A Multi-classification Accessment Framework for Reproducible Evaluation of Multimodal Learning in Alzheimer's Disease.

Multimodal learning is widely used in automated early diagnosis of Alzheimer's disease. However, the current studies are based on an assumption that different modalities can provide more complementary information to help classify the samples from the public dataset Alzheimer's Disease Neuroimaging Initiative (ADNI). In addition, the combination of modalities and different tasks are external factors that affect the performance of multimodal learning. Above all, we summrise three main problems in the early diagnosis of Alzheimer's disease: (i) unimodal vs multimodal; (ii) different combinations of modalities; (iii) classification of different tasks. In this paper, to experimentally verify these three problems, a novel and reproducible multi-classification framework for Alzheimer's disease early automatic diagnosis is proposed to evaluate and verify the above issues. The multi-classification framework contains four layers, two types of feature representation methods, and two types of models to verify these three issues. At the same time, our framework is extensible, that is, it is compatible with new modalities generated by new technologies. Following that, a series of experiments based on the ADNI-1 dataset are conducted and some possible explanations for the early diagnosis of Alzheimer's disease are obtained through multimodal learning. Experimental results show that SNP has the highest accuracy rate of 57.09% in the early diagnosis of Alzheimer's disease. In the modality combination, the addition of Single Nucleotide Polymorphism modality improves the multi-modal machine learning performance by 3% to 7%. Furthermore, we analyse and discuss the most related Region of Interest and Single Nucleotide Polymorphism features of different modalities.

Neutrophil-to-lymphocyte ratio predicts coronary artery lesion severity and long-term cardiovascular mortality in patients with unstable angina pectoris.

OBJECTIVES: Neutrophil-to-lymphocyte ratio (NLR), one of the composite biomarker of systemic inflammatory status, was proved promising in predicting clinical outcomes of acute coronary syndrome (ACS). However, there were no evidences that NLR was directly relative to the clinical outcomes of unstable angina pectoris (UAP). Therefore, this study was aimed to detect whether NLR could predict the coronary artery lesion severity (indicated as SYNTAX score) and clinical outcomes (especially long-term cardiovascular mortality) in patients with. METHODS: In the single-centre retrospective study, 4110 patients with UAP were enrolled and divided into two groups according to their primary NLR values and followed up at a median time duration of 36 months. The differences of SYNTAX score and cardiovascular mortality between groups were analysed, and the predictive value of NLR was determined. RESULTS: NLR was positively and linearly correlated with SYNTAX score (r = 0.270). Diabetes (p = 0.049), lymphocyte (p = 0.004), NLR (p = 0.002) and SYNTAX score (p < 0.001) were independent predictors of long-term cardiovascular mortality in patients with UAP. Kaplan-Meier analysis revealed higher occurrence of cardiovascular mortality when NLR > 2.38 (p = 0.015). Receiver operating characteristic (ROC) analysis showed that NLR = 2.76 is an effective cut point for predicting cardiovascular mortality (69.2% sensitivity, 64.8% specificity). CONCLUSIONS: NLR value was positively related to the severity of coronary artery lesion and proved to be an independent predictor of cardiovascular mortality in patients with UAP. This study would contribute to therapy and prognosis optimisation of UAP.

Severe pneumonia and acute myocardial infarction complicated with pericarditis after percutaneous coronary intervention: A case report.

BACKGROUND: Cases of severe pneumonia complicated with acute myocardial infarction (AMI) with good prognosis after percutaneous coronary intervention (PCI) are rare, especially those with postoperative pericarditis and intestinal obstruction. CASE SUMMARY: A 53-year-old male patient was admitted to the emergency department of our hospital because of paroxysmal chest tightness for 4 d, aggravated with chest pain for 12 h. The symptoms, electrocardiography, biochemical parameters, echocardiography and chest computed tomography confirmed the diagnosis of severe pneumonia complicated with AMI. The patient was treated with antiplatelet aggregation, anticoagulation, lipid regulation, vasodilation, anti-infective agents and direct PCI. The patient was discharged after 3 wk of treatment. Follow-up showed that the patient was asymptomatic without recurrence. CONCLUSION: For patients with severe pneumonia complicated with AMI, PCI and antibiotic therapy is a life-saving strategy.

The uric acid to albumin ratio: a novel predictor of long-term cardiac mortality in patients with unstable angina pectoris after percutaneous coronary intervention.

