Heart failure classification using deep learning to extract spatiotemporal features from ECG.

BACKGROUND: Heart failure is a syndrome with complex clinical manifestations. Due to increasing population aging, heart failure has become a major medical problem worldwide. In this study, we used the MIMIC-III public database to extract the temporal and spatial characteristics of electrocardiogram (ECG) signals from patients with heart failure. METHODS: We developed a NYHA functional classification model for heart failure based on a deep learning method. We introduced an integrating attention mechanism based on the CNN-LSTM-SE model, segmenting the ECG signal into 2 to 20 s long segments. Ablation experiments showed that the 12 s ECG signal segments could be used with the proposed deep learning model for superior classification of heart failure. RESULTS: The accuracy, positive predictive value, sensitivity, and specificity of the NYHA functional classification method were 99.09, 98.9855, 99.033, and 99.649%, respectively. CONCLUSIONS: The comprehensive performance of this model exceeds similar methods and can be used to assist in clinical medical diagnoses.

Suicidal Ideation and Electroconvulsive Therapy: Outcomes in Adolescents With Major Depressive Disorder.

OBJECTIVE: Few studies on electroconvulsive therapy (ECT) investigate efficacy and safety on depressive adolescents with strong suicidal ideation. Our study examined adolescents (aged 13-18 years) with major depressive disorder to explore ECT effectiveness in improving suicidal ideation and depressive symptoms, as well as its impact on cognitive function. METHODS: This nonrandomized controlled trial enrolled 183 adolescent patients suffering from major depressive disorder. The ECT group (n = 81) was treated with antidepressants and 8 rounds of ECT for 2 weeks. The control group comprised 79 patients treated with antidepressants only. Depressive symptoms, suicidal ideation, and cognitive functions were assessed at baseline (pre-ECT) and at 2 and 6 weeks post-ECT. RESULTS: The ECT group showed significant improvements over control in suicidal ideation from the end of treatment to 6 weeks after ( P < 0.001). Depressive symptoms also improved ( P < 0.001). Patients treated with ECT demonstrated poorer performance in delayed memory, attention, and language, but these impairments were transient. Thus, ECT was generally safe in adolescent patients with major depressive disorder. CONCLUSIONS: Our findings verified ECT as effective and safe for improving suicidal ideation and depressive symptoms of adolescent patients with major depressive disorder. In addition, partially impaired cognitive function recovered gradually after ECT.

Research status and global trends of late-life depression from 2004 to 2023: bibliometric analysis.

Background: Global research hotspots and future research trends in the neurobiological mechanisms of late-life depression (LLD) as well as its diagnosis and treatment are not yet clear. Objectives: This study profiled the current state of global research on LLD and predicted future research trends in the field. Methods: Literature with the subject term LLD was retrieved from the Web of Science Core Collection, and CiteSpace software was used to perform econometric and co-occurrence analyses. The results were visualized using CiteSpace, VOSviewer, and other software packages. Results: In total, 10,570 publications were included in the analysis. Publications on LLD have shown an increasing trend since 2004. The United States and the University of California had the highest number of publications, followed consecutively by China and England, making these countries and institutions the most influential in the field. Reynolds, Charles F. was the author with the most publications. The International Journal of Geriatric Psychiatry was the journal with the most articles and citations. According to the co-occurrence analysis and keyword/citation burst analysis, cognitive impairment, brain network dysfunction, vascular disease, and treatment of LLD were research hotspots. Conclusion: Late-life depression has attracted increasing attention from researchers, with the number of publications increasing annually. However, many questions remain unaddressed in this field, such as the relationship between LLD and cognitive impairment and dementia, or the impact of vascular factors and brain network dysfunction on LLD. Additionally, the treatment of patients with LLD is currently a clinical challenge. The results of this study will help researchers find suitable research partners and journals, as well as predict future hotspots.

Bibliometric Analysis of the Research Status and Global Trends in Behavioral and Psychological Symptoms of Dementia in Alzheimer's Disease from 2002 to 2022.

