The trial was motivated by a persistent diagnostic dilemma that emergency physicians confront daily. Syncope, commonly known as fainting or a blackout, is defined as a transient loss of consciousness caused by a temporary reduction in blood flow to the brain. While most episodes are benign, arising from reflex responses such as vasovagal faints, postural hypotension, or dehydration, a proportion are triggered by potentially life-threatening cardiac rhythm disturbances. These malignant arrhythmias, which may include intermittent high-grade atrioventricular block, sustained ventricular tachycardia, or pauses in the heart’s natural pacing, can announce themselves with a single collapse before settling into silent intervals. The intermittent nature of these rhythm disturbances makes them notoriously difficult to catch.

“It can be difficult to determine the cause of syncope in the ED as many rhythm disturbances occur intermittently and are no longer present by the time patients arrive in hospital. Some patients then have to wait weeks or even months for investigations,” said Professor Matthew Reed of The Usher Institute in Edinburgh, UK, the trial’s Principal Investigator. His comments capture a well-recognised gap in the syncope pathway. By the time a patient reaches hospital, the heart rhythm has usually reverted to normal, leaving the electrocardiogram performed in the department unrevealing. Preliminary evidence before the trial had hinted that cardiac monitoring initiated during the emergency department visit could improve arrhythmia detection, but rigorous outcome data were lacking, leaving clinicians to improvise referral pathways that varied widely between institutions.

ASPIRED was designed to close that evidence gap. The trial was conducted at 45 hospitals across the UK, making it the largest randomised trial to date evaluating immediate ambulatory ECG monitoring in this population. Adults whose syncope remained unexplained after a full evaluation in the emergency department were randomised in a 1:1 ratio to either 14 days of continuous ambulatory cardiac monitoring or to the standard management practice of their hospital. That comparator arm matters, because in usual practice, patients with unexplained syncope are typically discharged with outpatient follow-up, and the timing of any subsequent Holter monitoring, loop recorder implantation, or electrophysiological assessment depends heavily on local resources and waiting lists.

Those assigned to monitoring received a small, waterproof, leadless, non-invasive device that recorded their cardiac rhythm continuously for two weeks. The design deliberately favoured wearability over complexity: patients could shower, sleep, and carry on with ordinary activities while the monitor captured every heartbeat. Participants were instructed to press a button on the monitor if they experienced another fainting episode, allowing the recording to be flagged for symptom-rhythm correlation, a crucial step in establishing whether a detected arrhythmia actually caused the syncope rather than merely coinciding with it. All patients in both arms were asked to keep a paper diary recording any syncopal events, providing a uniform method for counting recurrences across the two study groups.

In total, 2,233 patients were analysed, with a mean age of 58.3 years and 48% female. This cohort reflects a broad middle-aged and older adult population attending emergency departments, precisely the group in whom distinguishing a benign faint from the first manifestation of cardiac disease is most consequential. The trial’s primary endpoint was the number of self-reported syncope episodes over one year, a patient-centred measure chosen because recurrent fainting drives much of the anxiety, injury risk, and loss of independence associated with the condition.

On that primary measure, the intervention made no significant difference. Patients in the monitoring group reported a mean of 1.37 episodes compared with 1.58 in the standard care group, an incidence rate ratio of 0.89 with a 95% confidence interval of 0.68 to 1.18 and a p-value of 0.43. In other words, wearing the monitor did not prevent people from fainting again. The confidence interval, which spans well below and above unity, indicates genuine statistical uncertainty around a modest possible effect rather than a clear absence of benefit, but the trial was honest in reporting that its headline goal was not met.

The secondary findings, however, painted a very different picture of the technology’s value. Monitoring more than doubled the detection of clinically significant cardiac arrhythmias, identifying them in 22% of monitored patients versus 9% of those receiving standard care. Put another way, roughly one in five patients fitted with the device had a dangerous rhythm disturbance uncovered that would otherwise have remained hidden, at least temporarily. The magnitude of this diagnostic gain is striking given that both groups contained patients with the same entry criteria and comparable baseline risk.

