Physiological Measurement

Ventricular tachycardia (VT) and ventricular fibrillation (VF) are the leading electrical causes of sudden cardiac death, but automated detection is limited by strong class imbalance, where lethal arrhythmias account for fewer than 22% of ECG segments. In this setting, standard classifiers can achieve high accuracy by predicting normal rhythm in most cases while missing many lethal events, a failure mode referred to as rare-class collapse. We evaluated six imbalance-handling approaches: naive logistic regression, inverse-frequency reweighting, label-distribution-aware margin loss (LDAM), cost-sensitive training, two-stage cascade classification, and anomaly detection on 15,614 ECG segments from three PhysioNet databases (VTaC, VFDB, CUDB), with an overall normal-to-lethal ratio of 3.6:1. All methods were assessed at a fixed operating point of 95% specificity using recall, area under the precision-recall curve (AUPRC), and missed-lethal-event rate (MLER). The naive model achieved 45.1% recall (MLER = 0.549), missing 564 of 1,027 lethal events despite 84.1% accuracy. The two-stage cascade performed best, with 65.2% recall, AUPRC of 0.821, and MLER of 0.348, reducing missed events by 37% and achieving the highest decision-curve net benefit. Per-source analysis showed near-complete VF detection (recall up to 0.975) but much lower VT detection (recall 0.183), suggesting a feature-space limitation due to spectral similarity between organized VT and rapid sinus rhythm. Overall, the results show that evaluation metrics strongly influence the visibility of rare-class failure, and that cascade-based methods outperform simpler reweighting approaches for detecting lethal arrhythmias.

Adhesive electrocardiography (ECG) electrodes used in neonatal intensive care units (NICUs) may cause skin injury in premature infants. Although photoplethysmography (PPG)-based ECG reconstruction has been explored, existing studies have mainly focused on adult data and often rely on direct PPG-to-ECG mapping or artificial signal alignment, which may be unsuitable for neonates with highly variable pulse arrival time (PAT). In this study, we propose an alignment-free RoPE-based dual-stream Transformer for reconstructing missing neonatal ECG segments using concurrent PPG signals and bidirectional ECG context. A total of 52,566 10-second ECG-PPG windows were extracted from 159 NICU patients and split at the patient level to prevent data leakage. The model was designed to learn ECG-PPG temporal coupling without forced synchronization by integrating PPG-derived hemodynamic timing information with lead-specific ECG context. Under a 40% random missing condition, the model achieved a Pearson correlation coefficient of 0.96, mean absolute error of 0.04, and root mean square error of 0.07. It also maintained robust performance under 4.0-second continuous block loss and 60% random patch loss, preserving a PCC of at least 0.90. These findings suggest that the proposed framework may serve as a signal imputation module for maintaining ECG monitoring continuity in NICU environments. Prospective validation is required before clinical diagnostic use.

Background Ventilator-associated pneumonia (VAP) is the most frequent nosocomial infection in critical care, affecting 20-36% of mechanically ventilated patients. Early prediction is hampered by the absence of a reliable, objective diagnostic standard. We developed ADVISE (Automated Dudley Ventilation Infection Series Evaluation), a machine learning model to predict physiological deterioration consistent with developing VAP using routinely collected electronic health record data from a UK NHS intensive care unit. Methods Retrospective observational study of admissions at Russell's Hall Hospital ICU (2008-2026). Following National Data Opt-Out exclusion (158 admissions, 4.2%), 3,566 admissions generated 33,208 candidate 48-hour observation blocks. Six temporal variables - FiO2, ventilator mode, P:F ratio, procalcitonin (PCT), secretion amount, and secretion description - were extracted across the baseline window (hours 1-24). A composite VAP-surrogate outcome required concurrent P:F ratio decline (>=5%) and PCT rise (>=0.5 ng/mL) across the outcome window (hours 25-48). After sequential quality filters, 2,134 blocks (18 positive, 0.84% prevalence) were retained. An XGBoost classifier was trained using nested 5-fold cross-validation with scale_pos_weight=114.0 and ROC-based hyperparameter optimisation on 1,495 training blocks, evaluated on 639 held-out test blocks. Performance was assessed via AUROC, AUPRC, and calibration (Brier score). Bootstrap resampling (1,000 iterations) generated 95% confidence intervals. Results On the held-out test set (n=639, 5 positive outcomes), ADVISE achieved AUROC 0.874 [95% CI: 0.771-0.939] and AUPRC 0.031 [0.008-0.069], representing a 4.0-fold improvement over the no-skill baseline. Nested cross-validation mean AUROC was 0.844 +/- 0.078 (range 0.716-0.915). At the Youden-optimal threshold, sensitivity was 0% with specificity 97.8%, reflecting extreme class imbalance (0.78% test prevalence). A threshold targeting 80% sensitivity achieved sensitivity 80.0% [33.3-100.0%], specificity 87.4% [84.8-89.9%], positive predictive value 4.8% [1.1-9.9%], and negative predictive value 99.8% [99.4-100.0%], detecting 4 of 5 VAP cases with approximately 80 false alarms (12.6% false positive rate). Brier score was 0.0078. Feature importance identified baseline P:F ratio as the dominant predictor (41.3% total gain), followed by ventilator mode (26.1%), secretion amount (13.2%), secretion description (9.1%), procalcitonin (5.9%), and FiO2; (4.5%). Conclusions ADVISE demonstrates that baseline oxygenation trajectory and ventilatory support patterns - derived exclusively from routinely charted ICCA variables - can identify admissions at risk of VAP-related physiological deterioration with meaningful discrimination (AUROC 0.874) despite severe class imbalance. The 80% sensitivity operating point offers a clinically actionable alert rate (12.6% FPR), supporting integration into existing ICU workflows. This proof-of-concept study establishes feasibility; multi-site prospective validation is required before clinical deployment.

