Heart rate variability (HRV) is a non-invasive physiological indicator of autonomic nervous system activity and provides an objective means to assess psychological states such as perceived stress and resilience. This study investigated whether HRV can reflect individual tendencies in terms of perceived stress and resilience, as assessed by the Perceived Stress Scale (PSS), the Connor–Davidson Resilience Scale (CD-RISC), and their combined groups according to the Perceived Stress Scale (PSS), the Connor–Davidson Resilience Scale (CD-RISC), and their combined groups, and examined the autonomic mechanisms underlying these constructs. Ninety-two adults completed both questionnaires and participated in a stress-induction protocol based on the Trier Social Stress Test, consisting of pre-resting, stress session, and post-resting sessions. HRV features across time, frequency, and nonlinear domains were extracted from the resting, reactivity, and recovery phases, analyzed with linear mixed models, and applied in classification models using sequential forward selection and leave-one-subject-out cross-validation. The results showed that high PSS participants exhibited reduced parasympathetic activity primarily at rest, whereas high CD-RISC individuals demonstrated higher parasympathetic activity and autonomic balance across all phases, with greater stability under acute stress and faster recovery. The combined PSS–CD-RISC grouping revealed compounded autonomic dysfunction in the high-stress–low-resilience quadrant. Classification accuracies reached approximately 82% for PSS and CD-RISC separately and 87% when combined, with resilience-related models benefiting particularly from reactivity and recovery features in addition to resting indices. These findings demonstrate that HRV captures distinct autonomic processes underlying stress and resilience, indicating that the two constructions are not redundant but complementary. HRV thus holds promise as a supportive indicator in wearable systems for continuous monitoring and personalized intervention.

Noninvasive blood glucose monitoring is crucial for detecting early dysglycemia, yet continuous glucose monitors remain invasive and costly. Electrocardiogram (ECG) and its derived heart rate variability (HRV) measure may offer a noninvasive indicator of autonomic and cardiac responses associated with acute changes in glucose. In this study, 30 adults underwent a 75 g oral glucose tolerance test with concurrent ECG Holter and interstitial glucose monitoring. From these recordings, HRV and ECG features were extracted. A deep learning classifier with HRV and ECG was then trained to detect hyperglycemia (glucose ≥ 180 mg/dL). Cross-correlation analysis confirmed a significant association between HRV and glucose (Pearson r ~0.65, p < 0.05) when aligning each participant’s data according to individual response delays. The model achieved high classification performance under rigorous temporal validation (accuracy ~89%, area under the receiver operating characteristic curve ~0.89). Saliency analyses revealed that the classifier’s decisions focus on distinct ECG waveform transitions and key HRV features linked to glucose-induced autonomic changes. Overall, acute hyperglycemia elicited discernible changes in HRV and cardiac conduction, supporting the feasibility of this physiologically grounded approach for detecting the acute hyperglycemic phase under controlled conditions. This method holds promise for real-time implementation in wearable devices, enabling early diabetes risk screening.