Challenges and solutions of echocardiography generalization for deep learning: a study in patients with constrictive pericarditis.

Purpose: The inherent characteristics of transthoracic echocardiography (TTE) images such as low signal-to-noise ratio and acquisition variations can limit the direct use of TTE images in the development and generalization of deep learning models. As such, we propose an innovative automated framework to address the common challenges in the process of echocardiography deep learning model generalization on the challenging task of constrictive pericarditis (CP) and cardiac amyloidosis (CA) differentiation. Approach: Patients with a confirmed diagnosis of CP or CA and normal cases from Mayo Clinic Rochester and Arizona were identified to extract baseline demographics and the apical 4 chamber view from TTE studies. We proposed an innovative preprocessing and image generalization framework to process the images for training the ResNet50, ResNeXt101, and EfficientNetB2 models. Ablation studies were conducted to justify the effect of each proposed processing step in the final classification performance. Results: The models were initially trained and validated on 720 unique TTE studies from Mayo Rochester and further validated on 225 studies from Mayo Arizona. With our proposed generalization framework, EfficientNetB2 generalized the best with an average area under the curve (AUC) of 0.96 (±0.01) and 0.83 (±0.03) on the Rochester and Arizona test sets, respectively. Conclusions: Leveraging the proposed generalization techniques, we successfully developed an echocardiography-based deep learning model that can accurately differentiate CP from CA and normal cases and applied the model to images from two sites. The proposed framework can be further extended for the development of echocardiography-based deep learning models.

Using Artificial Intelligence in Predicting Ischemic Stroke Events After Percutaneous Coronary Intervention.

BACKGROUND: Ischemic stroke (IS) is an uncommon but severe complication in patients undergoing percutaneous coronary intervention (PCI). Despite significant morbidity and economic cost associated with post PCI IS, a validated risk prediction model is not currently available. AIMS: We aim to develop a machine learning model that predicts IS after PCI. METHODS: We analyzed data from Mayo Clinic CathPCI registry from 2003 to 2018. Baseline clinical and demographic data, electrocardiography (ECG), intra/post-procedural data, and echocardiographic variables were abstracted. A random forest (RF) machine learning model and a logistic regression (LR) model were developed. The receiver operator characteristic (ROC) analysis was used to assess model performance in predicting IS at 6-month, 1-, 2-, and 5-years post-PCI. RESULTS: A total of 17,356 patients were included in the final analysis. The mean age of this cohort was 66.9 ± 12.5 years, and 70.7% were male. Post-PCI IS was noted in 109 patients (.6%) at 6 months, 132 patients (.8%) at 1 year, 175 patients (1%) at 2 years, and 264 patients (1.5%) at 5 years. The area under the curve of the RF model was superior to the LR model in predicting ischemic stroke at 6 months, 1-, 2-, and 5-years. Periprocedural stroke was the strongest predictor of IS post discharge. CONCLUSIONS: The RF model accurately predicts short- and long-term risk of IS and outperforms logistic regression analysis in patients undergoing PCI. Patients with periprocedural stroke may benefit from aggressive management to reduce the future risk of IS.

The impact of moderate aortic stenosis in acute myocardial infarction: A multicenter retrospective study.