Several reviews on behavioral and psychological symptoms (BPSDs) in patients with Alzheimer's disease (AD) have summarized the current state of this field, but global trends are unclear. This study utilized CiteSpace to provide a global overview of the current (from 2002 to 2022) state of research on AD and its BPSDs and to predict future research trends in the field. Data were retrieved from the Web of Science Core Collection. Bibliometric and co-occurrence analyses were performed using CiteSpace software. In total, 787 valid publications were included in the analysis. Publications on AD and BPSD have shown an increasing trend since 2002. The United States and the University of Toronto were the countries and institutions with the highest total number of publications, respectively, whereas Japan and China were the second and third most influential in the field in terms of number of publications. Clive Ballard was the top author in terms of the number of publications. Journal of Alz- heimer's Disease had the highest number of publications on this topic. Co-occurrence analysis showed that AD, behavioral symptoms, cognitive impairment, and early markers are hot topics in this area. Non-drug management of BPSDs, pharmacological treatment, and physiotherapy will be a hot topic in this field in the future. Our study visualized the relevant articles over the past 21 years to detect global hotspots and trends. Our findings may help researchers to identify research hotspots in this field and will help in the selection of appropriate research topics, while possibly leading to cross-regional coop-eration.

Association of age at first sexual intercourse and lifetime number of sexual partners with cardiovascular diseases: a bi-directional Mendelian randomization study.

Background: Limited studies have explored the association between sexual factors [age at first sexual intercourse (AFS) and lifetime number of sexual partners (LNSP)] and cardiovascular diseases (CVDs), leaving the causality inconclusive. Methods: We performed a bi-directional Mendelian randomization (MR) study to investigate the causality between sexual factors and CVDs, including coronary artery disease, myocardial infarction, atrial fibrillation (AF), heart failure (HF), and ischemic stroke (IS). Single-nucleotide polymorphisms (SNPs) for sexual factors were extracted from the UK Biobank. Statistics for each CVD were derived from two different databases. MR estimates were calculated per outcome database and were combined through meta-analysis. Several complementary sensitivity analyses were also performed. Results: The primary analysis suggested that AFS was causally associated with the risk of CVDs; the odds ratios (ORs) ranged from 0.686 [95% confidence interval (CI), 0.611-0.770] for HF to 0.798 (95% CI, 0.719-0.886) for AF. However, the association between AFS and IS (OR, 0.844; 95% CI, 0.632-1.126) was not consistent in the meta-analysis after excluding SNPs related to confounders. Moreover, non-significant associations were found between LNSP and CVDs. Reverse direction MR analysis showed that CVDs were not associated with sexual factors. Conclusions: Genetic evidence suggested that AFS was causally associated with the risk of CVDs except for IS, whereas non-significant association of LNSP with CVDs was detected. Further investigation into AFS could be warranted in preventing the progression of CVDs.

Association between electroconvulsive therapy and depressive disorder from 2012 to 2021: Bibliometric analysis and global trends.

Background: Depressive disorder is a chronic mental illness that is vulnerable to relapse, imposes a huge economic burden on society and patients, and is a major global public health problem. Depressive disorders are characterized by depressed mood, decreased energy and interest, and suicidal ideation and behavior in severe cases. They can be treated through pharmacotherapy and psychotherapy or physical treatments such as electroconvulsive therapy (ECT). In patients with suicidal ideation, behavior, or refractory depressive disorder ECT has a faster onset of action and better efficacy than pharmacotherapy. This study used bibliometric and visual analyses to map the current state of global research on ECT for depressive disorder and to predict future research trends in this area. Materials and methods: A literature search was performed for studies on ECT and depressive disorder in the Web of Science Core Collection (WoSCC) database. All studies considered for this paper were published between 2012 and 2021. Bibliometric and co-occurrence analyses were performed using the CiteSpace software. Results: In total, 2,184 publications were retrieved. The number of publications on ECT and depressive disorder have been increasing since 2012, with China being a emerging hub with a growing influence in the field. Zafiris J. Daskalakis is the top author in terms of number of publications, and The Journal of ECT is not only the most published journal but also the most co-cited journal in the field. Co-occurrence analysis showed that electroconvulsive therapy, treatment-resistant depression, bipolar disorder, hippocampus, efficacy, and electrode placement are current research hotspots. Molecular biomarkers, neuroimaging predictors, and late-life depression will become research hotspots in the future. Conclusion: Our analysis made it possible to observe an important growth of the field since 2012, to identify key scientific actors in this growth and to predict hot topics for future research.

Assessment of causal associations between handgrip strength and cardiovascular diseases: A two sample mendelian randomization study.

