DWT-CNNTRN: a Convolutional Transformer for ECG Classification with Discrete Wavelet Transform.

Cardiovascular diseases are the leading cause of death worldwide. The diagnoses of cardiovascular diseases are usually carried out by cardiologists utilizing Electrocardiograms (ECGs). To assist these physicians in making an accurate diagnosis, there is a growing need for reliable and automatic ECG classifiers.In this study, a new method is proposed to classify 12-lead ECG recordings. The proposed model is composed of four components: the CNN(Convolutional Neural Network) module, the transformer module, the global hybrid pooling layer, and a classification layer. To improve the classification performance, the model takes the discrete wavelet transform of ECG signals as the model inputs and utilizes a hybrid pooling layer to condense the most important features over each period.The proposed model is evaluated using the test set of the China Physiological Signal Challenge 2018 dataset with 12-lead ECGs. It performs with an average accuracy of 0.86 and an average F1-scores of 0.83. The scores are particularly good for the block conditions (LBBB, RBBB, I-AVB). The main advantage of the proposed model is that, it obtains good results with a significantly smaller number of parameters compared to other individual and ensemble models.Clinical relevance- This work establishes a new ECG classifier model with high performance and low model size. It can make automatic ECG analysis more accessible, efficient, and accurate, especially in remote or underserved areas.

Heartbeat Classification by Random Forest With a Novel Context Feature: A Segment Label.

OBJECTIVE: Physicians use electrocardiograms (ECG) to diagnose cardiac abnormalities. Sometimes they need to take a deeper look at abnormal heartbeats to diagnose the patients more precisely. The objective of this research is to design a more accurate heartbeat classification algorithm to assist physicians in identifying specific types of the heartbeat. METHODS AND PROCEDURES: In this paper, we propose a novel feature called a segment label, to improve the performance of a heartbeat classifier. This feature, provided by a Convolutional Neural Network, encodes the information surrounding the particular heartbeat. The random forest classifier is trained based on this new feature and other traditional features to classify the heartbeats. RESULTS: We validate our method on the MIT-BIH Arrhythmia dataset following the inter-patient evaluation paradigm. The proposed method is competitive with other similar works. It achieves an accuracy of 0.96, and F1-scores for normal beats, ventricular ectopic beats, and Supra-Ventricular Ectopic Beats (SVEB) of 0.98, 0.93, and 0.74, respectively. The precision and sensitivity for SVEB are 0.76 and 0.78, which outperforms the state-of-the-art methods. CONCLUSION: This study demonstrates that the segment label can contribute to precisely classifying heartbeats, especially those that require rhythm information as context information (e.g. SVEB). Clinical impact: Using a medical devices embedding our algorithm could ease the physicians' processes of diagnosing cardiovascular diseases, especially for SVEB, in clinical implementation.

CT differentiation of enlarged mediastinal lymph node due to anthracosis from metastatic lymphadenopathy: a comparative study proven by endobronchial US-guided transbronchial needle aspiration.

PURPOSE: Anthracosis often results in mediastinal nodal enlargement. The aim of this comparative study was to evaluate if it is possible to differentiate endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) proven anthracotic lymph nodes from malignant lymph node enlargement by means of multislice computed tomography (MSCT). METHODS: We compared the MSCT findings of 89 enlarged lymph nodes due to anthracosis with 54 malignant lymph nodes (non-small cell lung cancer 75.9%, small cell lung cancer 18.5%, and non-Hodgkin lymphoma 5.6%). The lymph nodes were assessed for density (calcification, fat, and necrosis), shape (oval, round), contrast enhancement, and contour (sharp, ill-defined). RESULTS: Malignant lymph nodes showed significantly greater axis diameters (P < 0.001). Both anthracotic and malignant nodes were most often oval (86.5% of all malignant nodes vs. 81.5% of all anthracotic nodes, P = 0.420) and showed confluence in a remarkable percentage (28.1% vs. 42.6%, P = 0.075). Anthracotic nodes showed calcifications more often (18% vs. 0%, P < 0.001). Malignant lymph nodes showed a significantly greater short and long axis diameter (P < 0.001), and they had a higher frequency of ill-defined contours (27.8% vs. 2.2%, P < 0.001) and contrast enhancement (27.8% vs. 5.6%, P < 0.001). Nodal necrosis, which appeared in one third of the malignant nodes, was not observed in anthracosis (35.2% vs. 0%, P < 0.001). Confluence of enlarged lymph nodes was seen in malignant lymph nodes (42.6%), as well as in lymph node enlargement due to anthracosis (28.1%, P = 0.075). CONCLUSION: Our results show that there are significant differences in MSCT findings of malignant enlarged lymph nodes and benign lymph node enlargement due to anthracosis.

Polyspecies biofilm formation on implant surfaces with different surface characteristics.