Diagnosis also came substantially sooner: the median time to diagnosis was 22 days with monitoring compared with 55 days under usual practice. For patients and families, those extra weeks of waiting are not a neutral experience; they are filled with restrictions on driving, work, and daily activities, alongside the persistent fear of another collapse. For clinicians, a faster diagnosis shortens the window during which an untreated malignant arrhythmia might strike. That acceleration translated directly into treatment. A higher proportion of monitored patients received appropriate interventions, including pacemaker implantation in 6.8% versus 4.6%, and anti-arrhythmic therapy in 10.8% versus 7.3%. Pacemakers, which maintain the heartbeat when the heart’s intrinsic electrical system falters, and anti-arrhythmic drugs, which suppress dangerous rapid rhythms, are established therapies whose benefit depends on identifying the right patients in time.

Perhaps the most striking result was the mortality signal. At one year, all-cause death occurred in 1.5% of the monitoring group compared with 2.9% of the standard care group, a relative reduction of approximately 50%. While the absolute numbers are small, reflecting the overall low one-year death rate in this population, the direction and size of the difference are consistent with the plausible mechanism: earlier detection of lethal rhythm disturbances leading to earlier definitive treatment. The investigators also noted that patients reported very high acceptability of the wearable device, an important consideration for any strategy that depends on patients wearing equipment for two consecutive weeks in daily life. A monitoring programme is only as good as its adherence rates, and the trial’s findings on tolerability suggest the approach is practical at scale.

“Although immediate ECG monitoring did not reduce recurrent fainting, it enabled earlier identification of serious cardiac rhythm disorders, allowing patients to receive treatment much sooner, reducing uncertainty and anxiety, and potentially preventing avoidable deaths,” Professor Reed summarised. The disconnect between the primary and secondary outcomes is instructive rather than contradictory. Many syncopal episodes have benign reflex or circulatory causes that monitoring would be unlikely to eliminate, so preventing recurrent fainting was perhaps an ambitious target for a diagnostic device. Detecting the dangerous minority of cases, by contrast, is exactly what continuous rhythm recording is designed to do, and the trial suggests it succeeds at that task with considerable margin.

The implications for health systems are considerable. If early monitoring is adopted as routine emergency department care for unexplained syncope, a large share of the roughly 650,000 annual UK syncope attendances could be assessed with a device that patients wear at home, potentially shortening or avoiding the current wait of weeks or months for conventional investigations. This shift could relieve pressure on outpatient cardiology services, which currently absorb these referrals at variable speed, and could reduce repeat emergency attendances from patients who faint again while awaiting answers. Earlier pacemaker implantation and anti-arrhythmic treatment could prevent serious adverse events, including injury from falls during faints and, in the worst cases, sudden cardiac death, in patients whose fainting is the first warning sign of a treatable arrhythmia.

At the same time, important questions remain. The mortality reduction was observed, not pre-specified as a trial-proven causal endpoint, and Professor Reed acknowledged that further research should explore the observed survival benefit before firm conclusions are drawn. Observational signals of this kind can be influenced by chance, by imbalances between randomised groups, or by treatment pathways that correlate with other aspects of care. It is also unclear whether the approach is cost-effective across different health systems, which patients benefit most, and whether shorter or longer monitoring windows might perform better. Some arrhythmias occur infrequently enough that 14 days may miss them, while for others a shorter period might suffice at lower cost. The trial population consisted of adults whose syncope was unexplained after emergency department evaluation, so the results may not generalise to patients whose cause is already established at presentation, such as those with obvious vasovagal features or an abnormal initial ECG pointing to a specific diagnosis.