Body surface gastric mapping (BSGM) enables non-invasive measurement of gastric electrophysiology, but the signals are approximately 100 times weaker than cardiac potentials and overlap spectrally with motion artifacts, necessitating labor-intensive manual review that limits clinical scalability. We present an uncertainty-aware deep learning framework combining a signal reconstruction network with a parallel uncertainty estimation network to automate artifact correction in high-resolution BSGM. Models were trained on 2,398 multihour, 64-channel recordings from 27 international clinical sites using weak supervision, a physiology-aware loss function, and uncertainty-gated quality control. In an independent cohort of 127 patients, the system achieved relative reductions of 39% in signal reconstruction error, 9% in total data removed, and 23% in amplitude--movement correlation compared with the industry-standard Wiener filter. Improved signal fidelity altered automated clinical phenotyping in 7% of patients by recovering previously obscured gastric rhythms. Uncertainty-aware deep learning enables reliable automated artifact correction in body-surface gastric mapping, improving signal fidelity and enabling scalable clinical interpretation. The system is FDA-cleared (510(k) K252504) and deployed in clinical practice, demonstrating that data-driven artifact correction can meet regulatory requirements for medical devices and reduce dependence on specialist manual review.

The electrocardiogram (ECG) contains rich nonlinear and non-stationary dynamic information that is only partly captured by conventional ECG interpretation and beat-to-beat metrics, and is increasingly analyzed using black-box artificial intelligence models that often lack interpretability. Here, we introduce the ECG time-frequency "eyeball", an interpretable framework that transforms a brief single-lead ECG recording into a geometric signature and a set of low-dimensional rotational and geometrical features using empirical mode decomposition and Hilbert-based analytic signal mapping. In 30-second lead I-equivalent recordings from 170 healthy subjects and 80 patients with acute myocardial infarction (AMI), the proposed "eyeball" metrics significantly differentiated groups, with AMI associated with higher rotational frequency metrics, lower envelope metrics, and displaced centroid location. Representative examples revealed a coherent morphologic spectrum from normal patterns to geometries consistent with myocardial ischemia, injury, and infarction. The representation remained stable across recording windows from 30 seconds to 5 minutes, and individual "eyeball" features achieved areas under the receiver operating characteristic curve (AUCs) of up to 0.78 for AMI detection. These findings suggest that the ECG time-frequency "eyeball" condenses clinically relevant nonlinear ECG dynamics into an interpretable representation that may reveal hidden AMI signatures, complement conventional ECG interpretation, and provide a foundation for accessible single-lead cardiovascular screening using future smart wearables.

Deep learning reads 12 lead electrocardiograms at close to expert level on public benchmarks, yet most reports give one accuracy figure for the whole test set and stop there. We trained three architectures that are standard in this field, a 1D ResNet, a convolutional network with a bidirectional LSTM, and a convolutional network with a bidirectional LSTM followed by a transformer encoder, on the PTB-XL dataset to classify the five diagnostic superclasses, and then looked at how each one performed across sex and age. On the held out fold all three reached a macro AUC near 0.92, in line with the strongest published results on this benchmark, and the simplest model, the 1D ResNet, was marginally the best at 0.9241. The averages hid a steady pattern. Every model scored lower for female patients than for male patients, and every model scored lowest for patients aged 80 and over, where the 1D ResNet fell to 0.8878 and the transformer to 0.8693. Adding complexity did not close either gap and slightly widened the gap by age. Overall accuracy on PTB-XL is close to solved for these model families, but the benefit is not shared evenly, and a single headline number hides the patients a model serves worst. We release the full stratified evaluation to support fairness aware reporting.