The prognosis of unstable angina pectoris (UAP) differs from non-ST-segment elevation myocardial infarction, and percutaneous coronary intervention (PCI) is considered to improve outcomes of UAP. This study aimed to assess the prognostic value of uric acid to albumin ratio (UAR) for long-term mortality in UAP patients after PCI. Our study retrospectively enrolled 2298 patients hospitalized because of UAP in a tertiary hospital. Divided by medium UAR, the patients were classified into two groups. Baseline demographics, clinical features and laboratory characteristics were obtained from medical records. Post-discharge follow-up was performed either in outdoor clinic or through phone call. The primary endpoint in this study was cardiac death, while all-cause death and rehospitalization were designated as the secondary endpoints. The median follow-up time was 672 days. Among all patients, 58 (2.5%) died, 28 of which died of cardiac deaths (1.2%), and 467 were re-hospitalized (20.3%). Cardiac mortality and all-cause mortality were found to be significantly higher in the high UAR group than in the low UAR group (p = 0.007, p < 0.001), and Kaplan-Meier analysis showed patients with higher UAR may suffer from worse outcomes (p = 0.020). UAR, PCI history, and age were identified as independent predictors of cardiac mortality by multivariate Cox regression. A UAR value of >8.35 was demonstrated as an ideal cut-off point to predict post-PCI cardiac mortality (p <0.001). Overall, it is indicated that baseline UAR was independently correlated with long-term cardiac mortality in patients with UAP treated by PCI.

Analysis of Ticagrelor's Cardio-protective Effects on Patients with ST-segment Elevation Acute Coronary Syndrome Accompanied with Diabetes.

BACKGROUND: To analyze the cardio-protective effects of ticagrelor in patients with acute coronary syndrome with S-T segment elevation. METHODS: The sample was 200 patients who had been diagnosed with acute coronary syndrome accompanied by diabetes Mellitus type II. Only patients having ST segment elevation before the treatment were included. Then, the subjects were further randomly divided into an observation group and a control group. The control group of 100 patients received clopidogrel; the observation group of 100 patients of ticagrelor. The serous creatine kinase CK-MB, functional cardiac indexes of left ventricular end diastolic diameter (LVDD), cardiac troponin I, ventricular ejection fraction, and relevant major adverse cardiovascular events (MACE) were compared between the two groups. RESULTS: One month after a percutaneous coronary intervention (PCI) the observation group showed better results against angina, stent thrombosis, and all-cause mortality compared with those of the control subjects. Six months after treatment, both groups suffered adverse reactions. The number of patients who suffered adverse reactions in respiratory tract in the observation group was higher than in the control group. The inhibition of platelet aggregation IPA of ticagrelor was found to be significantly higher than clopidogrel, having a significant p value. CONCLUSION: Ticagrelor can effectively protect myocardial function for patients with ST-segment elevation acute coronary syndrome accompanied by diabetes and can reduce the incidence of adverse reactions..

An Initialization Method Based on Hybrid Distance for k-Means Algorithm.

The traditional [Formula: see text]-means algorithm has been widely used as a simple and efficient clustering method. However, the performance of this algorithm is highly dependent on the selection of initial cluster centers. Therefore, the method adopted for choosing initial cluster centers is extremely important. In this letter, we redefine the density of points according to the number of its neighbors, as well as the distance between points and their neighbors. In addition, we define a new distance measure that considers both Euclidean distance and density. Based on that, we propose an algorithm for selecting initial cluster centers that can dynamically adjust the weighting parameter. Furthermore, we propose a new internal clustering validation measure, the clustering validation index based on the neighbors (CVN), which can be exploited to select the optimal result among multiple clustering results. Experimental results show that the proposed algorithm outperforms existing initialization methods on real-world data sets and demonstrates the adaptability of the proposed algorithm to data sets with various characteristics.

Management of antibiotic-associated pseudomembranous colitis in Non-hospitalized and hospitalized patients.

Proper management of antibiotic-associated pseudo membranous colitis is not clear. This article is to investigate proper treatment of antibiotic-associated pseudo membranous colitis. Data of 67 patients (aged 18-69 years, with 31 males and 46 females) with antibiotic-associated pseudo membranous colitis were retrospectively analyzed including the demography, antibiotics to induce and for treatment of the pseudo membranous colitis, and other supportive measures. All 67 patients had a positive cytotoxin test, which confirmed the pseudo membranous colitis. Antibiotics which induced the pseudo membranous colitis included clindamycin, ofloxacin, piperacillin, cefatriaxone, penbritin and ceftazidime. Once the correct diagnosis was made, the culprit antibiotics were discontinued immediately, and narrow-spectrum antibiotics like metronidazole and vancomycin were administered in combination with correction of fluid and electrolyte abnormalities, use of vitamins C and B complex to repair the intestinal mucosa, and avoidance of antispasmodic and antidiarrheal agents. After appropriate treatment for 2-20 days, all patients recovered with no sequela. Sixty-two patients were clinically cured while five (7.5%) had diarrhea recurrence within two months of the end of therapy. Retreatment with tapering and extended period of metronidazole and/or vancomycin led to complete recovery of the patients. Multiple antibiotic agents are associated with pseudo membranous colitis, and correction of fluid and electrolyte abnormalities and use of vitamins to repair the intestinal mucosa should be performed to speed up the cure process.