OBJECTIVE: To investigate the microbial adherence and colonization of a polyspecies biofilm on 7 differently processed titanium surfaces. MATERIAL AND METHODS: Six-species biofilms were formed anaerobically on 5-mm-diameter sterilized, saliva-preconditioned titanium discs. Material surfaces used were either machined, stained, acid-etched or sandblasted/acid-etched (SLA). Samples of the latter two materials were also provided in a chemically modified form, with increased wettability characteristics. Surface roughness and contact angles of all materials were determined. The discs were then incubated anaerobically for up to 16.5 h. Initial microbial adherence was evaluated after 20 min incubation and further colonization after 2, 4, 8, and 16.5 h using non-selective and selective culture techniques. Results at different time points were compared using ANOVA and Scheffé post hoc analysis. RESULTS: The mean differences in microorganisms colonizing after the first 20 min were in a very narrow range (4.5 to 4.8 log CFU). At up to 16.5 h, the modified SLA surface exhibited the highest values for colonization (6.9±0.2 log CFU, p<0.05) but increasing growth was observed on all test surfaces over time. Discrepancies among bacterial strains on the differently crafted titanium surfaces were very similar to those described for total log CFU. F. nucleatum was below the detection limit on all surfaces after 4 h. CONCLUSION: Within the limitations of this in vitro study, surface roughness had a moderate influence on biofilm formation, while wettability did not seem to influence biofilm formation under the experimental conditions described. The modified SLA surface showed the highest trend for bacterial colonization.

Polyspecies biofilm formation on implant surfaces with different surface characteristics

Objective: To investigate the microbial adherence and colonization of a polyspecies biofilm on 7 differently processed titanium surfaces. Material and Methods: Six-species biofilms were formed anaerobically on 5-mm-diameter sterilized, saliva-preconditioned titanium discs. Material surfaces used were either machined, stained, acid-etched or sandblasted/acid-etched (SLA). Samples of the latter two materials were also provided in a chemically modified form, with increased wettability characteristics. Surface roughness and contact angles of all materials were determined. The discs were then incubated anaerobically for up to 16.5 h. Initial microbial adherence was evaluated after 20 min incubation and further colonization after 2, 4, 8, and 16.5 h using non-selective and selective culture techniques. Results at different time points were compared using ANOVA and Scheffé post hoc analysis. Results: The mean differences in microorganisms colonizing after the first 20 min were in a very narrow range (4.5 to 4.8 log CFU). At up to 16.5 h, the modified SLA surface exhibited the highest values for colonization (6.9±0.2 log CFU, p<0.05) but increasing growth was observed on all test surfaces over time. Discrepancies among bacterial strains on the differently crafted titanium surfaces were very similar to those described for total log CFU. F. nucleatum was below the detection limit on all surfaces after 4 h. Conclusion: Within the limitations of this in vitro study, surface roughness had a moderate influence on biofilm formation, while wettability did not seem to influence biofilm formation under the experimental conditions described. The modified SLA surface showed the highest trend for bacterial colonization.

A comprehensive study of polymorphisms in ABCB1, ABCC2 and ABCG2 and lung cancer chemotherapy response and prognosis.

ATP-binding cassette (ABC) transporter expression and genetic heterogeneity have been implicated in response to anticancer therapy. This study characterized genetic variability of the ABCB1 (also known as MDR1), ABCC2 (MRP2) and ABCG2 (BCRP) genes, which are key players in the metabolism of many chemotherapeutic agents including those used in the treatment of lung cancer. We genotyped 53 polymorphisms in the candidate genes in genomic DNA samples of 171 cases of small cell lung carcinoma (SCLC) and 206 cases of non-small cell lung carcinoma (NSCLC), and studied their impact on early response to chemotherapy, progression-free survival and overall survival. SNP rs717620 in ABCC2 was moderately associated with a poor response to chemotherapy but strongly with shorter progression-free survival and overall survival in SCLC but not NSCLC patients, indicating that ABCC2 genetic variation is an important factor in SCLC survival after chemotherapy.

A deficiency in nucleoside salvage impairs murine lymphocyte development, homeostasis, and survival.

The homeostasis of the immune system is tightly controlled by both cell-extrinsic and -intrinsic mechanisms. These regulators, not all known to date, drive cells in and out of quiescence when and where required to allow the immune system to function. In this article, we describe a deficiency in deoxycytidine kinase (DCK), one of the major enzymes of the nucleoside salvage pathway, which affects peripheral T cell homeostatic proliferation and survival. As a result of an N-ethyl-N-nitrosourea-induced mutation in the last α helix of DCK, a functionally null protein has been generated in the mouse and affects the composition of the hematopoietic system. Both B and T lymphocyte development is impaired, leading to a state of chronic lymphopenia and to a significant increase in the number of myeloid cells and erythrocytes. In the periphery, we found that mutant lymphocytes adopt a CD44(high)CD62L(low) memory phenotype, with high levels of proliferation and apoptosis. These phenotypes are notably the result of a cell-extrinsic-driven lymphopenia-induced proliferation as wild-type cells transferred into DCK-deficient recipients adopt the same profile. In addition, DCK also regulates lymphocyte quiescence in a cell-intrinsic manner. These data establish dCK as a new regulator of hematopoietic integrity and lymphocyte quiescence and survival.

