Artificial Intelligence (AI) methodologies have profoundly influenced healthcare research, particularly in chronic disease management and public health. This paper provides a comprehensive state-of-the-art review of AI’s applications across diabetes, cancer, epidemiology, and mortality prediction. The analysis highlights advancements in machine learning (ML), deep learning (DL), and natural language processing (NLP) that enable robust predictive models and decision support systems, leading to significant clinical and public health outcomes. The study examines predictive modeling, pattern recognition, and decision support applications, addressing their respective challenges and potential in real-world healthcare settings. Emphasis is placed on the emerging role of explainable AI (XAI), multimodal data fusion, and privacy-preserving techniques such as federated learning, which aim to enhance interpretability, robustness, and ethical compliance. This paper underscores the vital role of interdisciplinary collaboration and adaptive AI systems in creating resilient, scalable, and patient-centric healthcare solutions.
1 January 2016 in Computational Intelligence and Neuroscience
We introduce a lexical resource for preprocessing social media data. We show that a neural network-based feature representation is enhanced by using this resource. We conducted experiments on the PAN 2015 and PAN 2016 author profiling corpora and obtained better results when performing the data preprocessing using the developed lexical resource. The resource includes dictionaries of slang words, contractions, abbreviations, and emoticons commonly used in social media. Each of the dictionaries was built for the English, Spanish, Dutch, and Italian languages. The resource is freely available.
Mikhail Krasitskii, Olga Kolesnikova, Liliana Chanona Hernandez, Grigori Sidorov, Alexander Gelbukh. Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities. 2025.
Reclassification of massive datasets acquired through different approaches, such as web scraping, is a big challenge to demonstrate the effectiveness of a machine learning model. Notably, there is a strong influence of the quality of the dataset used for training those models. Thus, we propose a threshold algorithm as an efficient method to remove stopwords. This method employs an unsupervised classification technique, such as K-means, to accurately categorize user reviews from the IMDb dataset into their most suitable categories, generating a well-balanced dataset. Analysis of the performance of the algorithm revealed a notable influence of the text vectorization method used concerning the generation of clusters when assessing various preprocessing approaches. Moreover, the algorithm demonstrated that the word embedding technique and the removal of stopwords to retrieve the clustered text significantly impacted the categorization. The proposed method involves confirming the presence of a suggested stopword within each review across various genres. Upon satisfying this condition, the method assesses if the word’s frequency exceeds a predefined threshold. The threshold algorithm yielded a mapping genre success above 80% compared to precompiled lists and a Zipf’s law-based method. In addition, we employed the mini-batch K-means method for the clustering formation of each differently preprocessed dataset. This approach enabled us to reclassify reviews more coherently. Summing up, our methodology categorizes sparsely labeled data into meaningful clusters, in particular, by using a combination of the proposed stopword removal method and TF-IDF. The reclassified and balanced datasets showed a significant improvement, achieving 94% accuracy compared to the original dataset.
In Mexico, according to data from the General Directorate of Health Information (2018), there is an annual incidence of 689 newborns with Trisomy 21, well-known as Down Syndrome. Worldwide, this incidence is estimated between 1 in every 1000 newborns, approximately. That is why this work focuses on the detection and analysis of facial emotions in children with Down Syndrome in order to predict their emotions throughout a dolphin-assisted therapy. In this work, two databases are used: Exploratory Data Analysis, with a total of 20,214 images, and the Down’s Syndrome Dataset database, with 1445 images for training, validation, and testing of the neural network models. The construction of two architectures based on a Deep Convolutional Neural Network manages an efficiency of 79%, when these architectures are tested with a large reference image database. Then, the architecture that achieves better results is trained, validated, and tested in a small-image database with the facial emotions of children with Down Syndrome, obtaining an efficiency of 72%. However, this increases by 9% when the brain activity of the child is included in the training, resulting in an average precision of 81%. Using electroencephalogram (EEG) signals in a Convolutional Neural Network (CNN) along with the Down’s Syndrome Dataset (DSDS) has promising advantages in the field of brain–computer interfaces. EEG provides direct access to the electrical activity of the brain, allowing for real-time monitoring and analysis of cognitive states. Integrating EEG signals into a CNN architecture can enhance learning and decision-making capabilities. It is important to note that this work has the primary objective of addressing a doubly vulnerable population, as these children also have a disability.
There are several pathologies attacking the central nervous system and diverse therapies for each specific disease. These therapies seek as far as possible to minimize or offset the consequences caused by these types of pathologies and disorders in the patient. Therefore, comprehensive neurological care has been performed by neurorehabilitation therapies, to improve the patients’ life quality and facilitating their performance in society. One way to know how the neurorehabilitation therapies contribute to help patients is by measuring changes in their brain activity by means of electroencephalograms (EEG). EEG data-processing applications have been used in neuroscience research to be highly computing- and data-intensive. Our proposal is an integrated system of Electroencephalographic, Electrocardiographic, Bioacoustic, and Digital Image Acquisition Analysis to provide neuroscience experts with tools to estimate the efficiency of a great variety of therapies. The three main axes of this proposal are: parallel or distributed capture, filtering and adaptation of biomedical signals, and synchronization in real epochs of sampling. Thus, the present proposal underlies a general system, whose main objective is to be a wireless benchmark in the field. In this way, this proposal could acquire and give some analysis tools for biomedical signals used for measuring brain interactions when it is stimulated by an external system during therapies, for example. Therefore, this system supports extreme environmental conditions, when necessary, which broadens the spectrum of its applications. In addition, in this proposal sensors could be added or eliminated depending on the needs of the research, generating a wide range of configuration limited by the number of CPU cores, i.e., the more biosensors, the more CPU cores will be required. To validate the proposed integrated system, it is used in a Dolphin-Assisted Therapy in patients with Infantile Cerebral Palsy and Obsessive–Compulsive Disorder, as well as with a neurotypical one. Event synchronization of sample periods helped isolate the same therapy stimulus and allowed it to be analyzed by tools such as the Power Spectrum or the Fractal Geometry.