Search Results (2,247)

Automated electrocardiogram (ECG) arrhythmia classification remains challenging due to signal noise, inter-patient variability, and limited annotated data, which constrain the generalization of supervised learning approaches. This study presents a self-supervised ECG representation learning framework that combines contrastive pretraining with ensemble-based supervised classification. A signal-to-noise ratio criterion is applied during self-supervised pretraining to stabilize contrastive optimization, while all extracted ECG beats, including noisy segments, are retained during downstream evaluation. The learned representations are classified using a hybrid ensemble composed of convolutional encoders and tree-based models. Model evaluation follows strict patient-level partitioning with stratified 10-fold cross-validation and bootstrap-based uncertainty estimation on a held-out test set. Under this evaluation protocol, the framework achieved high beat-level performance on curated datasets (internal and external). Class-wise performance shows precision and recall values between 0.99 and 0.999 across normal, supraventricular, ventricular, fusion, and paced beat categories. External validation is conducted on independent ECG cohorts, including PTB-XL, Chapman–Shaoxing, and INCART 12-lead datasets. On these datasets, the hybrid model attains macro-F₁ scores ranging from 0.91 to 0.94, compared with standalone convolutional and handcrafted feature-based Random Forest classifiers evaluated under identical conditions. These results characterize the behavior of the proposed representation learning framework across heterogeneous patient populations and recording configurations. Full article

Atrial fibrillation is the most prevalent sustained cardiac arrhythmia and a major risk factor for stroke, heart failure, and premature mortality. Automatic detection remains challenging due to the variability of electrocardiogram (ECG) morphology, noise, and the paroxysmal nature of atrial fibrillation events. This study proposes a comprehensive framework that integrates optimised segmentation, feature extraction, and advanced deep learning architectures to improve detection accuracy. A coalescence window is introduced to dynamically cluster arrhythmic episodes, aligning computational analysis with clinical event distributions. Multiple classifiers are investigated, ranging from traditional machine learning models to state-of-the-art deep neural networks, including Temporal Convolutional Networks (TCNs), Convolutional Neural Networks (CNNs), and Bidirectional Long Short-Term Memory (BiLSTM). Experimental evaluation on a balanced dataset of ECG signals demonstrates the superior performance of deep learning models, with the best architecture achieving high accuracy and F1-score, significantly outperforming traditional approaches. Furthermore, the proposed pipeline is designed to be modular and resource-aware, supporting potential deployment in real-time and edge computing environments. These results highlight the feasibility of scalable atrial fibrillation monitoring systems that bridge algorithmic innovation with clinical applicability, ultimately contributing to earlier diagnosis and improved patient management. Full article

Electrocardiogram waveform delineation is a fundamental task for quantitative cardiac analysis, yet accurate and consistent estimation of waveform boundaries remains challenging due to heart rate variability, inter-subject morphological differences, and nonlinear temporal distortions across cardiac cycles. Conventional rule-based methods and pointwise Dynamic Time Warping approaches are sensitive to amplitude variations and baseline fluctuations, while deep learning–based models require large annotated datasets and often suffer from limited interpretability and generalization. In this study, we propose a morphology-oriented ECG waveform alignment framework based on Pearson correlation–based Dynamic Time Warping (PCDTW). By integrating window-level matching with a correlation-driven cost function, the proposed method explicitly emphasizes local morphological similarity rather than absolute amplitude differences. Each ECG record is aligned using a subject-specific reference cycle constructed from normalized RR intervals, enabling stable correspondence of waveform boundaries without any training process. The proposed method was evaluated on two publicly available databases, the QT Database (QTDB) and the Lobachevsky University Electrocardiography Database (LUDB). Experimental results show that PCDTW significantly reduces QT and QTcB estimation errors compared with conventional DTW variants, demonstrating improved temporal consistency and lower bias across cardiac cycles. In particular, the mean QTcB error was reduced to 28.14 ms, compared with 124.54 ms obtained using conventional DTW. In addition, on LUDB, the overall mean delineation error for the P wave, QRS complex, and T wave boundaries was 10.68 ms, showing comparable or superior performance to state-of-the-art deep learning–based methods despite requiring no external training data. These findings indicate that morphology-aware, correlation-based temporal alignment provides a robust and interpretable alternative for ECG waveform boundary detection under realistic physiological variability. Full article

