Artificial intelligence (AI) has emerged as a crucial tool in healthcare with the primary aim of improving patient outcomes and optimizing healthcare delivery. By harnessing machine learning algorithms, natural language processing, and computer vision, AI enables the analysis of complex medical data. The integration of AI into healthcare systems aims to support clinicians, personalize patient care, and enhance population health, all while addressing the challenges posed by rising costs and limited resources. As a subdivision of computer science, AI focuses on the development of advanced algorithms capable of performing complex tasks that were once reliant on human intelligence. The ultimate goal is to achieve human-level performance with improved efficiency and accuracy in problem-solving and task execution, thereby reducing the need for human intervention. Various industries, including engineering, media/entertainment, finance, and education, have already reaped significant benefits by incorporating AI systems into their operations. Notably, the healthcare sector has witnessed rapid growth in the utilization of AI technology. Nevertheless, there remains untapped potential for AI to truly revolutionize the industry. It is important to note that despite concerns about job displacement, AI in healthcare should not be viewed as a threat to human workers. Instead, AI systems are designed to augment and support healthcare professionals, freeing up their time to focus on more complex and critical tasks. By automating routine and repetitive tasks, AI can alleviate the burden on healthcare professionals, allowing them to dedicate more attention to patient care and meaningful interactions. However, legal and ethical challenges must be addressed when embracing AI technology in medicine, alongside comprehensive public education to ensure widespread acceptance.

Class imbalance is a prevalent challenge in machine learning that arises from skewed data distributions in one class over another, causing models to prioritize the majority class and underperform on the minority classes. This bias can significantly undermine accurate predictions in real-world scenarios, highlighting the importance of the robust handling of imbalanced data for dependable results. This study examines one such scenario of real-time monitoring systems for fall risk assessment in bedridden patients where class imbalance may compromise the effectiveness of machine learning. It compares the effectiveness of two resampling techniques, the Synthetic Minority Oversampling Technique (SMOTE) and SMOTE combined with Edited Nearest Neighbors (SMOTEENN), in mitigating class imbalance and improving predictive performance. Using a controlled sampling strategy across various instance levels, the performance of both methods in conjunction with decision tree regression, gradient boosting regression, and Bayesian regression models was evaluated. The results indicate that SMOTEENN consistently outperforms SMOTE in terms of accuracy and mean squared error across all sample sizes and models. SMOTEENN also demonstrates healthier learning curves, suggesting improved generalization capabilities, particularly for a sampling strategy with a given number of instances. Furthermore, cross-validation analysis reveals that SMOTEENN achieves higher mean accuracy and lower standard deviation compared to SMOTE, indicating more stable and reliable performance. These findings suggest that SMOTEENN is a more effective technique for handling class imbalance, potentially contributing to the development of more accurate and generalizable predictive models in various applications.

The occurrence of inpatient falls and new-onset seizures are common complications during hospital stays, posing risks to patient safety and potentially leading to prolonged hospital stays and further complications. Given the constraints on medical staff’s ability to provide constant monitoring due to their workload, the implementation of a sensor device equipped with machine learning capabilities to recognize and prevent these events becomes imperative. This study utilized data acquired through the Movella Xsens sensor, which detects real-time motions and 3D movements, in conjunction with the PyCaret machine-learning algorithm. Adult-sized and infant-sized mannequins were used to assess the algorithm’s ability in predicting specific movements associated with breathing, seizures, rolling to the right side, rolling to the left side, rolling off the bed from the left, and rolling off the bed from the right. The study achieved an overall 89% accuracy rate in detecting each specific movement using the combination of PyCaret and Xsens sensors. The application of PyCaret alongside Xsens sensors demonstrates promising results in accurately detecting movements, thereby mitigating falls and post-seizure complications in an inpatient setting, consequently improving patient safety. Further exploration of this technology holds the potential to revolutionize healthcare delivery by incorporating it into a trigger alert system capable of promptly warning medical staff of urgent situations through real-time capture and analysis of potentially harmful motions.

This study explores the influence of chinstrap stiffness in baseball helmets on brain stress distribution during high-velocity impacts through a computational biomechanical model integrating neuroanatomical structures and helmet components. Using a framework that combines finite element analysis and smoothed-particle hydrodynamics, this research evaluates fluid–structure interactions between cerebrospinal fluid, brain tissue, and six chinstrap configurations ranging from highly flexible to non-stretchable. The results reveal a critical trade-off: highly flexible straps reduce intracranial stress by dissipating energy through viscoelastic deformation but compromise helmet stability, while non-stretchable designs transmit undampened forces directly to the skull base, amplifying stress in vulnerable neurovascular regions. Intermediate stiffness configurations introduce a hazardous instability regime, where partial decoupling between the helmet and mandible causes lateral sliding of the chin guard, concentrating stresses at bony interfaces. The study identifies a nonlinear relationship between material rigidity and neuroprotection, emphasizing that optimal chinstrap design must balance elasticity to absorb impact energy with sufficient rigidity to maintain alignment and prevent stress redirection. Intermediate stiffness thresholds, despite partial energy absorption, paradoxically heighten risks due to incomplete coupling and dynamic instabilities. These findings challenge conventional helmet design paradigms, advocating for material engineering strategies that prioritize energy dissipation pathways while avoiding detrimental intermediate stiffness ranges. The insights advance concussion mitigation by refining chinstrap performance criteria to address both direct force transmission and instability-mediated injury mechanisms.

Epilepsy is one of the most common neurological disorders globally, affecting about 50 million people, with nearly 80% of those affected residing in low- and middle-income countries. It is characterized by recurrent seizures that result from abnormal electrical brain activity, with seizures varying widely in manifestation. The exploration of the biomechanical effects that seizures have on brain dynamics and stress levels is relevant for the development of more effective treatments and protective strategies. This study uses a blend of experimental data and computational simulations to assess the brain’s physical response during seizures, particularly focusing on the behavior of cerebrospinal fluid and the resulting mechanical stresses on different brain regions. Notable findings show increases in stress, predominantly in the posterior gyri and brainstem, during seizures and an evidence of brain displacement relative to the skull. These observations suggest a dynamic and complex interaction between the brain and skull, with maximum shear stress regions demonstrating the limited yet essential protective role of the CSF. By providing a deeper understanding of the mechanical changes occurring during seizures, this research supports the goal of advancing diagnostic tools, informing more targeted treatment interventions, and guiding the creation of customized therapeutic strategies to enhance neurological care and protect against the adverse effects of seizures.

The purpose of this research is to explore the biomechanical consequences of maternal injuries on fetal movements. Additionally, the research aims to comprehend the relationship between these injuries and fetal movement within the amniotic sac and to understand the extent to which the amniotic fluid can provide protection during severe injuries. The focus is on the potential impact these injuries could have on surgical procedures and preventative strategies. Using advanced computational simulations, the study investigates how various maternal injuries can influence the behavior of amniotic fluid and the subsequent stress exerted on fetal development. The findings suggest that maternal injuries can induce stress, primarily affecting the posterior regions of the fetus and the umbilical cord, depending on the boundary and initial conditions. This stress is associated with fetal displacement within the amniotic sac. While the amniotic fluid provides a certain level of protection, its limitations become apparent during severe injuries. These insights have implications for the field of surgery, particularly fetal procedures. They underscore the need for improved protective measures and the development of personalized obstetric and neonatal care strategies. Moreover, the study highlights the potential of computational simulations in aiding surgeons. These simulations can provide a more accurate understanding of the critical areas to focus on during surgical procedures, thereby enhancing the precision and safety of these operations.