The Use of Retinal Microvascular Function and Telomere Length in Age and Blood Pressure Prediction in Individuals with Low Cardiovascular Risk.

Ageing represents a major risk factor for many pathologies that limit human lifespan, including cardiovascular diseases. Biological ageing is a good biomarker to assess early individual risk for CVD. However, finding good measurements of biological ageing is an ongoing quest. This study aims to assess the use retinal microvascular function, separate or in combination with telomere length, as a predictor for age and systemic blood pressure in individuals with low cardiovascular risk. In all, 123 healthy participants with low cardiovascular risk were recruited and divided into three groups: group 1 (less than 30 years old), group 2 (31-50 years old) and group 3 (over 50 years old). Relative telomere length (RTL), parameters of retinal microvascular function, CVD circulatory markers and blood pressure (BP) were measured in all individuals. Symbolic regression- analysis was used to infer chronological age and systemic BP measurements using either RTL or a combination of RTL and parameters for retinal microvascular function. RTL decreased significantly with age (p = 0.010). There were also age-related differences between the study groups in retinal arterial time to maximum dilation (p = 0.005), maximum constriction (p = 0.007) and maximum constriction percentage (p = 0.010). In the youngest participants, the error between predicted versus actual values for the chronological age were smallest in the case of using both retinal vascular functions only (p = 0.039) or the combination of this parameter with RTL (p = 0.0045). Systolic BP was better predicted by RTL also only in younger individuals (p = 0.043). The assessment of retinal arterial vascular function is a better predictor than RTL for non-modifiable variables such as age, and only in younger individuals. In the same age group, RTL is better than microvascular function when inferring modifiable risk factors for CVDs. In older individuals, the accumulation of physiological and structural biological changes makes such predictions unreliable.

A study on CNN image classification of EEG signals represented in 2D and 3D.

Objective.The novelty of this study consists of the exploration of multiple new approaches of data pre-processing of brainwave signals, wherein statistical features are extracted and then formatted as visual images based on the order in which dimensionality reduction algorithms select them. This data is then treated as visual input for 2D and 3D convolutional neural networks (CNNs) which then further extract 'features of features'.Approach.Statistical features derived from three electroencephalography (EEG) datasets are presented in visual space and processed in 2D and 3D space as pixels and voxels respectively. Three datasets are benchmarked, mental attention states and emotional valences from the four TP9, AF7, AF8 and TP10 10-20 electrodes and an eye state data from 64 electrodes. Seven hundred twenty-nine features are selected through three methods of selection in order to form 27 × 27 images and 9 × 9 × 9 cubes from the same datasets. CNNs engineered for the 2D and 3D preprocessing representations learn to convolve useful graphical features from the data.Main results.A 70/30 split method shows that the strongest methods for classification accuracy of feature selection are One Rule for attention state and Relative Entropy for emotional state both in 2D. In the eye state dataset 3D space is best, selected by Symmetrical Uncertainty. Finally, 10-fold cross validation is used to train best topologies. Final best 10-fold results are 97.03% for attention state (2D CNN), 98.4% for Emotional State (3D CNN), and 97.96% for Eye State (3D CNN).Significance.The findings of the framework presented by this work show that CNNs can successfully convolve useful features from a set of pre-computed statistical temporal features from raw EEG waves. The high performance of K-fold validated algorithms argue that the features learnt by the CNNs hold useful knowledge for classification in addition to the pre-computed features.

Country-level pandemic risk and preparedness classification based on COVID-19 data: A machine learning approach.

In this work we present a three-stage Machine Learning strategy to country-level risk classification based on countries that are reporting COVID-19 information. A K% binning discretisation (K = 25) is used to create four risk groups of countries based on the risk of transmission (coronavirus cases per million population), risk of mortality (coronavirus deaths per million population), and risk of inability to test (coronavirus tests per million population). The four risk groups produced by K% binning are labelled as 'low', 'medium-low', 'medium-high', and 'high'. Coronavirus-related data are then removed and the attributes for prediction of the three types of risk are given as the geopolitical and demographic data describing each country. Thus, the calculation of class label is based on coronavirus data but the input attributes are country-level information regardless of coronavirus data. The three four-class classification problems are then explored and benchmarked through leave-one-country-out cross validation to find the strongest model, producing a Stack of Gradient Boosting and Decision Tree algorithms for risk of transmission, a Stack of Support Vector Machine and Extra Trees for risk of mortality, and a Gradient Boosting algorithm for the risk of inability to test. It is noted that high risk for inability to test is often coupled with low risks for transmission and mortality, therefore the risk of inability to test should be interpreted first, before consideration is given to the predicted transmission and mortality risks. Finally, the approach is applied to more recent risk levels to data from September 2020 and weaker results are noted due to the growth of international collaboration detracting useful knowledge from country-level attributes which suggests that similar machine learning approaches are more useful prior to situations later unfolding.