Background/Objectives: Dilated cardiomyopathy (DCM) and hypertrophic cardiomyopathy (HCM) are common cardiomyopathies associated with heart failure. Electrocardiogram (ECG) screening before an echocardiogram could help streamline diagnosis, particularly in rural areas. Prior ECG–machine learning (ML) studies do not use open-source data when studying cardiomyopathy, and very few proprietary studies directly compare HCM and DCM or address ECG differences within obstructive (HOCM) and non-obstructive HCM (HNCM). Methods: Standard and vectorcardiogram-derived (VCG) ECG features were extracted from the MIMIC-IV-ECG database. The final cohort comprised 599 patients (HCM = 208 [HOCM = 99, HNCM = 53, unknown = 56]; DCM = 391 [ischemic cardiomyopathy with left ventricular dilation = 250, non-ischemic = 141]). Logistic regression (LR) and extreme gradient boosting (XGBoost) with five-fold cross-validation separated HCM from ischemic cardiomyopathy with left ventricular dilation (DCM-I) and non-ischemic DCM (DCM-NI), and HOCM from HNCM. Results: Using the area under the receiver-operating-characteristic curve (AUC-ROC) as the performance metric, LR achieved high discrimination of HCM from DCM-I (0.92) and DCM-NI (0.90). However, differentiating HOCM from HNCM proved more difficult (XGBoost = 0.81; LR = 0.75). Both DCM subtypes (especially ischemic) showed lower QRS amplitudes and right-posterior ventricular gradient orientation; HCM displayed higher amplitudes and larger, more complex T-loops. Within HCM, HOCM had stronger leftward electrical activity and more dipolar to non-dipolar QRS energy after singular value decomposition. Conclusions: Using only open-access data, we demonstrate an interpretable ECG-based pipeline that discriminates cardiomyopathy and highlights distinct features. While detecting obstruction remains difficult, ECG features provide measurable separation, supporting possible diagnostic screening and offering a reproducible framework for future studies. Full article

Respiration is closely related to the parasympathetic nervous system (PSNS). This relation occurs within a single respiratory cycle, with PSNS activity reduced during inspiration and increased during expiration. Over a longer timescale, deep and slow breathing has been reported to enhance PSNS activity, indicating that not only the timing (phase) but also the respiratory depth and rate may influence autonomic nervous system activity. However, under spontaneous breathing, it remains unclear which of the following best reflects PSNS activity: (i) raw respiratory waveform, (ii) respiratory depth, or (iii) respiratory rate. Respiratory depth was defined as instantaneous amplitude and respiratory rate as instantaneous frequency, both derived from the Hilbert transform. Respiratory waveforms and electrocardiograms were recorded at rest in 37 healthy adults. PSNS activity was quantified using heart rate variability indices reflecting parasympathetic modulation, including HF power, RMSSD, and CVI. Within-participant correlations between each respiratory measure and PSNS indices were obtained, and repeated-measures ANOVA with respiratory measure as a factor was used to compare correlation strengths. Results showed a significant main effect, with instantaneous amplitude consistently exhibiting significantly stronger correlations than the instantaneous frequency across all PSNS indices. These findings suggest that Hilbert-derived amplitude serves as a useful indicator of respiratory depth during spontaneous breathing and that depth is more strongly associated with PSNS activity. Full article