Background: Outpatient chronic heart failure (HF) assessment relies on NYHA class and distance-based testing that can obscure physiological heterogeneity. Near-infrared spectroscopy (NIRS) enables tissue oxygenation phenotyping but is underexplored during standardized stressors in outpatient HF. We tested whether wearable NIRS-derived oxygenation kinetics during a vascular occlusion test (VOT) and six-minute walk test (6MWT) differ across NYHA classes. Methods: In this prospective, single-center pilot study, 44 chronic HF outpatients (mean age 70.9 {+/-} 8.7 years, 75% male; NYHA I [n=19], II [n=12], III [n=13]) were monitored with a novel wearable NIRS device (NIRSense Envello Core) during a VOT and 6MWT. Primary endpoints were the post-occlusion net area under the curve (net AUC; VOT) and post-walk recovery net AUC (modified 6MWT). Secondary endpoints included the exertional tissue oxygenation (Oxy) nadir, VOT reperfusion kinetics, gait metrics, and tolerability. Results: Despite NYHA I and II walking identical median distances (420 m), post-walk recovery net AUC was lower in NYHA II (-16.3 a.u.xs) and III (-12.8 a.u.xs) than NYHA I (46.1 a.u.xs, p=0.004). The exertional Oxy nadir did not differ (p=0.722), but NYHA III walked 27% and 38% slower than NYHA II and I (p<0.001). NYHA II had higher VOT net AUC (134.2 a.u.xs) than NYHA I (71.9; p=0.018) and III (61.1; p=0.011). Post-walk recovery net AUC correlated with gait velocity (rs=0.44) and distance (rs=0.39; both p<0.05). VOT net AUC did not correlate with functional metrics, but resting reperfusion kinetics correlated with 6MWT performance (rs=0.41-0.46, p<0.05). The sensor was well tolerated. Conclusions: Wearable NIRS-derived recovery kinetics differentiated NYHA I from NYHA II despite these classes walking identical median distances. Coupled with distinct resting VOT hyperemic differences, these preliminary findings indicate wearable NIRS may capture physiological heterogeneity in outpatient HF not reflected by NYHA class and standard functional metrics.

Autonomic dysfunction is a common sequela of mild traumatic brain injury (mTBI). Physical activity progression is an integral component of mTBI rehabilitation, particularly in addressing autonomic dysfunction. However, clinicians often rely on point-in-time evaluation of orthostatic and exercise intolerance to guide activity recommendations. Commercially available wearable devices (e.g., Fitbits) provide an opportunity to evaluate heart rate response to activity in a real-world setting. Previous work has used physiologic (heart rate) and activity (step count) data to identify subgroups of adults with stroke that may be used to guide activity recommendations. This method may be useful to subgroup youth post-mTBI to identify those who have abnormal physiologic responses to activity. We aimed to identify subgroups using heart rate and step count data in adolescents presenting for specialty care after diagnosed mTBI. Eighty participants aged 13-18 within six months of mTBI diagnosis were recruited to wear a Fitbit Sense 2. Data from seven days and two nights collected within fourteen days of enrollment were included. A group-based steps per minute (SPM) threshold (25th percentile; 10 SPM) and individualized heart rate threshold (20% heart rate reserve (HRR)) were used to classify each minute of active daytime data into one of four quadrants: SPM>10 & HRR>20% (QI), SPM<10 & HRR>20% (QII), SPM<10 & HRR<20% (QIII), and SPM>10 & HRR<20% (QIV). We used percentage of minutes in each quadrant, mean steps per day, percentage of minutes with zero steps, mean SPM in QI, and resting heart rate in a k-means clustering algorithm to identify subgroups. We evaluated subgroup differences by clustering variables using Kruskal-Wallis tests. Sixty-one participants were included. Three subgroups emerged: Sedentary (n=12), Active (n=23), and Atypically Elevated Heart Rate (AEHR; n=26). Subgroups varied significantly on all clustering variables (p<0.01). The Active subgroup took a high number of steps per day, had lower sedentary time, and had the highest activity intensity (mean SPM in QI). The Sedentary subgroup took fewer steps per day compared to the Active subgroup, had high sedentary time, and showed the highest resting heart rate. The AEHR subgroup took fewer steps per day compared to the Active subgroup and had high sedentary time. The AEHR subgroup also spent a higher percentage of time with an atypically high heart rate response to low levels of activity compared to the other subgroups. Our findings suggest that data from wearable devices can identify subgroups of adolescents with mTBI with distinct physiologic/physical activity profiles, which may ultimately be used to inform personalized activity prescriptions. Future work should aim to understand how the identified subgroups relate to longitudinal outcomes.

