Dimitrios Tsalikakis

Atrial fibrillation (AF) is the most common sustained arrhythmia and a growing global health burden, yet conventional monitoring with Holter devices, event recorders and implantable loop recorders often fails to adequately capture recurrence. Rapid advances in digital health, wearable biosensors and artificial intelligence (AI) have transformed consumer smartwatches and wearables into potential clinical tools capable of continuous, real-world rhythm surveillance. This narrative review synthesizes contemporary evidence on smartwatch-based AF monitoring, spanning core technologies—photoplethysmography, single-lead electrocardiography and AI fusion algorithms—and validation studies across post-ablation follow-up. Compared with traditional modalities, smartwatch-based AF monitoring demonstrates improved detection of AF recurrence, enhanced characterization of AF burden, symptom–rhythm correlation, and greater patient engagement. At the same time, key limitations are critically examined, including motion artifacts, false-positive alerts, short recording windows, adherence dependence, digital literacy and access gaps, as well as unresolved issues around regulation, interoperability and data privacy. By integrating engineering advances with guideline-directed care pathways, smartwatch-based AF monitoring holds promise to complement, rather than immediately replace, established diagnostic tools and to enable more proactive, individualized AF management. Future work must focus on robust clinical validation, equitable implementation and clear regulatory frameworks to safely scale these technologies.

A multitude of problems in the contemporary literature are addressed using machine learning models, the most widespread of which are artificial neural networks. Furthermore, in recent years, evolutionary techniques have emerged that identify both the architecture of artificial neural networks and their corresponding parameters. Among these techniques, one can also identify the artificial neural networks being constructed, in which the structure and parameters of the neural network are effectively identified using Grammatical Evolution. In this work, a pre-training stage is introduced in which an artificial neural network with a fixed number of parameters is trained using some optimization technique such as the genetic algorithms used here. The final result of this additional phase is a trained artificial neural network, which is introduced into the genetic population used by Grammatical Evolution in the second phase. In this way, finding the overall minimum of the error function will be significantly accelerated, making the second phase method more efficient. The current work was applied to many classification and regression problems found in the related literature, and it was compared against other methods used for neural network training as well as against the original method used to construct neural networks.

Radial basis function (RBF) networks are an established parametric machine learning tool which has been extensively utilized in data classification and data fitting problems. These specific machine learning tools have been applied in various scientific areas, such as problems in physics, chemistry, and medicine, with excellent results. A two-step technique is usually used to adjust the parameters of these models, which is in most cases extremely effective. However, it does not effectively explore the value space of the network parameters and often results in parameter stability problems. In this paper, the use of a bounding technique that explores the value space of the parameters of these networks using intervals generated by a procedure based on the Simulated Annealing method is recommended. After finding a promising range of values for the network parameters, a genetic algorithm is applied within this range of values to more effectively adjust its parameters. The new method was applied on a wide range of classification and regression datasets from the relevant literature and the results are reported in the current manuscript.

Artificial neural networks are widely established models used to solve a variety of real-world problems in the fields of physics, chemistry, etc. These machine learning models contain a series of parameters that must be appropriately tuned by various optimization techniques in order to effectively address the problems that they face. Genetic algorithms have been used in many cases in the recent literature to train artificial neural networks, and various modifications have been made to enhance this procedure. In this article, the incorporation of a novel genetic operator into genetic algorithms is proposed to effectively train artificial neural networks. The new operator is based on the differential evolution technique, and it is periodically applied to randomly selected chromosomes from the genetic population. Furthermore, to determine a promising range of values for the parameters of the artificial neural network, an additional genetic algorithm is executed before the execution of the basic algorithm. The modified genetic algorithm is used to train neural networks on classification and regression datasets, and the results are reported and compared with those of other methods used to train neural networks.