Even with those caveats, ASPIRED provides the most robust evidence to date that a simple, wearable ECG monitor, applied at the point of emergency care, can transform the diagnostic pathway for unexplained fainting. By converting a period of anxious uncertainty into a rapid, actionable diagnosis for the one in five monitored patients found to have a significant arrhythmia, the strategy offers clinicians a practical tool to identify and treat the dangerous cardiac causes of syncope before they claim a life. The authors suggest that early monitoring should now be considered as part of routine emergency department care for unexplained syncope, with future studies tasked with confirming the mechanisms behind the survival advantage. If those confirmatory efforts bear out the one-year mortality findings, the humble wearable ECG patch could become as standard a part of the syncope workup as the electrocardiogram already is, and the weeks of waiting that currently define this pathway could become a relic of an earlier era of cardiac medicine.

Central venous pressure reflects the pressure in the right atrium and is widely used as an indicator of venous return, cardiac function, and a patient’s response to fluids or vasoactive medications. The conventional reference method requires placement of a central venous catheter, an invasive procedure that can cause bleeding, infection, thrombosis, pneumothorax, or other complications. Although catheterization remains essential for many critically ill patients, it may be unsuitable or technically difficult in people with coagulopathy, infection, distorted anatomy, or limited venous access. Noninvasive alternatives based on physical examination or intermittent ultrasound can provide valuable information, but they are often operator-dependent and do not deliver uninterrupted monitoring. The new system is designed to bridge that gap by combining a neck-worn imaging device with automated interpretation.

At the center of the platform is an ultra-thin, 128-element linear-array ultrasound transducer developed to sit comfortably over the right side of the neck. The probe operates at a center frequency of 8.5 megahertz, a range that provides a balance between fine spatial resolution and sufficient penetration to visualize the internal jugular vein and common carotid artery. These vessels are important because the internal jugular vein connects directly to the right atrium without intervening valves. Changes in its cross-sectional area can therefore reflect variations in right-sided filling pressure and central venous pressure. The adjacent common carotid artery provides an anatomical reference that helps normalize measurements for differences in probe placement, body habitus, and neck geometry.

The patch’s engineering is intended to preserve image quality during prolonged use. Its acoustic structure includes a dual-layer matching system and a customized backing layer, producing an 85% fractional bandwidth and high sensitivity across a broad range of frequencies. A solid hydrogel coupling material maintains acoustic transmission between the probe and skin without requiring a liquid gel that can dry, leak, or become uncomfortable over time. The electronics and transducer are enclosed in silicone, allowing the device to remain attached while patients move or receive routine care. In feasibility testing, the patch was worn for as long as 24 hours while maintaining stable imaging and acceptable skin comfort, raising the possibility of near-continuous vascular surveillance rather than occasional manual examinations.

Continuous ultrasound, however, generates far more information than a clinician can realistically inspect frame by frame. The device produces cine-loop videos of the jugular vein and carotid artery, and each recording may contain thousands of individual images. To automate this process, the researchers created a semi-supervised artificial-intelligence model called the dual-decoder spatiotemporal attention network, or DSTA-Net. Instead of requiring experts to outline the vessels in every frame, the model uses manual annotations for only about 10% of the images. These key frames correspond to points at which the internal jugular vein is near its maximum or minimum dilation, providing highly informative examples of the vessel’s changing geometry.

DSTA-Net learns from the remaining unlabeled frames through a dual-decoder consistency strategy. A shared encoder first converts each ultrasound image into features that represent vessel boundaries, texture, and surrounding anatomy. Two separate decoders then interpret those features in complementary ways: one incorporates temporal attention to track how structures evolve across consecutive frames, while the other uses a lighter pathway to generate an independent segmentation. The model is trained to make the two pathways agree, allowing unlabeled images to serve as additional learning signals. This approach avoids relying on a continuously updated teacher model, a technique that can be vulnerable to unstable or incorrect predictions in noisy ultrasound data. By exploiting the natural temporal continuity of the cine-loop, the network can follow vessel motion while reducing the annotation burden for medical experts.