Background: Several observational studies have identified that handgrip strength was inversely associated with cardiovascular diseases (CVDs). Nevertheless, causality remains controversial. We conducted Mendelian randomization (MR) analysis to examine whether handgrip strength and risk of CVDs are causally associated. Methods: We identified 160 independent single nucleotide polymorphisms (SNPs) for right-hand grip strength and 136 independent SNPs for left-hand grip strength at the genome-wide significant threshold (P < 5 × 10-8) from UK Biobank participants and evaluated these in relation to risk of CVDs. MR estimates was calculated using the inverse-variance weighted (IVW) method and multiple sensitivity analysis was further conducted. Results: Genetical liability to handgrip strength was significantly associated with coronary artery disease (CAD) and myocardial infarction (MI), but not stroke, hypertension, or heart failure. Additionally, there was significant association between right-hand grip strength and atrial fibrillation (OR, 0.967; 95% CI, 0.950-0.984; p = 0.000222), however, suggestive significance was found between left-hand grip strength and atrial fibrillation (OR, 0.977; 95% CI, 0.957-0.998; p = 0.033). Results were similar in several sensitivity analysis. Conclusion: Our study provides support at the genetic level that handgrip strength is negatively associated with the risk of CAD, MI, and atrial fibrillation. Specific handgrip strength interventions on CVDs warrant exploration as potential CVDs prevention measures.

[(99)Tc(m)-MIBI exercise stress single photon emission computed tomography myocardial perfusion imaging of patients with myocardial bridge].

OBJECTIVE: To observe the exercise single photon emission computed tomography (SPECT) myocardial perfusion imaging of patients with myocardial bridge and assess the association between myocardial ischemia and extent of myocardial systolic compression. METHODS: Seventeen patients with myocardial bridge diagnosed by coronary angiogram were included and underwent exercise SPECT myocardial perfusion imaging. RESULTS: Abnormal SPECT perfusion imaging was evidenced in 12 out of 17 patients with myocardial bridge (2 out of 6 patients with systolic compression induced stenosis < 50%, 3 out of 4 patients with systolic compression induced stenosis between 50% - 75% and 7 out of 7 patients with the systolic compression induced stenosis between 75% - 100%). CONCLUSION: Exercise stress SPECT myocardial perfusion imaging could detect myocardial ischemia in patients with myocardial bridge and abnormal perfusion is positively related to the extent of systolic compression induced stenosis.

Circulating microRNAs as biomarkers for severe coronary artery disease.

Coronary artery disease (CAD) is the second leading cause of death after stroke in China. Percutaneous coronary intervention (PCI) significantly improves the prognosis of CAD patients. This study aimed to evaluate the diagnostic value of circulating microRNAs (miRNAs) in patients with severe CAD requiring PCI. The plasma miRNA profiles were determined using miRNA microarray. The relative expression levels of differentially expressed miRNA were measured by quantitative reverse transcription polymerase chain reaction (qRT-PCR). Nine miRNAs (ebv-miR-BART12, ebv-miR-BART16, let-7i-5p, miR-130a-3p, miR-26a-5p, miR-3149, miR-3152-3p, miR-32-3p, and miR-149-3p) were differentially expressed between severe CAD and control groups. Four miRNAs (let-7i-5p, miR-32-3p, miR-3149, and miR-26a-5p) validated by qRT-PCR showed good diagnostic accuracy, with the area under the receiver operating characteristic curves (AUCs) of 0.634 (95% confidence interval [CI] 0.528-0.739), 0.745 (95%CI 0.649-0.84), 0.795 (95%CI 0.709-0.88), and 0.818 (95%CI 0.739-0.897), respectively. Furthermore, the combination of these 4 miRNAs exhibited better diagnostic performance compared with any individual miRNA, with an AUC of 0.837 (95%CI 0.763-0.911). These data indicate that plasma let-7i-5p, miR-32-3p, miR-3149, and miR-26a-5p have promising diagnostic value for severe CAD.

Effects of Stereo and Screen Size on the Legibility of Three-Dimensional Streamtube Visualization.

We report the impact of display characteristics (stereo and size) on task performance in diffusion magnetic resonance imaging (DMRI) in a user study with 12 participants. The hypotheses were that (1) adding stereo and increasing display size would improve task accuracy and reduce completion time, and (2) the greater the complexity of a spatial task, the greater the benefits of an improved display. Thus we expected to see greater performance gains when detailed visual reasoning was required. Participants used dense streamtube visualizations to perform five representative tasks: (1) determine the higher average fractional anisotropy (FA) values between two regions, (2) find the endpoints of fiber tracts, (3) name a bundle, (4) mark a brain lesion, and (5) judge if tracts belong to the same bundle. Contrary to our hypotheses, we found the task completion time was not improved by the use of the larger display and that performance accuracy was hurt rather than helped by the introduction of stereo in our study with dense DMRI data. Bigger was not always better. Thus cautious should be taken when selecting displays for scientific visualization applications. We explored the results further using the body-scale unit and subjective size and stereo experiences.