Background: Automatic tube compensation (ATC) was designed to compensate for the additional resistive load imposed by the endotracheal tube during spontaneous breathing. In ATC mode, the ventilator adds or subtracts the flow-dependent pressure drop across the tube during both inspiration and expiration so that tracheal pressure remains close to PEEP. Early prototype ventilators achieved true tracheal-pressure control and showed physiological and clinical benefits, but clinical studies with commercial systems have failed to confirm these earlier findings. A 2003 bench study found that commercial ventilators provided, at best, only partial tube compensation, unlikely to result in meaningful clinical benefit. We therefore tested whether this limitation has been remedied in contemporary ICU ventilators. Methods: We performed a bench comparison of five commercial ICU ventilators and an ATC prototype ventilator designed to accurately compensate for the flow-dependent resistance over a wide range of flow rates. An active lung simulator generated spontaneous breathing patterns with weak, moderate, and strong inspiratory efforts at different PEEP levels. We tested each breathing pattern through endotracheal tubes with inner diameters of 7 and 8 mm, and measured airway pressure, tracheal pressure, and flow during CPAP with and without ATC. Breathing through the tube against open atmosphere served as a zero-PEEP/T-piece reference. Results: In CPAP mode, the commercial ventilators showed flow-dependent airway-pressure deviations, amounting to a substantial added resistance of 1.5 - 6.5 mbar/(L/s), whereas the ATC prototype ventilator imposed an added resistance of only 0.6 mbar/(L/s). In ATC mode, the commercial ventilators reduced the resistive load by no more than by 25%, and large tracheal-pressure deviations remained, especially at higher inspiratory effort and during expiration. In some cases, the residual load during ATC was even greater than the load during unsupported breathing through the tube. By contrast, the ATC prototype ventilator maintained tracheal pressure close to PEEP throughout the breathing cycle and eliminated on average 79% of the tube-related resistive load. Conclusions: In the commercial ventilators evaluated in this study, the defining physiological objective of ATC was only partially achieved. Therefore, clinical benefits previously reported for tracheal-pressure control support should be interpreted with caution when applied to commercial ATC implementations, unless effective tube compensation has been demonstrated under relevant conditions. These findings suggest that more advanced control approaches, such as those implemented in the ATC prototype ventilator, may be required to achieve consistent and physiologically accurate tube compensation.

Heart rate (HR) and its variability (HRV), mediated by the autonomic nervous system are key indicators of diving physiology and behavioral state, in vertebrates. However, these indicators remain understudied in cetaceans due to the technical challenges of recording electrocardiograms (ECGs) underwater. To overcome these challenges, we developed a waterproof device based on an all-in-one suction-cup that integrate an ECG-accelerometer logger with bipolar electrodes. Using this device, we obtained high-resolution ECG signals in bottlenose dolphins (Tursiops truncatus, n=8), belugas (Delphinapterus leucas, n=2), and orcas (Orcinus orca, n=1) during breathing and apnea. This approach allowed us to highlight species-specific features of the ECG waveform, consistent with a biphasic T wave in the three species of cetaceans and a bifid P wave unique to belugas, which were independent from the respiration state. Resting surface HRs were 70 {+/-} 4 bpm in dolphins, 51 {+/-} 1 bpm in belugas, and 50 {+/-} 2 bpm in the orca and exhibited pronounced oscillation related to the mechanism of respiratory sinus arrhythmia. As expected, short apneas ([~] 1 min) induced bradycardia in all three species (53 {+/-} 5, 33 {+/-} 3, and 37 {+/-} 2 bpm, respectively). In dolphins this bradycardia was coupled with a significant decrease of the coefficient of variability of RR intervals, one of the indices of HRV. Moreover, we were surprised to observe HR oscillations throughout apnea, suggesting a persistent fluctuation of autonomic modulation. Thus, to better understand autonomic modulation in cetaceans we employed food (fishes, squids, gelatin, etc.) as a strong rewarding stimulus. For that we compared HR and HRV during 2-min of food deprivation versus continuous feeding periods. In dolphins, food deprivation produced no significant change in HR or HRV from resting surface values, whereas continuous feeding decreased HR of about 20 % and increased HRV metrics (StDRR, CVRR, RMSSD). Belugas showed similar responses, with a HR decline of about 40 % and an increase HRV indices. These findings established baseline HR and HRV parameters during breathing or apnea for three cetacean species and demonstrate that autonomic responses to appetitive stimuli can be non-invasively quantified, validating a novel tool to investigate cetacean cardiovascular physiology and environmental perception.

