Atrial Fibrillation and Early Vascular Aging: Clinical Implications, Methodology Issues and Open Questions-A Review from the VascAgeNet COST Action.

Atrial fibrillation (AF), the most common cardiac arrhythmia, is associated with adverse CV outcomes. Vascular aging (VA), which is defined as the progressive deterioration of arterial function and structure over a lifetime, is an independent predictor of both AF development and CV events. A timing identification and treatment of early VA has therefore the potential to reduce the risk of AF incidence and related CV events. A network of scientists and clinicians from the COST Action VascAgeNet identified five clinically and methodologically relevant questions regarding the relationship between AF and VA and conducted a narrative review of the literature to find potential answers. These are: (1) Are VA biomarkers associated with AF? (2) Does early VA predict AF occurrence better than chronological aging? (3) Is early VA a risk enhancer for the occurrence of CV events in AF patients? (4) Are devices measuring VA suitable to perform subclinical AF detection? (5) Does atrial-fibrillation-related rhythm irregularity have a negative impact on the measurement of vascular age? Results showed that VA is a powerful and independent predictor of AF incidence, however, its role as risk modifier for the occurrence of CV events in patients with AF is debatable. Limited and inconclusive data exist regarding the reliability of VA measurement in the presence of rhythm irregularities associated with AF. To date, no device is equipped with tools capable of detecting AF during VA measurements. This represents a missed opportunity to effectively perform CV prevention in people at high risk. Further advances are needed to fill knowledge gaps in this field.

Applying Image-Based Food-Recognition Systems on Dietary Assessment: A Systematic Review.

Dietary assessment can be crucial for the overall well-being of humans and, at least in some instances, for the prevention and management of chronic, life-threatening diseases. Recall and manual record-keeping methods for food-intake monitoring are available, but often inaccurate when applied for a long period of time. On the other hand, automatic record-keeping approaches that adopt mobile cameras and computer vision methods seem to simplify the process and can improve current human-centric diet-monitoring methods. Here we present an extended critical literature overview of image-based food-recognition systems (IBFRS) combining a camera of the user's mobile device with computer vision methods and publicly available food datasets (PAFDs). In brief, such systems consist of several phases, such as the segmentation of the food items on the plate, the classification of the food items in a specific food category, and the estimation phase of volume, calories, or nutrients of each food item. A total of 159 studies were screened in this systematic review of IBFRS. A detailed overview of the methods adopted in each of the 78 included studies of this systematic review of IBFRS is provided along with their performance on PAFDs. Studies that included IBFRS without presenting their performance in at least 1 of the above-mentioned phases were excluded. Among the included studies, 45 (58%) studies adopted deep learning methods and especially convolutional neural networks (CNNs) in at least 1 phase of the IBFRS with input PAFDs. Among the implemented techniques, CNNs outperform all other approaches on the PAFDs with a large volume of data, since the richness of these datasets provides adequate training resources for such algorithms. We also present evidence for the benefits of application of IBFRS in professional dietetic practice. Furthermore, challenges related to the IBFRS presented here are also thoroughly discussed along with future directions.

Design and Development of a Sitting Posture Recognition System.

Sitting posture recognition can be used to evaluate the awareness of a person carrying out a task, such as working or driving, and can aid in avoiding accidents or other health risks, such as musculoskeletal disorders. In addition, sitting posture can reveal wellness or unhealthiness for the elderly and mobility disabled individuals. This paper focuses on body posture monitoring, by acquiring the pressure distribution of a sitting person with thirteen piezoresistive sensors placed on a seat. The measurements from the sensors passing through a microcontroller unit fed several machine learning techniques in order to discriminate among five sitting postures (upright, leaning left, leaning right, leaning forward and leaning backward). Experiments with body postures from twelve individuals (six men and six women) of different Body Mass Index (underweight, normal and overweight) were conducted. The developed classifiers achieved average discrimination accuracy over 98% among the aforementioned five body postures.