Testing indicated that the system could segment the internal jugular vein more accurately than several established deep-learning approaches. On an internal dataset, DSTA-Net achieved a Dice similarity coefficient of 83.5%, while its score on an external dataset was 75.8%. The Dice coefficient measures the overlap between the region identified by an algorithm and the region outlined by an expert, with higher values indicating closer agreement. According to the study, the model improved on the strongest fully supervised baselines, including UNet, Swin-UNet, and DeepLabV3+, by approximately 12 percentage points internally and 9 points externally. It also outperformed semi-supervised systems including UniMatch, DWL, and AllSpark. The model’s derived vascular measurements showed Spearman correlation values above 0.88 for most parameters, and Bland–Altman analyses indicated percentage errors well below the commonly cited 30% threshold for clinical agreement.

The segmented images were converted into five vascular indices: the maximum area of the internal jugular vein, its minimum area, the area of the common carotid artery, the ratio between the maximum jugular and carotid areas, and a jugular-vein area ratio reflecting dynamic changes over time. These measurements were combined with age, body mass index, blood pressure, and heart rate in a second artificial-intelligence system known as a dual-modality multilayer perceptron, or DM-MLP. Unlike image-focused architectures such as convolutional ResNets or vision Transformers, the DM-MLP was designed for structured clinical data. Its Attribute-Mixing operation models relationships among different clinical features, while Case-Mixing refines how each feature is represented across patients. The resulting low-rank architecture uses relatively few parameters while retaining the ability to capture nonlinear interactions, and it outperformed ResNet, DenseNet, and Transformer-based alternatives by roughly 4% to 8% in area under the curve.

The clinical evaluation included 349 intensive-care patients, with 272 enrolled at Shanghai Sixth People’s Hospital and 77 at Shanghai Tenth People’s Hospital. The principal target was elevated CVP, defined as a pressure of at least 8 millimeters of mercury. The model reached an AUC of 0.91 on the internal test set and 0.87 on the external test set, indicating strong discrimination between patients above and below the threshold. Additional analyses using thresholds of 7 and 9 millimeters of mercury produced similarly robust results. SHAP-based interpretability analysis suggested that the ultrasound-derived variables, especially maximum internal jugular vein area and the jugular-to-carotid ratio, contributed more strongly to the predictions than conventional variables such as blood pressure and body mass index. The system processed images at approximately 32 frames per second, or about one frame every 30 milliseconds, on a hospital server, enabling near-real-time analysis.

The researchers stress that the technology is not intended to eliminate central venous catheters in every clinical situation. Instead, it could provide a rapid, repeatable assessment when catheterization is contraindicated, delayed, or unnecessary, and could help identify rising venous pressure before a patient undergoes an invasive procedure. The study remains an early demonstration: its cohort is modest for training modern AI systems, it evaluates diagnostic performance rather than whether the technology improves survival or treatment decisions, and some aspects of the semi-supervised model remain difficult to interpret. Future work will expand the number of participating hospitals, test direct prediction of continuous CVP values rather than categories, add interpretability methods such as Grad-CAM, and assess whether AI-guided monitoring changes fluid and vasopressor management. By uniting wearable ultrasound, temporal image analysis, and clinical prediction, the platform brings automated noninvasive hemodynamic monitoring closer to routine use in acute and critical care.

Subject of Research: Wearable ultrasound and artificial intelligence for noninvasive central venous pressure monitoring in intensive-care patients.

Article Title: AI-Enabled Wearable Ultrasound for Noninvasive Central Venous Pressure Monitoring

News Publication Date: August 8, 2026

Web References: DOI: 10.34133/cbsystems.0653

References: Cyborg and Bionic Systems, “AI-Enabled Wearable Ultrasound for Noninvasive Central Venous Pressure Monitoring.”

Image Credits: Liping Zhang, Department of Emergency Medicine, Shanghai Sixth People’s Hospital, Shanghai Jiao Tong University School of Medicine.

Keywords: wearable ultrasound, artificial intelligence, central venous pressure, internal jugular vein, common carotid artery, intensive care, medical imaging, semi-supervised learning, DSTA-Net, DM-MLP, noninvasive monitoring, hemodynamics

At the core of this technology lies an ingeniously designed enclosed chamber that rests immediately next to the skin surface but avoids direct physical coupling. This chamber captures the subtle fluxes of vaporized molecular substances that naturally diffuse in and out of the skin. These molecular streams—comprising water vapor, volatile organic compounds (VOCs), and carbon dioxide—play critical roles as biomarkers in physiological and pathological processes. By continuously assessing changes in the microclimate within this chamber, the device unlocks a wealth of information about the wearer’s health status and environmental exposures.

