Cardiac anomaly detection based on time and frequency domain features using tree-based classifiers.

OBJECTIVE: Recent advantages in mHealth-enabled ECG recorders boosted the demand for algorithms, which are able to automatically detect cardiac anomalies with high accuracy. APPROACH: We present a combined method of classical signal analysis and machine learning which has been developed during the Computing in Cardiology Challenge (CinC) 2017. Almost 400 hand-crafted features have been developed to reflect the complex physiology of cardiac arrhythmias and their appearance in single-channel ECG recordings. For the scope of this article, we performed several experiments on the publicly available challenge dataset to improve the classification accuracy. We compared the performance of two tree-based algorithms-gradient boosted trees and random forests-using different parameters for learning. We assessed the influence of five different sets of training annotations on the classifiers performance. Further, we present a new web-based ECG viewer to review and correct the training labels of a signal data set. Moreover, we analysed the feature importance and evaluated the model performance when using only a subset of the features. The primary data source used in the analysis was the dataset of the CinC 2017, consisting of 8528 signals from four classes. Our best results were achieved using a gradient boosted tree model which worked significantly better than random forests. MAIN RESULTS: Official results of the challenge follow-up phase provided by the Challenge organizers on the full hidden test set are 90.8% (Normal), 84.1% (AF), 74.5% (Other), resulting in a mean F1-score of 83.2%, which was only 1.6% behind the challenge winner and 0.2% ahead of the next-best algorithm. Official results were rounded to two decimal places which lead to the equal-second best F1 F -score of 83% with five others. SIGNIFICANCE: The algorithm achieved the second-best score among 80 algorithms of the Challenge follow-up phase equal with five others.

CROSSTALK BETWEEN VITAMIN B AND IMMUNITY.

Vitamin B1 (thiamin) is considered to be the oldest vitamin and in 1936 R.R. Williams and colleagues determined its chemical structure and were able to synthesize this vitamin. Vitamin B1 influences pro-apoptotic proteins, mitochondrial membrane potential, cytochrome C release, protein kinases, p38-MAPK, suppresses oxidative stress-induced NF-kappaB and has anti-inflammatory properties. Deficiency of vitamin B1 may cause beriberi, dysfunction of the nervous system, neuroinflammation, T cell infiltration, chemokine CCL2 activation, over expression of proinflammatory cytokines, such as IL-1, TNF, IL-6, and arachidonic acid products, and induces expression of CD40 by the microglia and CD40L by astrocytes which provoke the death of neurons. Here we report the relationship between vitamin B complex and immunity.

Can vitamin a mediate immunity and inflammation?

Vitamins are natural components of foods and are organic compounds distinct from fat, carbohydrates and proteins. Vitamin A is the generic descriptor for compounds with the qualitative biological activity of retinol. Unlike beta-carotene, vitamin A is not an antioxidant and its benefit is related to possible boosting of immune reactions. The effect of vitamin A on immune function is wide-reaching and its deficiency appears to affect immunity in several ways. Innate and adaptive immune responses are affected in some way by lack of vitamin A. Retinoids seem to act on differentiation of lymphocytes, antibody production, phagocytosis of macrophages, NK, Treg, and T helper cell activity. In addition, in humans, signs of a vitamin A deficiency also include the dysregulation of cytokine/chemokine generation and release. However, excess of vitamin A has been demonstrated to have toxic effects in most species studied. Here we summarize some important effects of vitamin A in immunity and inflammation.

Impact of mast cells on multiple sclerosis: inhibitory effect of natalizumab.

Mast cells (MCs) derive from a distinct precursor in the bone marrow and are predominantly found in tissues at the interface between the host and the external environment where they can secrete mediators without overt degranulation. Mast cells mature under local tissue microenvironmental factors and are necessary for the development of allergic reactions, through crosslinking of their surface receptors for IgE (FcεRI), leading to degranulation and the release of vasoactive, pro-inflammatory and nociceptive mediators that include histamine, pro-inflammatory and anti-inflammatory cytokines and proteolytic enzymes. Multiple sclerosis (MS) is an autoimmune disease characterized by inflammatory demylination within the central nervous system. MCs are involved in the pathogenesis of MS by generating various vasoactive mediators and cytokines and participate in the destruction of the myelin sheath and the neuronal cells. The process of the development of demyelinating plaques in MS is probably linked with the rupture of the blood-brain barrier by MC products. The effects of natalizumab, which is a very effective drug in reducing the annualized relapse rate and other relapse-based endpoints, are discussed. Here, we report the relationship between MCs and MS.

Effects of alpha-glucosidase inhibitors on mouth to caecum transit time in humans.

The alpha-glucosidase inhibitors acarbose and miglitol have been successfully used to control postprandial hyperglycaemia in diabetics. They probably work by slowing carbohydrate digestion and absorption, but their effect on mouth to caecum transit time has not been studied. The effect acarbose (100 mg), miglitol (100 mg), and placebo on mouth to caecum transit time (380 kcal breakfast with 20 g of lactulose) was investigated in 18 normal volunteers using breath hydrogen analysis. Both miglitol and acarbose significantly increased breath hydrogen excretion (F2,34 = 6.31, p = 0.005) and shortened the mouth to caecum transit time (F2,34 = 3.49, p = 0.04) after breakfast compared with placebo. There was a significant negative correlation between breath hydrogen excretion and mouth to caecum transit time suggesting that with shorter transit times significantly more carbohydrates were spilled into the colon. These results indicate that alpha-glucosidase inhibitors accelerate mouth to caecum transit time by inducing carbohydrate malabsorption.

Invasive balantidiasis presented as chronic colitis and lung involvement.

A unique case of chronic balantidiasis is described, presenting with chronic colitis and inflammatory polyposis of the rectum and sigmoid colon and an intrapulmonary mass. Histology of the colonic polyps showed Balantidium coli, and both Aspergillus and Balantidium coli were found in the aspirate of the pulmonary mass. The patient was treated with doxycycline HCl 100 mg/day for 10 days with complete clinical recovery and marked improvement of the endoscopic appearance of the colonic mucosa.