In recent years, artificial intelligence has begun to play a salient role in various medical fields, including ophthalmology. This extensive review is addressed to ophthalmologists and aims to capture the current landscape and future potential of AI applications for eye health. From automated retinal screening processes and machine learning models predicting the progression of ocular conditions to AI-driven decision support systems in clinical settings, this paper provides a comprehensive overview of the clinical implications of AI in ophthalmology. The development of AI has opened new horizons for ophthalmology, offering innovative solutions to improve the accuracy and efficiency of ocular disease diagnosis and management. The importance of this paper lies in its potential to strengthen collaboration between researchers, ophthalmologists, and AI specialists, leading to transformative findings in the early identification and treatment of eye diseases. By combining AI potential with cutting-edge imaging methods, novel biomarkers, and data-driven approaches, ophthalmologists can make more informed decisions and provide personalized treatment for their patients. Furthermore, this paper emphasizes the translation of basic research outcomes into clinical applications. We do hope this comprehensive review will act as a significant resource for ophthalmologists, researchers, data scientists, healthcare professionals, and managers in the healthcare system who are interested in the application of artificial intelligence in eye health.

The paper proposes a comparative analysis of the projection matrices and dictionaries used for compressive sensing (CS) of electrocardiographic signals (ECG), highlighting the compromises between the complexity of preprocessing and the accuracy of reconstruction. Starting from the basic notions of CS theory, this paper proposes the construction of dictionaries (constructed directly by cardiac patterns with R-waves, centered or not-centered) specific to the application and the results of their testing. Several types of projection matrices are also analyzed and discussed. The reconstructed signals are analyzed quantitatively and qualitatively by standard distortion measures and by the classification of the reconstructed signals. We used a k-nearest neighbors (KNN) classifier to evaluate the reconstructed models. The KNN module was trained with the models from the mega-dictionary used in the classification block and tested with the models reconstructed with class-specific dictionaries. In addition to the KNN classifier, a neural network was used to test the reconstructed signals. The neural network was a multilayer perceptron (MLP). Moreover, the results are compared with those obtained with other compression methods, and ours proved to be superior.

Classification performances for some classes of electrocardiographic (ECG) and electroencephalographic (EEG) signals processed to dimensionality reduction with different degrees are investigated. Results got with various classification methods are given and discussed. So far we investigated three techniques for reducing dimensionality: Laplacian eigenmaps (LE), locality preserving projections (LPP) and compressed sensing (CS). The first two methods are related to manifold learning while the third addresses signal acquisition and reconstruction from random projections under the supposition of signal sparsity. Our aim is to evaluate the benefits and drawbacks of various methods and to find to what extent they can be considered remarkable. The assessment of the effect of dimensionality decrease was made by considering the classification rates for the processed biosignals in the new spaces. Besides, the classification accuracies of the initial input data were evaluated with respect to the corresponding accuracies in the new spaces using different classifiers.

This paper analyzes two main categories of feature selection: filter methods (such as minimum redundancy maximum relevance, CHI2, Kruskal–Wallis, and ANOVA) and embedded methods (such as alternating direction method of multipliers (BP_ADMM), least absolute shrinkage and selection operator, and orthogonal matching pursuit). The mathematical foundations of feature selection methods inspired by compressed detection are presented, highlighting how the principles of sparse signal recovery can be applied to identify the most relevant features. The results have been obtained using two biomedical databases. The used algorithms have, as their starting point, the notion of sparsity, but the version implemented and tested in this work is adapted for feature selection. The experimental results show that BP_ADMM achieves the highest classification accuracy (77% for arrhythmia_database and 100% for oncological_database), surpassing both the full feature set and the other methods tested in this study, which makes it the optimal feature selection option. The analysis shows that embedded methods strike a balance between accuracy and efficiency by selecting features during the model training, unlike filtering methods, which ignore feature interactions. Although more accurate, embedded methods are slower and depend on the chosen algorithm. Although less comprehensive than wrapper methods, they offer a strong trade-off between speed and performance when computational resources allow for it.

We analyzed the possibility of detecting and predicting ventricular fibrillation (VF), a medical emergency that may put people’s lives at risk, as the medical prognosis depends on the time in which medical personnel intervene. Therefore, besides immediate detection of VF, the possibility of predicting VF 40 or even 50 min in advance was analyzed. For testing the proposed algorithm, we used ECG signals taken from the MIT-BIH database, namely, Malignant Ventricular Ectopy Database, Sudden Cardiac Death Holter Database and Normal Sinus Rhythm Database. The presented method is based on features extracted from the ECG signals in the time domain, frequency domain and complexity measures. For VF detection, the possibility of identifying the VF episode in the first 3 s after its occurrence was tested. For this, the first 3 s immediately after the appearance of VF were cut out and the features were computed on these sections. For VF prediction, 3 min of the ECG signal clipped 40 or 50 min before VF onset was used. Then, on these pieces of ECG signal, the specific features were calculated for 1 s segments. For the normal signal situation, 3 min was randomly selected from the database with normal ECGs. For the classification or detection stage, both an MLP-type neural network and the classifiers from the Machine Learning toolbox of the MATLAB^® environment were used. The results obtained for both detection and classification are over 94% in both cases. The novelty of our results compared to those previously obtained is the time interval with which the possibility of prediction was analyzed, namely, 50 min in advance of the VF installation date. This means that the patient will be informed that it is possible to suffer a VF and has time to take the necessary measures to overcome a possible medical emergency.

This review offers a detailed examination of modern ECG signal processing techniques employed in the prediction and detection of ventricular fibrillation (VF). It contains a thorough analysis of recent advancements in the field, exploring the strengths, limitations, and real-world applications of these techniques. By evaluating the current state of research, the review seeks to identify the most effective approaches and highlight key areas where further investigation is needed, ultimately guiding future research efforts toward improving VF prediction and detection. Overall, AI has shown significant potential in a range of VF-related tasks. However, real-world implementation encounters several challenges, including difficulties in accurately interpreting ECG signals, the variability in individual physiological responses, and the infrequency of ventricular fibrillation events. Additionally, there are issues related to the critical timing required for detecting VF, the presence of similar arrhythmias, the need for adaptation to new ECG devices, energy consumption concerns, and the complex process of obtaining regulatory and legislative approvals for integrating software components into medical equipment. We consider that the present work might be useful in approaching the above challenges.