Polymorphisms in the apoptotic pathway gene BCL-2 and survival in small cell lung cancer.

INTRODUCTION: We investigated the single-nucleotide polymorphism C-938A in the apoptotic gene BCL-2 to assess the potential impact as a genetic marker for response to chemotherapy and outcome prediction in small cell lung cancer (SCLC) patients. Such a marker might help optimize lung cancer treatment in a tailored approach. METHODS: DNA derived from peripheral blood lymphocytes of 188 Caucasian SCLC patients treated at the Thoraxklinik Heidelberg was genotyped. Chemotherapy response, time to progression (TTP), and overall survival (OS) were evaluated using multivariable regression (unconditional logistic for response and Cox proportional hazard for TTP and OS) with odds ratios and hazard ratios (HRs) and their 95% confidence intervals (CIs) as quantitative outcome measures, respectively. RESULTS: Small cell lung cancer patients carrying the BCL-2 -938CC genotype showed significantly worse TTP than patients carrying the BCL-2 -938AA genotype (HR = 1.86; 95% CI = 1.10-3.13, p = 0.021). The same adverse effect was shown for OS (HR = 2.38; 95% CI = 1.38-4.12, p = 0.002). Also, patients with limited disease (HR = 2.57; 95% CI = 1.18-5.60, p = 0.017) showed worse OS with the BCL-2 -938CC genotype. CONCLUSION: BCL-2 -938CC genotype shows significantly worse outcome in small cell lung cancer patients. This genetic marker might particularly impact on treatment strategies using BCL-2 antisense approaches.

Polymorphisms in ABCG2, ABCC3 and CNT1 genes and their possible impact on chemotherapy outcome of lung cancer patients.

The prognosis of lung cancer patients treated with chemotherapy is poor, motivating the search for predictive factors. Single nucleotide polymorphisms (SNPs) in membrane transporter genes could influence the pharmacokinetics of cytostatic drugs and therefore affect treatment outcome. We examined 6 SNPs with known or suspected phenotypic effect: ABCG2 G34A, C421A; ABCC3 C-211T, G3890A, C3942T and CNT1 G565A. For 349 Caucasian patients with primary lung cancer [161 small cell lung cancer (SCLC), 187 nonsmall cell lung cancer (NSCLC) and 1 mixed] receiving first-line chemotherapy 3 different endpoints were analyzed: response after the 2nd cycle (R), progression-free survival (PFS) and overall survival (OS). The prognostic value of the SNPs was analyzed using multivariable logistic regression, calculating odds ratios (ORs) when comparing genotype frequencies in responders and nonresponders after the 2nd cycle. Hazard ratios (HRs) for PFS and for OS were calculated using Cox regression methods. In all lung cancer patients, none of the investigated polymorphisms modified response statistically significant. The only significant result in the histological subpopulations was in SCLC patients carrying the ABCC3 -211T allele who showed significantly worsened PFS (HR: 1.79; 95% confidence interval (CI) 1.13-2.82). In an exploratory subgroup analysis significantly worse OS was seen for carriers of the ABCG2 421A-allele treated with platinum-based drugs (HR: 1.60; 95% CI 1.04-2.47; n = 256). In conclusion, this study prioritizes ABCC3 C-211T and ABCG2 C421A as candidate transporter SNPs to be further investigated as possible predictors of the clinical outcome of chemotherapy in lung cancer patients.

Polymorphisms in transporter and phase II metabolism genes as potential modifiers of the predisposition to and treatment outcome of de novo acute myeloid leukemia in Israeli ethnic groups.

Drug metabolism/disposition and transporter genes may influence predisposition or prognosis of AML (acute myeloid leukemia) patients. We analyzed polymorphisms in 3 transporters and 4 drug metabolism genes in 293 Israeli individuals (112 AML patients and 181 controls). We analyzed: ABCC3 (MRP3) C-211T; ABCG2 (BCRP) C421A; CNT1 (SLC28A1) G565A and NAT1, NAT2, and GSTT1 and GSTM1 null alleles for influence on predisposition, as well as treatment response and survival. We found that the ABCC3 C-211T polymorphism and GSTM1 null genotype have adverse prognostic significance in AML. None of the other polymorphisms studied were found to influence either predisposition or prognosis in Israeli AML patients.