BACKGROUND: Aortic stenosis (AS) is associated with myocardial ischemia through different mechanisms and may impair coronary arterial flow. However, data on the impact of moderate AS in patients with acute myocardial infarction (MI) is limited. AIMS: This study aimed to investigate the impact of moderate AS in patients presenting with acute myocardial infarction (MI). METHODS: We conducted a retrospective analysis of all patients who presented with acute MI to all Mayo Clinic hospitals, using the Enterprise Mayo PCI Database from 2005 to 2016. Patients were stratified into two groups: moderate AS and mild/no AS. The primary outcome was all cause mortality. RESULTS: The moderate AS group included 183 (13.3%) patients, and the mild/no AS group included 1190 (86.7%) patients. During hospitalization, there was no difference between both groups in mortality. Patients with moderate AS had higher in-hospital congestive heart failure (CHF) (8.2% vs. 4.4%, p = 0.025) compared with mild/no AS patients. At 1-year follow-up, patients with moderate AS had higher mortality (23.9% vs. 8.1%, p < 0.001) and higher CHF hospitalization (8.3% vs. 3.7%, p = 0.028). In multivariate analysis, moderate AS was associated with higher mortality at 1-year (odds ratio 2.4, 95% confidence interval [1.4-4.1], p = 0.002). In subgroup analyses, moderate AS increased all-cause mortality in STEMI and NSTEMI patients. CONCLUSION: The presence of moderate AS in acute MI patients was associated with worse clinical outcomes during hospitalization and at 1-year follow-up. These unfavorable outcomes highlight the need for a close follow-up of these patients and for timely therapeutic strategies to best manage these coexisting conditions.

Endophytic Bacillus subtilis SR22 Triggers Defense Responses in Tomato against Rhizoctonia Root Rot.

Rhizoctonia root rot is one of the most destructive diseases of tomato and other crops. The biocontrol of plant diseases using endophytic bacteria has gained significant attention due to their distinct advantages compared with the free-living ones, as well as their new unexplored and unique properties. Endophytic Bacillus subtilis SR22 represents a promising and more effective biocontrol and growth-promoting agent for tomato plants than the free-living agents, being an ecofriendly and sustainable tool in modern agriculture. In this study, the direct antagonistic activity of B. subtilis SR22 was investigated against Rhizoctonia solani in vitro. The biocontrol activity of B. subtilis SR22 against Rhizoctonia root rot of tomato was also investigated. Effects on the level of the transcriptional expression of defense-related genes, biochemical responses, and the vegetative growth of tomato plants were also studied. The dual culture test showed 51% inhibition in the mycelial growth of R. solani due to B. subtilis SR22, indicating its potent antagonistic behavior. Using a GC-MS analysis, twenty bioactive compounds were detected to be produced by B. subtilis SR22, including chlorogenic acid, pyrrolo [1,2-a]pyrazine-1,4-dione, hexahydro, propyl thioglycolic acid, phthalic acid, and 2,3-butanediol. Under greenhouse conditions, the application of B. subtilis SR22 led to a reduction (up to 51%) in Rhizoctonia root rot of tomato. Furthermore, an upregulation in the expression of the responsive factor JERF3 (10.9-fold) and the defense-related genes POD (9.1-fold) and PR1 (4.5-fold) in tomato plants was recorded due to the application of B. subtilis SR22. In addition, this treatment enhanced the total phenolic content (76.8%) and activity of the antioxidant enzymes POD (56%) and PPO (29.2%) in tomato roots, indicating its resistance-inducing effect on tomato plants. Moreover, this treatment enhanced most of the evaluated growth parameters in tomato plants (up to 35%). We can conclude that B. subtilis SR22 is a promising biocontrol agent and growth promoter in tomato plants against Rhizoctonia root rot. An evaluation of the formulation and field application of this bio-agent is necessary in future studies.

Effects of Mycorrhizal Colonization on Transcriptional Expression of the Responsive Factor JERF3 and Stress-Responsive Genes in Banana Plantlets in Response to Combined Biotic and Abiotic Stresses.

Banana plants (Musa acuminata L.) are exposed to various biotic and abiotic stresses that affect their production worldwide. Banana plants respond to these stresses, but their responses to combined stresses are unique and differ from those to various individual stresses. This study reported the effects of the mycorrhizal colonization of banana roots and/or infection with root rot on the transcriptional expression of the responsive factor JERF3 and stress-responsive genes (POD, PR1, CHI, and GLU) under different salinity levels. Different transcriptional levels were recorded in response to the individual, dual, or triple treatments. All the applied biotic and abiotic stresses triggered the transcriptional expression of the tested genes when individually applied, but they showed different influences varying from synergistic to antagonistic when applied in combinations. The salinity stress had the strongest effect when applied in combination with the biotic stress and/or mycorrhizal colonization, especially at high concentrations. Moreover, the salinity level differentially affects the banana responses under combined stresses and/or mycorrhizal colonization in addition, the mycorrhizal colonization of banana plantlets improved their growth, photosynthesis, and nutrient uptake, as well as greatly alleviated the detrimental effects of salt and infection stresses. In general, the obtained results indicated that the responses of banana plantlets under the combined stresses are more complicated and differed from those under the individual stresses depending on the crosstalks between the signaling pathways.