Background Hypertension is a major modifiable risk factor for atrial fibrillation (AF), yet blood pressure (BP) control remains suboptimal in older U.S. adults. Objectives This study evaluated how improve systolic BP (SBP) control could affect incident AF, downstream AF ablation demand, Medicare savings, and hospital revenue. Methods A population-based modelling framework was developed to estimate mortality and incident AF hazards across SBP strata: <120, 120-139, 140-159, and ?160 mm/Hg. AF incidence in the SBP <120 mmHg group was set at 2.2 per 1,000 person-year, with hazard ratios of 1.17, 1.42 and 1.64 applied to higher SBP strata. We assumed 25% of incident AF patients would undergo ablation, with a 7.2% complication rate. AF prevalence was projected to increase by 4.6% annually over 10 years. Medicare savings and hospital revenue foregone were estimated under varying procedure cost and contribution-margin assumptions. Results Higher SBP was associated with greater hazards of death and incident AF. Improved SBP control reduced projected AF incidence and ablation demand. Over 10 years, cumulative Medicare savings were projected at $8.7B-$10.9B across the full modelled population. However, reduced ablation volume translated into hospital revenue foregone, ranging from $75M to $377M in the first year, and approximately $1.03B-$5.2B cumulatively over 10 years. Conclusions Improved SBP control may reduce AF incidence, prevent avoidable invasive ablation procedures, relieve pressure on surgical waitlists, and generate substantial Medicare savings. However, these benefits may reduce hospital procedural revenue, highlighting a misalignment between prevention-oriented care and fee-for-service reimbursement incentives.

Background: Predicting 28-day mortality in ICU patients with alcoholic cirrhosis is challenging because clinical deterioration is dynamic and heterogeneous. Methods: Using MIMIC-IV (v3.1), this study included 1,907 patients (training n = 1,334; validation n = 573), engineering 208 temporal and static predictors from 64 base variables and reducing them to 40 through multi-stage selection. Seven classifiers and a weighted gradient-boosting ensemble (XGBoost, CatBoost, LightGBM) were compared with Optuna tuning. Results: The ensemble achieved the highest internal validation AUC (0.9276; 95% CI: 0.9011-0.9507) and lowest Brier score (0.0870), with strong discrimination on eICU-CRD (AUC 0.9347) and related MIMIC-III (AUC 0.9071). Ablation indicated that temporal features, especially deltas, were major contributors ({triangleup}AUC {approx} 0.17 when removed). SHAP highlighted APS III score, anion gap, oxygen saturation (delta), lactate, and INR as leading predictors. Conclusions: The framework supports interpretable, trajectory-informed risk stratification in critically ill cirrhotic patients; prospective validation is needed before clinical use.

**Background:** Acute pancreatitis (AP) is a common gastrointestinal emergency with a subset of patients progressing to severe acute pancreatitis (SAP), which carries substantial morbidity and mortality. Current clinical severity scores such as BISAP, APACHE II, Ranson, and the Modified CT Severity Index require upon 48 hours of observation before reliable assessment is possible, limiting early triage. Machine learning (ML) approaches using routine admission laboratory values may enable earlier, more accurate prediction. **Methods:** We evaluated 11 models spanning three architectural families classical ML (Logistic Regression, Random Forest, Gradient Boosting), feedforward deep learning (MLP, Residual MLP, Attention MLP), and recurrent deep learning (LSTM, Stacked LSTM, Bidirectional LSTM, LSTM+Attention, CNN-LSTM) on a Chinese AP cohort of 722 patients (585 severe, 137 mild) labelled according to the 2012 Revised Atlanta Classification. Performance was assessed via 5-fold stratified cross-validation using AUC-ROC, F1 score, sensitivity, specificity, and PPV, with decision thresholds optimised for maximal F1. **Results:** Random Forest achieved the highest AUC of 0.877 (F1=0.917, sensitivity=96.8%, PPV=87.1%), followed closely by Gradient Boosting (AUC=0.874, F1=0.918). Classical ML models consistently outperformed deep learning counterparts. CNN-LSTM was the best recurrent model (AUC=0.777) but remained inferior to all classical approaches. LSTM-family models produced AUC values of 0.684-0.777, reflecting the cross-sectional tabular nature of the data. **Conclusions:** Random Forest provides robust, high-sensitivity early prediction of SAP severity using routine admission data. External prospective validation is required before clinical deployment. **Keywords:** acute pancreatitis; severity prediction; machine learning; random forest; deep learning; LSTM; Revised Atlanta Classification; early triage