British Sign Language Recognition via Late Fusion of Computer Vision and Leap Motion with Transfer Learning to American Sign Language.

In this work, we show that a late fusion approach to multimodality in sign language recognition improves the overall ability of the model in comparison to the singular approaches of image classification (88.14%) and Leap Motion data classification (72.73%). With a large synchronous dataset of 18 BSL gestures collected from multiple subjects, two deep neural networks are benchmarked and compared to derive a best topology for each. The Vision model is implemented by a Convolutional Neural Network and optimised Artificial Neural Network, and the Leap Motion model is implemented by an evolutionary search of Artificial Neural Network topology. Next, the two best networks are fused for synchronised processing, which results in a better overall result (94.44%) as complementary features are learnt in addition to the original task. The hypothesis is further supported by application of the three models to a set of completely unseen data where a multimodality approach achieves the best results relative to the single sensor method. When transfer learning with the weights trained via British Sign Language, all three models outperform standard random weight distribution when classifying American Sign Language (ASL), and the best model overall for ASL classification was the transfer learning multimodality approach, which scored 82.55% accuracy.

Ageing effect on flicker-induced diameter changes in retinal microvessels of healthy individuals.

PURPOSE: To compare flicker-induced retinal vessel diameter changes in varying age groups with low cardiovascular risk. METHODS: Retinal vascular reactivity to flicker light was assessed by means of dynamic retinal vessel analysis in 57 participants aged 19-30 years, 75 participants aged 31-50 years and 62 participants aged 51-70 years participants. Other assessments included carotid intima-media thickness (c-IMT), augmentation index (AIx), blood pressure profiles, blood lipid metabolism markers and Framingham risk scores (FRS). RESULTS: Retinal arterial dilation amplitude (DA) and postflicker percentage constriction (MC%) were significantly decreased in the oldest group compared to the middle-aged (p = 0.028; p = 0.021) and youngest group (p = 0.003; p = 0.026). The arterial constriction slope (SlopeAC ) was also decreased in the oldest group compared to the youngest group (p = 0.027). On the venous side, MC% was decreased in the middle-aged and oldest groups in comparison with the youngest group (p = 0.015; p = 0.010, respectively). Additionally, men exhibited increased arterial DA (p = 0.007), and percentage dilation (MD%, p < 0.001) in comparison with women, but only in the youngest age group. Both AIx and c-IMT scores increased with age (both p < 0.001); however, no correlations were found between the observed differences in the measured retinal vascular function and systemic parameters. CONCLUSION: In individuals with low cardiovascular risk, there are age-related differences in flicker-induced retinal vessel diameter changes throughout the entire functional response curve for arteries and veins. Gender differences mainly affect the arterial dilatory phase and are only present in young individuals.

Systemic circulatory influences on retinal microvascular function in middle-age individuals with low to moderate cardiovascular risk.