Objective: To investigate the changes in T-wave amplitude and Tp-Te interval on supine and standing electrocardiograms (ECGs) in pediatric postural orthostatic tachycardia syndrome (POTS), and to explore their predictive value for the therapeutic effect of metoprolol. Methods: A total of 59 children diagnosed with POTS who presented with syncope or pre-syncopal symptoms were enrolled as the POTS group, and 52 healthy children served as the control group. Supine and standing ECGs were recorded for all subjects, and T-wave amplitude and Tp-Te interval were measured. Children with POTS were followed-up after metoprolol treatment and divided into a therapeutic response group and a non-response group. Results: (1) Comparison of supine vs. standing ECGs: In the POTS group, standing posture (compared with supine posture) was associated with increased heart rate (HR), decreased T-wave amplitude in leads II, III, aVF, V4, V5, and V6, shortened Tp-Te interval in leads I, II, III, aVR, aVF, V1, V3, V4, V5, and V6, and elevated Tp-Te/QT ratio in leads aVL and V5 (all p < 0.05). (2) Comparison with the control group: The POTS group exhibited a greater HR difference (ΔHR), as well as larger differences in T-wave amplitude (ΔT-wave amplitude) between supine and standing positions in leads II, aVR, aVL, aVF, V3, and V5 (all p < 0.05). (3) Follow-up: Compared with the non-response group, the therapeutic response group showed larger ΔT-wave amplitude in leads III, aVF, V2, V3, V4, and V5, larger Tp-Te interval difference (ΔTp-Te interval) in lead V3, and larger Tp-Te/QT ratio difference (ΔTp-Te/QT ratio) in lead V3 (all p < 0.05). (4) Receiver operating characteristic curve: ΔT-wave amplitude in leads III, aVF, V2, V3, V4, and V5, ΔTp-Te interval in lead V3, and ΔTp-Te/QT ratio in lead V3 all had predictive value for the therapeutic effect of metoprolol in pediatric POTS (all p < 0.05). Conclusions: ΔHR and ΔT-wave amplitude in lead V5 between supine and standing positions are independent risk factors for pediatric POTS. A combination of five indicators—ΔT-wave amplitude in leads V2, V3, and V5, ΔTp-Te interval in lead V3, and ΔTp-Te/QT ratio in lead V3 between supine and standing ECGs—exerts a good predictive effect on the therapeutic response of pediatric POTS to metoprolol intervention. Full article

Background: The Index of Cardiac Electrophysiological Balance (ICEB) has emerged as a electrocardiographic marker reflecting the equilibrium between ventricular depolarization and repolarization. Although obesity is known to alter cardiac electrophysiology, the combined influence of body mass index (BMI) and objective nutritional status on ICEB and its heart rate-corrected form (ICEBc) remains insufficiently defined. This study aimed to investigate the associations between BMI categories, nutritional status, and cardiac electrophysiological balance. Methods: This cross-sectional study included 591 adult patients classified as normal-weight, overweight, or obese according to BMI. Electrophysiological assessment of ICEB (QT/QRS) and ICEBc (QTc/QRS) values was calculated from standard 12-lead electrocardiogram recordings. Participants’ nutritional status was analyzed using validated clinical indices such as the Prognostic Nutritional Index (PNI), Controlling Nutritional Status (CONUT), Geriatric Nutritional Risk Index (GNRI) and Hemoglobin–Albumin–Lymphocyte–Platelet (HALP) score. Results: According to the results, both ICEB and ICEBc showed significant differences among BMI categories (p < 0.001). ICEB/ICEBc exhibited a non-linear distribution. The ICEB/ICEBc values were found to be minimum in the normal weight group at 4.22 ± 0.54/4.87 ± 0.66 and maximum in the obese group at 4.27 ± 0.51/4.99 ± 0.59. The ICEB/ICEBc value closest to the optimal physiological limits was found in the overweight group at 4.04 ± 0.53/4.59 ± 0.58. Higher ICEBc quartiles were accompanied by increased GNRI (120.9 ± 13.7, 129 ± 15.1, 130.5 ± 16.3, 131.8 ± 17.6, p < 0.001)and decreased HALP scores (59.7 ± 24.4, 56.1 ± 25.3, 55.2 ± 25.9, 51.1 ± 19.4, p: 0.025). Conclusion: The association between BMI and cardiac electrophysiological balance is non-linear and appears to be modulated by nutritional and inflammatory status. ICEBc may represent a more sensitive marker than ICEB for detecting subtle electrophysiological alterations related to obesity. Full article