Background: Accurate REM identification is critical for diagnosing REM sleep behaviour disorder (RBD), yet many automated sleep staging systems, especially single-channel EEG models trained on healthy cohorts, do not generalise well to real-life polysomnography (PSG) performed in patients. Objective: To compare a feature-based Random Forest (RF) model tuned for RBD with a state-of-the-art single-EEG deep architecture (AttnSleep), and to assess the impact of cohort adaptation and multimodal inputs (EEG, EOG, EMG, ECG). Methods: Experiments used 89 multi-site in-clinic PSGs (SleepWearables Phase-1) plus 53 MASS healthy controls (mean age 63, std 5 years), with 10-fold cross-validation and out-of-fold evaluation. Model performance was assessed using Cohen's kappa, and attention-based modality analysis was performed to quantify signal contributions. Results: When applied out-of-the-box after training on open-source healthy datasets, both models achieved moderate agreement overall (Cohen's kappa = 0.46), but performance declined in RBD, particularly for REM sleep (AttnSleep Cohen's kappa = 0.19 vs RF Cohen's kappa = 0.44), highlighting limited cross-cohort generalisation. The multimodal model improved overall agreement (Cohen's kappa 0.59 - 0.60) and performance in RBD (Cohen's kappa 0.45 - 0.46), with gains most pronounced in REM (Cohen's kappa 0.45 - 0.49). Attention-based modality analysis identified EEG as the dominant signal, increased EOG contribution during REM, and elevated ECG importance during N3. In RBD subjects, EOG weighting increased relative to non-RBD controls (Delta = +0.081). Guided by these weights, a reduced four-channel EEG model matched full multimodal performance in non-RBD subjects, and adding EOG achieved the best overall configuration (Cohen's kappa = 0.61 overall; Cohen's kappa = 0.48 in RBD) with improved REM classification (53% vs 45% recall). Inclusion of EOG also reduced inter-dataset variability in REM staging. Nonetheless, staging performance in RBD remained lower than in controls, particularly for REM. Conclusions: These results highlight the limited generalisability of minimal-sensor models trained on healthy cohorts, the value of mixed cohort-specific training, and the benefit of multimodal integration and attention-guided channel selection, rather than minimal-sensor approaches alone, for robust clinical sleep staging in pathological populations such as RBD.

Background: Automatic sleep staging algorithms are increasingly applied in clinical and home-based recordings. However, their performance may degrade when transferred to new montages and clinical populations. This is particularly relevant in reduced-channel portable PSG and in disorders such as REM sleep behaviour disorder (RBD), where altered sleep architecture may challenge pretrained models. Objective: To evaluate and compare multiple open-source sleep staging algorithms on a minimal portable PSG setup in controls and patients with and without RBD, and to assess the impact of fine-tuning on clinic-ascertained data. Methods: Six open-source models were applied to 76 subjects recruited from three clinical sleep medicine sites. Performance was assessed using accuracy, F1 scores, and Cohen's kappa, both overall and per sleep stage. Each model was evaluated out-of-the-box and after fine-tuning on clinical data. Results: Out-of-the-box performance varied substantially across models (Cohen's kappa 0.21-0.54). Fine-tuning consistently improved agreement, with the best-performing model (GSSC) reaching Cohen's kappa = 0.58 indicating moderate to good agreement. Performance was highest in controls and lower in patient groups. N3 was the most reliably classified stage across models, whereas N1 remained consistently challenging. REM classification improved after fine-tuning in several architectures but remained model, and subgroup-dependent, particularly in RBD subjects. Conclusion: Fine-tuning substantially mitigates domain shift, updating model parameters to align with new data distributions, when applying automatic sleep staging algorithms to portable clinical recordings. Model architecture influences robustness, with feature-learning approaches demonstrating greater adaptability than fixed-feature models. Despite moderate agreement after adaptation, performance, especially for REM and N1 remains insufficient for fully automated diagnostic use in clinical populations.