PURPOSE: To investigate the relationship between retinal microvascular reactivity, circulatory markers for CVD risk and systemic antioxidative defence capacity in healthy middle-aged individuals with low to moderate risk of CVD. METHODS: Retinal vascular reactivity to flickering light was assessed in 102 healthy participants (46-60 years) by means of dynamic retinal vessel analysis (DVA). Other vascular assessments included carotid intima-media thickness (C-IMT) and blood pressure (BP) measurements. Total cholesterol (CHOL), high-density lipoprotein cholesterol (HDL-C), low-density lipoprotein cholesterol (LDL-C), triglycerides (TG) and blood glutathione levels in its reduced (GSH) and oxidized (GSSG) forms were also determined for each participant, along with Framingham risk scores (FRS). RESULTS: Retinal arterial baseline diameter fluctuation (BDF) was independently, significantly and negatively influenced by LDL-C levels (ß = -0.53, p = 0.027). Moreover, the arterial dilation slope (SlopeAD ) was independently, significantly and positively associated with redox index (GSH: GSSG ratio, ß = 0.28, p = 0.016), while the arterial constriction slope (SlopeAC ) was significantly and negatively influenced by blood GSH levels (ß = -0.20, p = 0.042), and positively associated with FRS (ß = 0.25, p = 0.009). Venous BDF and dilation amplitude (DA) were also negatively influenced by plasma LDL-C levels (ß = -0.83, p = 0.013; and ß = -0.22, p = 0.028, respectively). CONCLUSIONS: In otherwise healthy individuals with low to moderate cardiovascular risk, retinal microvascular dilation and constriction responses to stress levels are influenced by systemic antioxidant capacity, and circulating markers for cardiovascular risk.

Patients with early age-related macular degeneration exhibit signs of macro- and micro-vascular disease and abnormal blood glutathione levels.

BACKGROUND: This pilot study aimed to investigate systemic and retinal vascular function and their relationship to circulatory markers of cardiovascular risk in early age-related macular degeneration (AMD) patients without any already diagnosed systemic vascular pathologies. METHODS: Fourteen patients diagnosed with early AMD and 14 age- and gender-matched healthy controls underwent blood pressure, carotid intima-media thickness (C-IMT) and peripheral arterial stiffness measurements. Retinal vascular reactivity was assessed by means of dynamic retinal vessel analysis (DVA) using a modified protocol. Blood analyses were conducted for glutathione levels and plasma levels of total cholesterol (CHOL), high-density lipoprotein cholesterol (HDL-C), low-density lipoprotein cholesterol (LDL-C) and triglycerides (TG). RESULTS: The AMD patients showed significantly greater C-IMT (p = 0.029) and augmentation index (AIx) (p = 0.042) than the age-matched controls. In addition, they demonstrated a shallower retinal arterial dilation slope (Slope AD) (p = 0.005) and a longer retinal venous reaction time (RT) to flickering light (p = 0.026). Blood analyses also revealed that AMD patients exhibited higher oxidized glutathione (GSSG) (p = 0.024), lower redox index (p = 0.043) and higher LDL-C (p = 0.033) levels than the controls. Venous RT parameter correlated positively with blood GSSG levels (r = 0.58, p = 0.038) in AMD subjects, but not in the controls (p > 0.05). CONCLUSIONS: Patients diagnosed with early AMD exhibit signs of systemic and retinal vascular alterations that correlated with known risk markers for future cardiovascular morbidity.

Coexistence of macro- and micro-vascular abnormalities in newly diagnosed normal tension glaucoma patients.

PURPOSE: To investigate the coexistence of ocular microvascular and systemic macrovascular abnormalities in early stage, newly diagnosed and previously untreated normal tension glaucoma patients (NTG). METHODS: Retinal vascular reactivity to flickering light was assessed in 19 NTG and 28 age-matched controls by means of dynamic retinal vessel analysis (IMEDOS GmbH, Jena, Germany). Using a newly developed computational model, the entire dynamic vascular response profile to flicker light was imaged and used for analysis. In addition, assessments of carotid intima-media thickness (IMT) and pulse wave analysis (PWA) were conducted on all participants, along with blood pressure (BP) measurements and blood analyses for lipid metabolism markers. RESULTS: Patients with NTG demonstrated an increased right and left carotid IMT (p = 0.015, p = 0.045) and an elevated PWA augmentation index (p = 0.017) in comparison with healthy controls, along with an enhanced retinal arterial constriction response (p = 0.028), a steeper retinal arterial constriction slope (p = 0.031) and a reduced retinal venous dilation response (p = 0.026) following flicker light stimulation. CONCLUSIONS: Early stage, newly diagnosed, NTG patients showed signs of subclinical vascular abnormalities at both macro- and micro-vascular levels, highlighting the need to consider multi-level circulation-related pathologies in the development and progression of this type of glaucoma.