Background: Rickettsial diseases are endemic in southeastern Mexico, yet their potential subclinical cardiac effects remain poorly understood. Although severe spotted fever and typhus group infections may cause myocarditis and arrhythmias, limited evidence exists regarding cardiac alterations in individuals previously diagnosed with rickettsiosis who later show Rickettsia spp. IgG seropositivity. Methods: This follow-up observational study was conducted at a tertiary referral hospital in the Yucatan Peninsula. From an initial cohort of 390 patients evaluated for suspected rickettsial disease, 284 were confirmed as IgG-positive during follow-up. Among them, 18 adults who were asymptomatic for acute rickettsiosis at reassessment, but reported mild or nonspecific cardiac symptoms, underwent standardized cardiological evaluation. Procedures included a 12-lead electrocardiogram (ECG), transthoracic echocardiography, and 24 h Holter monitoring. All studies were reviewed independently by two blinded cardiologists with senior adjudication. Results: Global systolic function was preserved in all participants. However, subclinical abnormalities were identified, including right ventricular dilation in 16.7%, clinically relevant QTc prolongation in 22.2%, sinus pauses in 11.1%, reduced heart rate variability in 11.1%, atrial flutter in one patient, and complete left bundle branch block in one patient. QTc prolongation was detected exclusively through Holter monitoring. Conclusions: Adults previously diagnosed with rickettsiosis may exhibit subclinical cardiac involvement despite apparent recovery. Holter monitoring appears more sensitive than ECG for identifying electrical disturbances, warranting larger prospective studies. Full article

According to in-depth research on the perception ability of dangerous omens of excellent drivers, references can be provided for the development of brain-like intelligence and its transplantation, as well as applications in the field of autonomous driving, which will improve the active safety and intelligence level of vehicles. Previous studies have shown that there is indeed a dangerous omen before an accident occurs. However, current studies are still unclear about the bio-psychophysiological characteristics exhibited by drivers with high levels of sensory agility when they anticipate potential warning signs, and there is no method for screening such drivers who can perceive dangerous omens proposed by any research. To address the above issues, this paper conducts in-depth research. Firstly, through designing dangerous scenarios and conducting hazard perception tests, we collect physiological, psychological, and physical data, such as drivers’ bioelectrical signals (electroencephalogram and electrocardiogram) and eye movements. Secondly, through playing back experimental videos, actively questioning drivers, and analyzing local changes in their electroencephalogram data, the driver’s ability to identify a dangerous omen and the moment of perception are determined. Thirdly, based on techniques such as the Kolmogorov–Smirnov test and the Mann–Whitney U test, the differences in bioelectrical and eye movement characteristics between drivers who can perceive a dangerous omen and others can be further revealed. Finally, the driver’s bioelectrical and eye movement characteristics are used as latent variables, and their corresponding data are utilized as observation indicators. We construct a structural equation model for screening drivers capable of perceiving a dangerous omen and conduct calibration and validation. This study provides inspirational ideas for empowering vehicles to identify potential hazards, advancing end-to-end and other higher-level autonomous driving technologies, and further enhancing road traffic safety. Full article