Background. Cardiopulmonary exercise testing (CPET) is a gold-standard test used to evaluate cardiopulmonary fitness and overall health by measuring physiological responses such as oxygen consumption during exercise. While traditional CPET warm-ups are typically low-intensity aerobic activities, alternative methods like coherence breathing may also prepare the body by influencing autonomic regulation. Breathing-based interventions have shown potential to improve heart rate recovery and performance, and heart rate variability (HRV) serves as a useful non-invasive indicator of autonomic nervous system activity. However, there is limited research on how brief breathing exercises before CPET affect outcomes. This study aims to investigate the effects of coherence breathing on oxygen uptake, HRV, and post-exercise heart rate recovery Objective. This study will aim to compare the acute cardiopulmonary and autonomic responses of coherence breathing versus spontaneous breathing immediately preceding cardiopulmonary exercise testing (CPET) in recreationally active healthy adults. Methods. This study will be a randomized counterbalanced crossover design. Healthy adults aged between 19 and 45 years of age will complete two separate CPETs over two non-consecutive test days (between 48 hours and 7days). During each visit, participants will complete five minutes of slow-paced coherence breathing (6 breaths per minute) or spontaneous breathing at normal breathing rate, followed by an incremental treadmill CPET protocol up to maximal exertion. HRV will be assessed at baseline, during the breathing interventions, and during cool-down for 5 minutes using the Emwave Pro Plus software. Gas exchange during the CPET protocol will be measured continuously using the VO2 Master Pro system. immediately after, and after 5 minutes of resting. The primary outcomes will be peak oxygen consumption and heart rate variability indices. Secondary outcomes will include heart rate recovery, peak heart rate, time to exhaustion, rate of perceived exertion and readiness, blood pressure, tidal volume, peak ventilation, and respiration rate. Analyses will use linear mixed-effects models and paired comparisons. Discussion. This protocol will determine whether pre-exercise coherence breathing can improve cardiopulmonary and autonomic nervous system responses to maximal performance. Findings may have practical implications for exercise testing and performance procedures as well as improving our understanding of pre-exercise breathing strategies for priming the autonomic and cardiopulmonary systems.

Residual congestion is the principal driver of heart failure readmission, and reliable serial assessment of volume status remains an unmet clinical need. This study asked whether a wrist-worn, machine-learning-based device for non-invasive venous waveform analysis in heart failure (the NIVAHF device), which produces an integer-scaled estimate of pulmonary capillary wedge pressure termed the NIVA Score, responds to acute changes in volume status. Agreement between the NIVA Score and invasively measured pulmonary capillary wedge pressure at single time points has been established in a separate prospective, multi-site study; however, such static agreement does not establish whether the measure tracks dynamic decongestion. We therefore evaluated the directional responsiveness of the locked NIVA Score in two prespecified cohorts: hospitalized adults with acute decompensated heart failure undergoing routine intravenous diuresis, and a controlled porcine model of volume overload followed by diuresis. In eleven patients contributing thirteen paired measurements (mean net fluid balance -2.1 {+/-} 1.0 L), NIVA Scores decreased significantly after diuresis (paired t-test, P = 0.04). In five pigs contributing twenty-four paired measurements, NIVA Scores decreased significantly after intravenous furosemide following crystalloid loading (P < 0.01), and the direction of change was concordant with measured urine output in every animal. Statistical significance was reached in both cohorts despite modest sample sizes, indicating a measurable NIVA Score reduction with volume removal. In an exploratory analysis, the discharge NIVA Score yielded an area under the receiver-operating-characteristic curve of 0.85 (95% confidence interval 0.575-1.00; P = 0.04) for thirty-day readmission. Together, the significant, directionally concordant NIVA Score reductions across independent clinical and preclinical cohorts demonstrate that the device tracks acute decongestion and support its use for serial, non-invasive congestion monitoring; an adequately powered prospective study is the planned next step.

