Ischemic stroke is a leading cause of mortality and disability. The relationships of heart rate variability (HRV) and stroke-related factors with mortality and functional outcome are complex and not fully understood. Understanding these relationships is crucial for providing better insights regarding ischemic stroke prognosis. The objective of this study is to examine the relationship between HRV, neurological function, and clinical factors with mortality and 3-month behavioral functional outcome in ischemic stroke. We prospectively collected the HRV data and monitored the behavioral functional outcome of patients with ischemic stroke. The behavioral functional outcome was represented by a modified Rankin Scale (mRS) score. This study population consisted of 58 ischemic stroke patients (56.9% male; mean age 70) with favorable (mRS score ≤ 2) and unfavorable (mRS score ≥ 3) outcome. The analysis indicated that the median of the mean RR interval (RR mean) showed no statistical difference between mortality groups. Conversely, the median of the RR mean had significant association with unfavorable outcome (OR = 0.989, p = 0.007). Lower hemoglobin levels had significant association with unfavorable outcome (OR = 0.411, p = 0.010). Higher National Institute of Health Stroke Scale (NIHSS) score at admission had significant association with unfavorable outcome (OR = 1.396, p = 0.002). In contrast, age, stroke history, NIHSS score at admission, and hemoglobin showed no significant association with mortality in ischemic stroke. These results imply that HRV, as indicated by the median of RR mean, alongside specific clinical factors and neurological function at admission (measured by NIHSS score), may serve as potential prognostic indicators for 3-month behavioral functional outcome in ischemic stroke.

Background: Heart rate variability (HRV) is a valuable indicator for assessing vascular health, but keeping clinical decision support systems (CDSSs) aligned with the rapidly evolving literature remains challenging. This study aimed to develop an LLM-assisted literature synthesis framework to support transparent HRV-based risk stratification, enabling systematic extraction and organization of HRV evidence from published studies. Methods: An LLM-driven framework was developed to extract HRV parameters from 140 medical abstracts. The system simulated step-by-step human reasoning to identify key HRV indicators and group patient data using predefined statistical thresholds derived from the literature. System performance was evaluated using ECG-derived HRV features as a feasibility evaluation of literature-guided HRV classification. Results: The proposed framework demonstrated an accuracy of 86% in literature-guided HRV classification, with a sensitivity of 81% and a specificity of 87%. Compared with traditional machine learning approaches, the LLM-assisted system provided transparent, literature-grounded reasoning and could be readily updated as new studies became available. Conclusions: Large language models can support evidence-guided parameter selection and feasibility-level HRV-based risk stratification, rather than serving as predictive classifiers. This approach reduces manual effort, enhances transparency, and addresses common “black box” concerns associated with AI-assisted CDSS development in clinical practice.

Empirical mode decomposition (EMD) is an adaptive signal analysis method requiring no predefined basis functions, capable of handling nonlinear and non-stationary signals. However, its high computational cost has long prevented real-time operation on embedded systems, particularly at audio frequencies (8–96 kHz). To the best of our knowledge, this study presents the first real-time audio-frequency EMD system running entirely on a commercial microcontroller (ARM Cortex-M7, STM32H730). The system captures audio via a MEMS microphone, decomposes signals into intrinsic mode functions (IMFs) using fast EMD, applies independent gain to each IMF, and reconstructs the output in real time. Systematic evaluation shows that: (1) the maximum processing rate increases approximately in proportion to the MCU clock frequency, achieving 100 kHz (one IMF) or 40 kHz (four IMFs) at 300 MHz; (2) processing latency is only approximately 1.6 ms (16 kHz, 8 ms window, four IMFs + residual), increasing approximately in proportion to window length; and (3) each IMF corresponds to a distinct frequency range, enabling data-driven frequency-selective processing. Built entirely from commercial off-the-shelf components and powered by two 1.5 V batteries, the system provides initial evidence for transitioning fast EMD from offline analysis to real-time embedded signal processing.