Background: Postoperative atrial fibrillation (POAF) after cardiac surgery is common and clinically relevant, yet optimal postdischarge ECG surveillance remains undefined. We assessed the incidence of POAF after isolated coronary artery bypass grafting (CABG) and surgical aortic valve replacement (SAVR) using a dual-modality ambulatory strategy. Methods: In an exploratory, single-center study, consecutive adults without pre-operative AF undergoing elective isolated CABG or SAVR received dual-modality monitoring after discharge: continuous patch-Holter for ~10 days and a patient-activated single-lead recorder for up to 30 days. Early POAF was AF/AFl during index hospitalization; late POAF was first AF/AFL detected postdischarge by either modality. Results: Fifty-five patients were enrolled (CABG 30 [54.5%], SAVR 25 [45.5%]; mean age 64.6 ± 9.8 years; 38.2% women). Early POAF occurred in 10/49 (20.4%); late POAF was detected in 21/55 (38.2%). By modality, late AF was identified on the 10-day Holter in 11/51 (21.6%) and on the 30-day recorder in 19/51 (37.3%). Cumulative detection reached 20.0% by day 7, 30.9% by day 10, and 38.2% thereafter, demonstrating that a substantive proportion of late POAF occurred after day 10, and 19/21 (90%) were captured by event monitoring. Female sex was independently associated with late POAF (OR 3.70, 95% CI 1.17–11.72); longer aortic cross-clamp time was related to late POAF in the SAVR subset, while larger LA size was related to POAF incidence in the CABG group. Early (in-hospital) POAF was associated with subsequent late POAF (p = 0.025). The difference in late POAF frequency between CABG and SAVR (33.3% vs. 44.0%; p = 0.42) was not significant. Conclusions: Among patients without prior AF undergoing CABG or SAVR, late POAF is frequent and often manifests beyond 10 days after discharge. Extending ambulatory surveillance to 30 days—or adopting a 10-day continuous plus patient-activated to day 30 hybrid—materially improves case finding and should be considered in routine postoperative pathways. Full article

Background/Objectives: Physiological changes during hyperbaric oxygen therapy (HBOT) are not well characterized, particularly in non-emergent patients receiving HBOT as part of a repeated or maintenance treatment course, in whom understanding physiological responses during individual sessions is important for clinical monitoring. This study evaluated changes in vital signs and electrocardiographic (ECG) findings across the pre-compression, compression, maintenance, decompression, and post-treatment phases and evaluated clinical symptoms. Methods: This prospective observational study enrolled 50 hemodynamically stable non-emergent patients undergoing HBOT at a single tertiary center. Changes in vital signs and ECG findings were recorded across all phases. Repeated vital sign measurements were analyzed using linear mixed models; ECG abnormalities were assessed using generalized linear mixed models. Results: Heart rate decreased significantly across all HBOT phases compared with baseline. Blood pressure (BP) remained stable during compression and maintenance but increased significantly during decompression and post-treatment. Respiratory rate decreased during treatment and then returned to baseline. Oxygen saturation remained within normal ranges throughout all phases. Transient ECG rhythm abnormalities were observed in 10.0% of patients, primarily during compression and maintenance phases. One patient developed brief clinical symptoms accompanied by supraventricular tachycardia immediately after decompression, which resolved spontaneously without intervention. No significant oxygen toxicity or serious adverse events were observed. Conclusions: HBOT in hemodynamically stable non-emergent patients induces predictable, largely transient physiological changes and is well tolerated under standard protocols. Blood pressure elevation was most pronounced during decompression and the post-treatment phase, whereas transient ECG abnormalities were observed primarily during the compression and maintenance phases, with a single episode of supraventricular tachycardia occurring immediately after decompression. These findings provide foundational clinical data for understanding phase-specific physiological responses during HBOT and inform future studies in higher-risk patient populations. Full article