Introduction: Standardizing fluid and vasopressor resuscitation in sep- tic shock is challenging due to patient heterogeneity. We trained a causal model to identify optimal dosing during the first six hours of intensive care unit (ICU) admission. Methods: Graphical causal inference models were applied to estimate het- erogeneous treatment effects. Grounding models in expert clinical knowl- edge minimizes bias from spurious correlations to generate robust, contextu- ally meaningful recommendations. Our model was trained on 1,702 MIMIC database admissions and externally validated on 1,434 eICU admissions. Pri- mary outcomes were in-hospital survival and 24-hour clinical improvement (SOFA score reduction of two points or more). Findings: The cohort comprised 3,136 participants (median age 65 years [IQR 53-75]; 42.7% female). Deviation from vasopressor recommendations was associated with increased in-hospital mortality (median OR 5.61, 95% CI 5.44-5.78) and failed clinical improvement (median OR 6.33, 95% CI 6.17-6.50). Fluid deviations yielded corresponding median ORs of 1.02 (95% CI 1.02-1.02) and 1.14 (95% CI 1.14-1.14). In external validation, the model achieved a median survival AUROC of 0.73 (95% CI 0.69-0.77) and clini- cal improvement AUROC of 0.69 (95% CI 0.66-0.72), matching predictive baselines. Treatment effects were heterogeneous: optimal fluids increased survival by up to 4% in low-severity subgroups, while vasopressor responses varied from 0.5% to 17% across acute severity levels. Sensitivity analyses across 36 scenarios confirmed primary associations in 33 cases (91.7%). Interpretation: Recommendations from expert-grounded causal models correlate with improved septic shock outcomes in external validation, cap- turing significant heterogeneity in patient response.

Background Perioperative incidents such as hypoxic cardiac injury often have subtle or nonspecific clinical manifestations. Reduction in myocardial oxygenation precedes biochemical changes, as well as electrical and functional changes. Photoacoustic imaging (PAI) is a modality that uses laser irradiation of tissue to generate ultrasonic waves, enabling spatially resolved quantitative mapping of oxygenated and deoxygenated haemoglobin. We investigated the utility of PAI for real-time monitoring of myocardial and great vessel oxygenation. Methods Male CD-1 mice were anaesthetised, and photoacoustic and simultaneous B-mode images were acquired of the myocardium and right ventricular outflow tract (RVOT), the pulmonary artery, and aorta. PAI was performed at fractional inspired oxygen levels (FiO2) of 100%, 21%, and then 10%. Separate cohorts of mice were exposed to increasing intravenous doses of either combined phenylephrine and isoprenaline, or individual administration of vasoactive or adrenergic agents. Results PAI reliably distinguished changes in oxygenation in the RVOT cavity, pulmonary artery, aorta, and myocardium. PAI detected hypoxia-induced changes in oxygenation, revealing greater desaturation in the myocardium than in the RVOT (-9.85%, 95% CI -14.94 to -4.77, P<0.0001). Escalating doses of phenylephrine and isoprenaline caused a progressive desaturation of the myocardium and RVOT (mean [95% CI]; myocardium 16 mg/kg: -14.64% [-27.62 to -1.65], P=0.0038 and RVOT 32 mg/kg: -18.71% [-32.15 to -5.27], P=0.0003). Myocardial deoxygenation was detected before changes in systolic function or electrical abnormalities. Conclusions This work demonstrates that PAI can reliably monitor cardiac oxygen desaturation, potentially offering an earlier warning of cardiac dysfunction and injury compared to existing monitoring tools. Keywords: Echocardiography, hypoxaemia, hypoxia, myocardial injury, oxygenation, perioperative monitoring, photoacoustic imaging

Background and Objective: Indications for right ventricular assist device (RVAD) insertion include right heart failure after implantation of a left ventricular assist device or early graft failure following heart transplantation. This study aimed to investigate how the upstream and downstream circulatory network interacts with the Impella RP(R) device. Methods: A numerical model of the Impella RP(R) was implemented within CARDIOSIM(C) software platform for this study. In the numerical configuration, the RVAD aspirated blood from either the right atrium (RA-PA connection) or the right ventricle (RV-PA connection) and delivered it to the pulmonary artery. Only RA-PA connection is the currently used setting for Impella RP(R) in clinical practice. Based on right ventricular (RV) decompression and total flow, our study may help define the need for a direct RV-unloading Impella RP(R). Results: The simulations showed that activating the RVAD in RA-PA mode, regardless of its rotational speed, the mean pulmonary artery pressure (PAP) percentage change was higher than the unsupported condition when the mean systemic venous pressure (SVP) and the pulmonary artery wedge pressure (PAWP) were both set to 20 mmHg. When RV-PA connection was applied, a similar trend was observed although the PAP percentage changes were about halved compared to the RA-PA connection. Conclusions: The Impella RP(R) has the potential to become a valid option for RV support based on current experimental and simulation data. Although already in use, further evaluation in the clinical setting will likely confirm its potential and lead to a more routinely application for RV support.