Clinical significance of SNP (rs2596542) in histocompatibility complex class I-related gene A promoter region among hepatitis C virus related hepatocellular carcinoma cases.

The major histocompatibility complex class I-related gene A (MICA) is an antigen induced by stress and performs an integral role in immune responses as an anti-infectious and antitumor agent. This work was designed to investigate whether (SNP) rs2596542C/T in MICA promoter region is predictive of liver cirrhosis (LC) and hepatocellular carcinoma (HCC) or not. Forty-seven healthy controls and 94 HCV-infected patients, subdivided into 47 LC and 47 HCC subjects were enrolled in this study. SNP association was studied using real time PCR and soluble serum MICA concentration was measured using ELISA. Results showed that heterozygous genotype rs2596542CT was significantly (P = 0.022) distributed between HCC and LC related CHC patients. The sMICA was significantly higher (P = 0.0001) among HCC and LC. No significant association (P = 0.56) between rs2596542CT genotypes and sMICA levels was observed. Studying SNP rs2596542C/T association with HCC and LC susceptibility revealed that statistical significant differences (P = 0.013, P = 0.027) were only observed between SNP rs2596542C/T and each of HCC and LC, respectively, versus healthy controls, indicating that the rs2596542C/T genetic variation is not a significant contributor to HCC development in LC patients. Moreover, the T allele was considered a risk factor for HCC and LC vulnerability in HCV patients (OR = 1.93 and 2.1, respectively), while the C allele contributes to decreasing HCC risk. Therefore, SNP (rs2596542C/T) in MICA promoter region and sMICA levels might be potential useful markers in the assessment of liver disease progression to LC and HCC.

Flank-free Modified Supine Percutaneous Nephrolithotomy in Pediatric Age Group.

OBJECTIVE: To evaluate the safety and efficacy of pediatric percutaneous nephrolithotomy (PCNL) in the flank-free modified supine position (FFMSP). PCNL in the supine position is increasingly and successfully used in pediatric age group. Different modifications of supine positions have been described; however, the best supine position is not well established and remains a matter of debate. PATIENTS AND METHODS: This prospective study included 22 children presenting with single renal pelvis stone (2-3 cm) in the period between May 2012 and April 2014. Diagnosis was set by plain x-ray and computed tomography in all patients. PCNL was performed with the patients placed in the FFMSP. The operative time and hospital stay were estimated. The outcome and any perioperative complications or conflicts were recorded. RESULTS: The study included 22 children (15 boys and 7 girls) with a solitary renal pelvis stone. Mean ± standard deviation age of the patients was 9.5 ± 3.2 years (range, 3-15.5 years). Stone length, operative time, and hospital stay had mean ± standard deviation of 2.4 ± 0.23 cm, 65.1 ± 18.7 minutes, and 4.4 ± 0.9 days. Stone-free rate was 90.9% after 1 session of PCNL. One patient (4.5%) needed a second-look PCNL. Shock wave lithotripsy was performed for another patient. Postoperative fever occurred in 4 patients (18.2%). One patient received postoperative blood transfusion. Postoperative transient urinoma occurred in 2 patients (9.1%). CONCLUSION: PCNL in pediatric age group via FFMSP was proved to be safe and effective in management of renal pelvis stones of size 2-3 cm. It provides stone clearance rate comparable with that reported of conventional PCNL in the prone position.