Biomarkers for the Diagnosis of Alzheimer’s Disease in Clinical Practice: The Role of CSF Biomarkers during the Evolution of Diagnostic Criteria

Alzheimer’s disease (AD) is a progressive condition and the most common cause of dementia worldwide. The neuropathological changes characteristic of the disorder can be successfully detected before the development of full-blown AD. Early diagnosis of the disease constitutes a formidable challenge for clinicians. CSF biomarkers are the in vivo evidence of neuropathological changes developing in the brain of dementia patients. Therefore, measurement of their concentrations allows for improved accuracy of clinical diagnosis. Moreover, AD biomarkers may provide an indication of disease stage. Importantly, the CSF biomarkers of AD play a pivotal role in the new diagnostic criteria for the disease, and in the recent biological definition of AD by the National Institute on Aging, NIH and Alzheimer’s Association. Due to the necessity of collecting CSF by lumbar puncture, the procedure seems to be an important issue not only from a medical, but also a legal, viewpoint. Furthermore, recent technological advances may contribute to the automation of AD biomarkers measurement and may result in the establishment of unified cut-off values and reference limits. Moreover, a group of international experts in the field of AD biomarkers have developed a consensus and guidelines on the interpretation of CSF biomarkers in the context of AD diagnosis. Thus, technological advancement and expert recommendations may contribute to a more widespread use of these diagnostic tests in clinical practice to support a diagnosis of mild cognitive impairment (MCI) or dementia due to AD. This review article presents up-to-date data regarding the usefulness of CSF biomarkers in routine clinical practice and in biomarkers research.     

Gene Variants Related to Cardiovascular and Pulmonary Diseases May Correlate with Severe Outcome of COVID-19

Background: Severe outcomes of COVID-19 account for up to 15% of all cases. The study aims to check if any gene variants related to cardiovascular (CVD) and pulmonary diseases (PD) are correlated with a severe outcome of COVID-19 in a Polish cohort of COVID-19 patients. Methods: In this study, a subset of 747 samples from unrelated individuals collected across Poland in 2020 and 2021 was used and whole-genome sequencing was performed. Results: The GWAS analysis of SNPs and short indels located in genes related to CVD identified one variant significant in COVID-19 severe outcome in the HADHA gene, while for the PD gene panel, we found two significant variants in the DRC1 gene. In this study, both potentially protective and risk variants were identified, of which variants in the HADHA gene deserve the most attention. Conclusions: This is the first study reporting the association between the HADHA and DRC1 genetic variants and COVID-19 severe outcome based on the cohort WGS analysis. Although all the identified variants are localised in introns, they may be correlated and therefore inherited along with other risk variants, potentially causative to severe outcome of COVID-19 but not discovered yet.     

Is attention all you need for intraday Forex trading?

The main objective of this paper is to analyse whether the Transformer neural network, which has become one of the most influential algorithms in Artificial Intelligence over the last few years, exhibits predictive capabilities for high-frequency Forex data. The prediction task is to classify short-term Forex movements for six currency pairs and five different time intervals from 60 to 720 min. We find that the Transformer exhibits high predictive power in the context of intraday Forex trading. This performance is slightly better than for the carefully selected benchmark – ResNet-LSTM, which currently is a state-of-the-art algorithm. Since intraday Forex trading based on deep learning models is largely unexplored, we offer insight on which currency pair and time interval are amenable to devising a profitable trading strategy. We also show that high predictive accuracy can be misleading in real world trading for short time intervals, as models trained on OHLC data tend to report the highest accuracy when the spread cost is the highest. This renders assessment based on typical machine learning metrics overly optimistic. Therefore, it is critical to backtest frequent intraday Forex trading strategies with realistic cost assumptions, which is rarely the case in empirical literature. Lastly, sensitivity analysis shows that the length of the time interval used for training does not play a critical role in the Transformer's predictive capabilities, whereas features derived from technical analysis are essential.     