Background: Cardiovascular disease (CVD) is the leading cause of mortality worldwide, creating demand for continuous, unobtrusive monitoring solutions. This clinical validation evaluates the accuracy of remote photoplethysmography (rPPG), a contactless method using camera video, for measuring pulse rate (PR) in patients with CVD. Methods: We enrolled 50 adults with confirmed CVD at a clinical trial center. In a 6 min rested session, synchronized facial video (under controlled lighting), electrocardiogram (ECG), and photoplethysmography (PPG) signals were recorded. PR was derived from 25 s video segments using rPPG-enabled software and compared to ECG-derived PR via regression and Bland–Altman analysis. Results: Data from 47 participants (n = 817 samples) were analyzed. rPPG-derived PR showed strong agreement with ECG, with a mean absolute error of 1.061 bpm, root-mean-squared error of 2.845 bpm, and Pearson correlation of 0.962. Mixed-effects regression analyses (after 2% outlier removal, n = 782) indicated minimal influence from demographic, environmental, or CVD factors on accuracy. PPG-ECG discrepancies reflected inherent methodological differences. Conclusion: The rPPG method provides accurate, contactless PR monitoring in CVD patients, supporting its potential for remote patient monitoring and early deterioration detection. Future work will validate rPPG for irregular rhythms, additional vital signs, and diverse cohorts to strengthen clinical robustness for cardiometabolic risk assessment. Full article

Background: Pain remains one of the most debilitating and prevalent symptoms in cancer patients. However, assessment based solely on subjective self-report tools is limited by cognitive impairment and the heterogeneous nature of cancer pain. Since evidence on the ability of physiological biosignals to discriminate cancer pain intensity and pain phenotypes in real clinical settings remains limited, this study explored the potential of biosignals to discriminate between pain intensity and pain type. Methods: Electrodermal activity (EDA) and electrocardiogram (ECG) signals were recorded in cancer patients using the BITalino (r)evolution board (sampling frequency 1000 Hz). EDA was processed to extract skin conductance responses (SCRs) using continuous decomposition analysis (CDA) and trough-to-peak (TTP) methods. Heart rate variability (HRV) features were extracted in both time and frequency domains, including low frequency (LF), high frequency (HF), and the LF/HF ratio. Non-parametric Kruskal–Wallis tests were performed to compare biosignal parameters across pain intensity (Numeric Rating Scale, NRS: low 1–3; medium 4–6; and high 7–10) and pain types (nociceptive, neuropathic, mixed, and breakthrough cancer pain—BTCP). Results: Data from 61 patients were analyzed. For EDA, the maximum skin conductance response amplitude (MaxCDA) significantly differed across intensity groups (p = 0.037). Post hoc analysis showed a significant difference between the low- and high-intensity groups (p = 0.015), with the low-intensity group exhibiting a higher mean MaxCDA (0.063 µS) than the high-intensity group (0.024 µS). Several EDA parameters were significantly associated with pain type. The number of SCRs (TTP) (p = 0.015) and maximum SCR amplitude (TTP) (p = 0.040) were significantly lower in the mixed pain group compared with the nociceptive and neuropathic groups. No HRV parameters showed significant associations with pain intensity or pain type. BTCP did not significantly affect any biosignal parameters. Subgroup analyses showed that EDA features discriminating mixed pain were preserved in patients without bone metastases, BTCP, or high opioid burden, whereas no clinical variable modified the association between biosignals and pain intensity and type. Conclusions: In this investigation, selected EDA parameters were associated with cancer pain intensity and pain type, whereas heart rate variability measures did not show significant discrimination under the present methodological conditions. These findings suggest that EDA may provide complementary information on pain-related autonomic alterations in oncology patients. However, biosignals should not be considered standalone indicators of pain, and their interpretation requires integration with clinical variables and pharmacological context. Further studies adopting multimodal and longitudinal approaches are needed to clarify their role in automatic pain assessment in cancer care. Full article

