Neurogenic bladder is a debilitating condition caused by neurological dysfunction that impairs urinary control, often requiring timed intermittent catheterisation. Although effective, intermittent catheterisation is invasive, uncomfortable, and associated with infection risks, reducing patients’ quality of life. SafeBladder is a low-cost wearable device developed to enable real-time, non-invasive bladder volume monitoring using near-infrared spectroscopy (NIRS) and machine learning algorithms. The prototype employs LEDs and photodetectors to measure light attenuation through abdominal tissues. Bladder filling was simulated through experimental tests using stepwise water additions to containers and tissue-mimicking phantoms, including silicone and porcine tissue. Machine learning models, including Linear Regression, Support Vector Regression, and Random Forest, were trained to predict volume from sensor data. The results showed the device is sensitive to volume changes, though ambient light interference affected accuracy, suggesting optimal use under clothing or in low-light conditions. The Random Forest model outperformed others, with a Mean Absolute Error (MAE) of 25 ± 4 mL and of 0.90 in phantom tests. These findings support SafeBladder as a promising, non-invasive solution for bladder monitoring, with clinical potential pending further calibration and validation in real-world settings.
This work presents a comprehensive theory of consciousness grounded in mathematical formalism and supported by clinical data analysis. The framework developed herein demonstrates that consciousness exists as a continuous, non-monotonic function across a high-dimensional neurochemical space, with dopamine serving as the primary intensity regulator and serotonin (5-HT2A) as the complexity modulator. This work offers mechanistic explanations for the full spectrum of conscious states, from deep sleep and psychosis to the ultimate collapse in neural death. The theory explains paradoxical phenomena such as prefrontal cortex hypoactivity during seizures, the evolutionary persistence of psychosis-prone individuals, and why controlled administration of classical 5-HT2A agonists shows a comparatively low incidence of serious medical events (< 0.01 % in modern clinical trials), while dopaminergic excess proves rapidly lethal. The framework is tested using 70,290 sleep nights from 242 Parkinson's disease patients, using disease severity (UPDRS) as a proxy for system integrity and medication (LEDD) as a proxy for dopaminergic input. The analysis reveals a significant LEDD x UPDRS interaction (beta=-1.7, p<.0001), confirming the model's prediction of state-dependent, non-linear dynamics.
The integration of Large Language Models (LLMs) into healthcare holds significant potential to enhance diagnostic accuracy and support medical treatment planning. These AI-driven systems can analyze vast datasets, assisting clinicians in identifying diseases, recommending treatments, and predicting patient outcomes. This study evaluates the performance of a range of contemporary LLMs, including both open-source and closed-source models, on the 2024 Portuguese National Exam for medical specialty access (PNA), a standardized medical knowledge assessment. Our results highlight considerable variation in accuracy and cost-effectiveness, with several models demonstrating performance exceeding human benchmarks for medical students on this specific task. We identify leading models based on a combined score of accuracy and cost, discuss the implications of reasoning methodologies like Chain-of-Thought, and underscore the potential for LLMs to function as valuable complementary tools aiding medical professionals in complex clinical decision-making.