Artificial neural networks are widely used in applications from various scientific fields and in a multitude of practical applications. In recent years, a multitude of scientific publications have been presented on the effective training of their parameters, but in many cases overfitting problems appear, where the artificial neural network shows poor results when used on data that were not present during training. This text proposes the incorporation of a three-stage evolutionary technique, which has roots in the differential evolution technique, for the effective training of the parameters of artificial neural networks and the avoidance of the problem of overfitting. The new method effectively constructs the parameter value range of the artificial neural network with one processing level and sigmoid outputs, both achieving a reduction in training error and preventing the network from experiencing overfitting phenomena. This new technique was successfully applied to a wide range of problems from the relevant literature and the results were extremely promising. From the conducted experiments, it appears that the proposed method reduced the average classification error by 30%, compared to the genetic algorithm, and the average regression error by 45%, as compared to the genetic algorithm.

The presented work outlines a new genetic crossover operator, which can be used to solve problems by the Grammatical Evolution technique. This new operator intensively applies the one-point crossover procedure to randomly selected chromosomes with the aim of drastically reducing their fitness value. The new operator is applied to chromosomes selected randomly from the genetic population. This new operator was applied to two techniques from the recent literature that exploit Grammatical Evolution: artificial neural network construction and rule construction. In both case studies, an extensive set of classification problems and data-fitting problems were incorporated to estimate the effectiveness of the proposed genetic operator. The proposed operator significantly reduced both the classification error on the classification datasets and the feature learning error on the fitting datasets compared to other machine learning techniques and also to the original models before applying the new operator.

Constructed neural networks with the assistance of grammatical evolution have been widely used in a series of classification and data-fitting problems recently. Application areas of this innovative machine learning technique include solving differential equations, autism screening, and measuring motor function in Parkinson’s disease. Although this technique has given excellent results, in many cases, it is trapped in local minimum and cannot perform satisfactorily in many problems. For this purpose, it is considered necessary to find techniques to avoid local minima, and one technique is the periodic application of local minimization techniques that will adjust the parameters of the constructed artificial neural network while maintaining the already existing architecture created by grammatical evolution. The periodic application of local minimization techniques has shown a significant reduction in both classification and data-fitting problems found in the relevant literature.

Atrial fibrillation (AF) is the most prevalent arrhythmia among adults worldwide, frequently co-occurring with comorbidities such as Heart Failure (HF) and Type 2 Diabetes Mellitus (T2DM). This association contributes to increased morbidity and mortality, elevated healthcare costs, and diminished quality of life. Consequently, preventing or delaying the onset and recurrence of AF is crucial for reducing the incidence of complications. Sodium-glucose cotransporter 2 inhibitors (SGLT2is), due to their multifaceted pharmacological actions, have been proposed as potential therapeutic agents in the management of AF. However, current evidence from both animal models and clinical studies remains inconclusive. This narrative literature review aims to provide a comprehensive analysis of existing evidence on the impact of SGLT2is on the prevalence, incidence of new-onset, and recurrence of AF in diabetic populations and patients with HF. Numerous observational studies, predominantly retrospective, suggest a consistent reduction in AF risk with SGLT2is, while randomized controlled trials (RCTs) have yielded mixed results, with some demonstrating benefits and others not reaching statistical significance. The heterogeneity in study outcomes, population characteristics, follow-up duration, and specific SGLT2is used, as well as potential biases, underscore the need for further extensive and rigorous RCTs to establish definitive conclusions and elucidate the underlying mechanisms.

In this paper, an innovative hybrid technique is proposed for the efficient training of artificial neural networks, which are used both in class learning problems and in data fitting problems. This hybrid technique combines the well-tested technique of Genetic Algorithms with an innovative variant of Simulated Annealing, in order to achieve high learning rates for the neural networks. This variant was applied periodically to randomly selected chromosomes from the population of the Genetic Algorithm in order to reduce the training error associated with these chromosomes. The proposed method was tested on a wide series of classification and data fitting problems from the relevant literature and the results were compared against other methods. The comparison with other neural network training techniques as well as the statistical comparison revealed that the proposed method is significantly superior, as it managed to significantly reduce the neural network training error in the majority of the used datasets.