Search

Elevated intracranial pressure (ICP) is a critical condition in traumatic brain injury, stroke, intracerebral hemorrhage, and hydrocephalus, often associated with poor outcomes when exceeding 20–25 mmHg. While invasive monitoring is accurate, it carries risks and is not always feasible, motivating the use of non-invasive approaches based on transcranial Doppler (TCD) ultrasound and arterial blood pressure (ABP) waveforms for continuous neurocritical care monitoring. However, existing non-invasive methods and purely data-driven machine learning models often lack physiological grounding, leading to reduced reliability and potential violations of cerebral hemodynamic principles, especially across diverse ICU settings with variable signal quality. To address these limitations, a physics-informed neural network (PINN) framework is proposed that integrates TCD and ABP signals while embedding cerebral hemodynamic equations into the learning process. The model uses separate encoders for TCD and ABP features, followed by a physics-constrained module and a loss function combining data accuracy with physical law consistency, such as mass conservation and pressure–flow relationships. This structure enables physiologically consistent ICP estimation, reduces data requirements, and improves generalization in clinical environments where labeled data are limited. Overall, the PINN-based approach enables more reliable, non-invasive, and continuous ICP monitoring by combining machine learning with physiological modeling. It offers a safer alternative when invasive monitoring is not possible and supports improved clinical decision-making in neurocritical care, though challenges remain in modeling complex autoregulation and ensuring high-quality waveform inputs.

Pressure ulcers are a persistent issue in bedridden patients, especially in intensive care, rehabilitation, and long-term care, leading to pain, infection, and extended hospital stays. Current risk assessments rely on intermittent scoring and clinical judgment, failing to account for continuous changes in body posture, tissue loading, and mechanical tolerance. This conceptual framework proposes a physics-informed graph neural network to predict pressure ulcer risk by integrating data from body position sensors, local tissue loading, and skin perfusion measurements into a dynamic, personalized model. The model represents the body as a graph, with nodes representing pressure-prone areas and edges indicating anatomical and mechanical connections. Tissue stress, perfusion data, and posture features are processed through network layers constrained by soft-tissue mechanics. By encoding the relationship between external forces, internal tissue deformation, ischemia, and damage, the framework allows risk propagation across adjacent anatomical regions. This approach offers a path for continuous, personalized pressure ulcer risk monitoring, laying the foundation for clinical validation and sensor integration.