 843 patients initially screened, 46 were randomized (N = 23 in each group) and reevaluated at one and three months. Compared to placebo, atomoxetine significantly reduced the primary endpoint after three months (P < 0.001). In the atomoxetine arm, the median time to first pre-syncopal episode was 55 days (95% confidence interval (CI): 41.21-68.79), while this was 27 days (95% CI: 14.48-39.52) for the placebo group (P < 0.001). In a subgroup analysis of patients with systolic blood pressure < 110 mmHg, atomoxetine reduced the primary endpoint, and the number of syncopal and pre-syncopal episodes after one and three months. In this subgroup, the median time to first pre-syncopal attack was 56 days in the atomoxetine group as opposed to 9 days in the placebo group. CONCLUSIONS: In this pilot study, the promising effects of atomoxetine in reducing syncopal/pre-syncopal episodes in recurrent VVS, especially with low blood pressure phenotype, warrant the conduction of future randomized trials.

Comparison of Grafting Success Rate and Hearing Outcomes between Primary and Revision Tympanoplasties.

INTRODUCTION: There are a few studies that compare the outcomes between primary and revision tympanoplasties. The purpose of the present study was to compare the results of type I tympanoplasty (i.e., synonymous to myringoplasty) and revision myringoplasty based on the closure of tympanic membrane perforation and hearing improvement. MATERIALS AND METHODS: This prospective single-blind study was carried out on a total of 240 patients with tympanic membrane perforation at a tertiary referral center. The subjects underwent primary or revision myringoplasty. Grafting success rate and hearing results were measured and the comparison between the primary and revision groups was drawn. RESULTS: Grafting success rate was reported as 96.6% (112 out of 116 cases) for myringoplasty, while in revision myringoplasty the success rate of 78.2% (97 out of 124 patients) was achieved (P=0.001). Speech reception threshold was 23.1±9.2 dB and 24.9±13.1 dB in the primary and revision groups, respectively (P>0.05). However, the percentage of air-bone gap on audiometry≤20 dB were 83.8% and 76% in the primary and revision groups, respectively (P=0.26). CONCLUSION: The findings of the present study have shown that although grafting success was reported significantly better in myringoplasty (tympanoplasty type 1), compared to that in revision myringoplasty, it did not reveal any superiority over revision tympanoplasty regarding the hearing outcomes. No consensus was achieved due to a great number of controversies in the literature.