Background: Fulminant type 1 diabetes (FT1D) is a rare but life-threatening subtype of type 1 diabetes. The concurrence of FT1D with myocarditis is uncommon and attracts further clinical attention. Case Presentation: A 33-year-old female was transferred by a local hospital to West China Hospital because of altered consciousness, abrupt onset of hyperglycemia with ketoacidosis, significantly increased cardiac biomarkers, and ST segment elevations. Her random blood glucose at the local hospital was 50.19 mmol/L. Insulin infusion and fluid resuscitation were started immediately before referral. On admission, her random blood glucose was 14.17 mmol/L. HbA1C and glycosylated albumin (GA) were 6.3% and 21.45%, respectively. Her fasting C-peptide level was 0.022 nmol/L. Anti-Glutamic Acid Decarboxylase (anti-GAD) antibody was 25.06 IU/mL. FT1D was diagnosed based on the 2012 New Diagnosis Criteria of FT1D. Electrocardiogram showed significant ST segment elevation in leads II, III, aVF, and V3-V6. Echocardiography revealed a mildly reduced left ventricular ejection fraction (LVEF) of 46%. Coronary angiography displayed no abnormality. Cardiac magnetic resonance imaging revealed areas of increased signal intensity in the interventricular septum, basal and mid inferolateral walls, and apical inferior wall and subepicardial late gadolinium enhancement (LGE), particularly in the lateral aspects of the left ventricle on T2-weighted imaging (T2WI). Acute myocarditis was diagnosed based on the European Society of Cardiology 2013 Task Force Criteria. She was treated with insulin, fluid resuscitation, and supportive care, leading to rapid recovery of ketoacidosis and cardiac function. At the four-month follow-up, she remained on insulin therapy with good glycemic control but persistent low C-peptide levels. Conclusion: This case report raises awareness about FT1D, determines the differential diagnosis of acute cardiac presentations in an FT1D patient, and highlights clinical reasoning so that clinicians can recognize and manage similar presentations on time. Full article

Background/Objectives: Pulmonary embolism (PE) remains a significant cause of cardiovascular mortality, with risk stratification being critical for optimizing treatment decisions. Heart rate variability (HRV), a measure of autonomic nervous system function, had been explored as a prognostic index in various cardiovascular conditions, yet has received limited investigation regarding PE prognosis. Our objective was to evaluate the prognostic value of ultra-short HRV indices, obtained at the emergency department (ED), in patients presenting with PE. Methods: A retrospective cohort study, conducted at Rambam Health Care Campus, Haifa, Israel. All eligible patients diagnosed with acute PE at the ED, between the years 2010 and 2012 were included. Further, a subgroup analysis was performed to differentiate between oncological (n = 118) and non-oncological (n = 115) patient populations. Ten-seconds electrocardiogram was used to compute ultra-short HRV indices, specifically SDNN (standard deviation of normal-to-normal RR intervals) and RMSSD (root mean square of successive differences). Multivariate logistic regression models were created to assess HRV’s independent predictive value for 30-day and 90-day mortality. In addition, a survival analysis was carried out utilizing Cox regression and Kaplan-Meier curves. Results: 233 patients (42% male; age 65 ± 17) were included in the analysis. Ultra-short HRV indices did not significantly correlate with short-term mortality. However, in non-oncological patients (n = 115), multivariate analysis demonstrated that higher SDNN (as a continuous variable), was independently associated with increased 90-day mortality (AOR 1.018, 95% CI 1.000–1.037; p = 0.044). In contrast, HRV showed no predictive value for mortality in oncological patients. In both the entire cohort and the non-oncological sub-group, Kaplan-Meier plots established statistically significant differences, with lower HRV indices correlating with worse survival. This finding is paradoxical. The issue of context-dependent HRV (i.e., based on ECG obtained during rapid shallow breathing, which reduces HRV on the one hand, but is possibly adaptive during an acute PE, to increase oxygen supply and prevent shock in the short run, on the other hand), may explain these findings. Conclusions: Ultra-short HRV shows some promise in short term risk stratification of non-oncological PE patients. As for oncological patients, HRV was not found to have short term prognostic relevance. Full article