Digital transformation is reshaping the healthcare field by streamlining diagnostic workflows and improving disease management. Within this transformation, Digital Twins (DTs), which are virtual representations of physical systems continuously updated by real-world data, stand out for their ability to capture the complexity of human physiology and behavior. When coupled with Artificial Intelligence (AI), DTs enable data-driven experimentation, precise diagnostic support, and predictive modeling without posing direct risks to patients. However, their integration into healthcare requires careful consideration of ethical, regulatory, and safety constraints in light of the sensitivity and nonlinear nature of human data. In this review, we examine recent progress in DTs over the past seven years and explore broader trends in AI-augmented DTs, focusing particularly on movement rehabilitation. Our goal is to provide a comprehensive understanding of how DTs bolstered by AI can transform healthcare delivery, medical research, and personalized care. We discuss implementation challenges such as data privacy, clinical validation, and scalability along with opportunities for more efficient, safe, and patient-centered healthcare systems. By addressing these issues, this review highlights key insights and directions for future research to guide the proactive and ethical adoption of DTs in healthcare.

Plants have mechanisms to perceive and transmit information between their organs and tissues to respond quickly to abiotic and biotic external stimuli from the environment, producing different electrical potential types. It is reported on the generation and conduction of electrochemical impulses within different tissues and organs of the plant, which have been acquired using different methods to use them in various applications in the improvement of the agro-industrial sector and the development of different types of phytosensors. In this review paper, the various studies that have been carried out since Pfeffer, Burdon-Sanderson, Darwin, Haberlandt, and Bose discovered electrical activity in plants until today are reported. Plants provide mechanisms to perform biosensors based on responding to environmental changes, opening a great path for the design of low-cost and highly sensitive sensors and sensor networks, the current trend is towards experimental analysis using various stimuli.

The function of the back, hip, knee, ankle and other orthopedic alterations of the human body can be analyzed through plantar pressure distribution. The development of Clinical Decision Support Systems (CDSS) can handle the uncertainties present in biological data using different Artificial Intelligence techniques to obtain accurate and easy-to-use systems. This paper presents the application of a Fuzzy Cognitive Map (FCM) formulation, for knowledge extraction in the classification of human plantar foot alterations, with a relatively small and transparent model. The FCM is trained using the Bacterial Search Optimization Algorithm (BFOA). One hundred and twenty-five volunteer subjects (aged 20-68 years) participated in the study. Classification of the foot into normal (n=31), flat (n=32), cavus type III (n=31) and cavus type IV (n=31) to train the system was performed by specialized physicians. The test was performed by walking on a FreeMed platform. The proposed method shows an accuracy rate of about 89% in the classification task and allows extracting information related to the important factors that the system considers to make a decision.

This article presents a progressive compensation strategy for gait recovery in patients with different degrees of limited knee mobility, based on angular analysis and muscle electrical activity, and artificial intelligence. Ten subjects were tested during gait on a flat surface simulating 4 conditions of limited knee mobility with an active knee brace. Data on the amplitude of the electrical signal from 3 leg muscles were analyzed: rectus femoris, tibialis anterior, and gastrocnemius. In addition to the electromyography sensors, an angular position sensor was placed on the knee joint. An artificial neural network was trained to identify the type of limitation of each patient in their muscle activity. A knee orthosis with a linear actuator was designed to compensate for the loss of force during knee flexion-extension movement, according with limiting condition. The actuator trajectory is controlled through a model reference adaptive controller with a fuzzy logic-based adaptation mechanism. The simulation demonstrates the efficiency of this strategy, despite the high-amplitude disturbances in the system.

The health situation caused by the SARS-Cov2 coronavirus, posed major challenges for the scientific community. Advances in artificial intelligence are a very useful resource, but it is important to determine which symptoms presented by positive cases of infection are the best predictors. A machine learning approach was used with data from 5,434 people, with eleven symptoms: breathing problems, dry cough, sore throat, running nose, history of asthma, chronic lung, headache, heart disease, hypertension, diabetes, and fever. Based on public data from Kaggle with WHO standardized symptoms. A model was developed to detect COVID-19 positive cases using a simple machine learning model. The results of 4 loss functions and by SHAP values, were compared. The best loss function was Binary Cross Entropy, with a single hidden layer configuration with 10 neurons, achieving an F1 score of 0.98 and the model was rated with an area under the curve of 0.99 aucROC. La situación sanitaria provocada por el coronavirus SARS-Cov2 plantea grandes retos a la comunidad científica. Los avances en inteligencia artificial son un recurso muy útil, pero es importante determinar qué síntomas presentados por los casos positivos de infección son los mejores predictores. Se utilizó un enfoque de aprendizaje automático con datos de 5.434 personas, con once síntomas: problemas respiratorios, tos seca, dolor de garganta, secreción nasal, antecedentes de asma, pulmón crónico, dolor de cabeza, enfermedad cardíaca, hipertensión, diabetes y fiebre. Basado en datos públicos de Kaggle con síntomas estandarizados por la OMS. Se desarrolló un modelo para detectar los casos positivos de COVID-19 utilizando un modelo simple de aprendizaje automático. Se compararon los resultados de 4 funciones de pérdida y por valores SHAP. La mejor función de pérdida fue la Entropía Cruzada Binaria, con una configuración de una sola capa oculta con 10 neuronas, logrando una puntuación F1 de 0,98 y el modelo fue calificado con un área bajo la curva de 0,99 aucROC.