The Effect of High and Variable Glucose on the Viability of Endothelial Cells Co-Cultured with Smooth Muscle Cells

Diabetes mellitus causes endothelial dysfunction. The aim of this study was to investigate the effect of normal (5 mmol/L), high (20 mmol/L), and fluctuating (5 and 20 mmol/L changed every day) glucose concentration in the culture medium on the viability of human umbilical vein endothelial cells (HUVECs) co-cultured with human umbilical artery smooth muscle cells (HUASMCs). The cultures were conducted on semi-permeable flat polysulfone (PSU) fibronectin-coated membranes immobilized in self-made inserts. The insert contained either HUVECs on a single membrane or HUASMCs and HUVECs on two membranes close to each other. Cultures were conducted for 7 or 14 days. Apoptosis, mitochondrial potential, and the production of reactive oxygen species and lactate by HUVECs were investigated. The results indicate that fluctuations in glucose concentration have a stronger negative effect on HUVECs viability than constant high glucose concentration. High and fluctuating glucose concentrations slow down cell proliferation compared to the culture carried out in the medium with normal glucose concentration. In conclusion, HUASMCs affect the viability of HUVECs when both types of cells are co-cultured in medium with normal or variable glucose concentration.     

Risk assessment for a video surveillance system based on Fuzzy Cognitive Maps

For various IT systems security is considered a key quality factor. In particular, it might be crucial for video surveillance systems, as their goal is to provide continuous protection of critical infrastructure and other facilities. Risk assessment is an important activity in security management; it aims at identifying assets, threats and vulnerabilities, analysis of implemented countermeasures and their effectiveness in mitigating risks. This paper discusses an application of a new risk assessment method, in which risk calculation is based on Fuzzy Cognitive Maps (FCMs) to a complex automated video surveillance system. FCMs are used to capture dependencies between assets and FCM based reasoning is applied to aggregate risks assigned to lower-level assets (e.g. cameras, hardware, software modules, communications, people) to such high level assets as services, maintained data and processes. Lessons learned indicate, that the proposed method is an efficient and low-cost approach, giving instantaneous feedback and enabling reasoning on effectiveness of security system.     

Evaluation of quadratic cost functionals for neutral systems: the frequency-domain approach

As shown in Grabowski (1983), the problem of evaluation of the quadratic performance index for delay-differential systems of neutral type can be effectively solved by the use of Lyapunov functionals. In this paper another solution to that problem, based on the frequency-domain approach, is proposed. With the use of Plancherel's theorem and other tools of complex analysis, this task is reduced to a Riemann-Hilbert problem, an explicit solution to which is found by elementary methods. Our results can be regarded as a generalization of those due to Walton and Marshall (1984, 1987). Two simple examples of application are also provided.     

A two-pronged approach for springback variability assessment using sparse polynomial chaos expansion and multi-level simulations

In this study, we show that stochastic analysis of metal forming process requires both a high precision and low cost numerical models in order to take into account very small perturbations on inputs (physical as well as process parameters) and to allow for numerous repeated analysis in a reasonable time. To this end, an original semi-analytical model dedicated to plain strain deep drawing based on a Bending-Under-Tension numerical model (B-U-T model) is used to accurately predict the influence of small random perturbations around a nominal solution estimated with a full scale Finite Element Model (FEM). We introduce a custom sparse variant of the Polynomial Chaos Expansion (PCE) to model the propagation of uncertainties through this model at low computational cost. Next, we apply this methodology to the deep drawing process of U-shaped metal sheet considering up to 8 random variables.     

Decision trees for uplift modeling with single and multiple treatments

Most classification approaches aim at achieving high prediction accuracy on a given dataset. However, in most practical cases, some action such as mailing an offer or treating a patient is to be taken on the classified objects, and we should model not the class probabilities themselves, but instead, the change in class probabilities caused by the action. The action should then be performed on those objects for which it will be most profitable. This problem is known as uplift modeling, differential response analysis, or true lift modeling, but has received very little attention in machine learning literature. An important modification of the problem involves several possible actions, when for each object, the model must also decide which action should be used in order to maximize profit. In this paper, we present tree-based classifiers designed for uplift modeling in both single and multiple treatment cases. To this end, we design new splitting criteria and pruning methods. The experiments confirm the usefulness of the proposed approaches and show significant improvement over previous uplift modeling techniques.