The system integrates a sophisticated collection of wireless sensors capable of quantifying the minute changes in molecular concentration and environmental parameters inside the chamber with impeccable precision. This sensor suite is enhanced by a programmable bistable valve mechanism, which orchestrates dynamic control over the chamber’s access to ambient air. By alternately opening and sealing off the chamber, the device induces a time-dependent transient response. Analysis of these sensor readings during controlled exposure and isolation phases enables the differentiation and quantification of inward and outward molecular fluxes, a feature highly valuable in both clinical diagnostics and environmental monitoring.

This non-contact operational mode introduces a transformative advantage in scenarios where maintaining an unbroken skin barrier is paramount. Conventional wound monitoring devices often require direct contact, bearing a risk of further damage to delicate or infected tissue. Here, the new wearable technology mitigates such concerns by relying on proximity without contact, thereby preserving tissue integrity and enabling more frequent and safer monitoring of wound healing progression.

The system’s ability to detect and measure fluxes of water vapor holds particular clinical relevance. Water vapor emanating from the skin correlates with hydration status, inflammation, and metabolic activity. In wound healing contexts, changes in water vapor flux can signify the transition between different healing phases or the onset of infection. Alongside this, the device’s sensitivity to volatile organic compounds enables the detection of biochemical signatures indicative of tissue necrosis, bacterial colonization, or metabolic imbalances, offering a non-invasive window into underlying physiological changes.

Carbon dioxide flux measurement adds yet another dimension to the monitoring capabilities of the wearable platform. Because elevated or diminished CO₂ emission rates relate closely to local metabolic rate and perfusion status, analyzing these fluxes allows researchers and clinicians to infer tissue viability and the efficiency of blood supply. This multifactorial sensing approach, combining water vapor, VOCs, and CO₂, therefore provides comprehensive, multiplexed data streams essential for nuanced clinical insight.

The validation studies conducted using models of healing dermal wounds in both healthy and diabetic mice have produced compelling data. Diabetic wounds notoriously exhibit delayed or aberrant healing dynamics, and the device successfully captured characteristic variations in molecular flux that distinguished these pathological conditions from normal healing trajectories. Moreover, the system demonstrated acute sensitivity to infection-induced shifts in molecular emissions, reinforcing its potential utility for early detection and intervention in wound management protocols.

An additional strength of this technology is its wireless operational framework. By integrating low-power, miniaturized sensors and communication modules, the device eliminates the need for tethered connections, drastically enhancing patient comfort and compliance. This wireless capability also facilitates real-time, remote monitoring, enabling healthcare providers to track wound healing progression or environmental exposures continuously without necessitating in-person visits.

This pioneering device platform represents a paradigm shift in wearable biosensing, driving a transition from invasive or contact-dependent modalities toward a sophisticated, non-contact interface that respects the fragility of human skin and wounds. Its modular design and programmability make it adaptable for a spectrum of applications beyond wound care, including athletic performance monitoring, environmental toxin exposure assessment, and potentially early detection of systemic illnesses through epidermal molecular profiling.

Future research may explore further miniaturization and integration with advanced data analytics powered by machine learning, enabling personalized health insights derived from the complex, time-varying molecular flux data. Moreover, expanding the range of detectable molecular species could unlock new diagnostic possibilities, enhancing the device’s clinical versatility. The innovation distinguishes itself by bridging the gap between fundamental physiological monitoring and practical, user-friendly wearable devices.

In summary, the development of this non-contact wearable device represents a significant leap forward in biosensing technology, offering unprecedented accuracy and safety in measuring epidermal molecular flux. Its multifunctional sensor suite and dynamic environmental control through a bistable valve provide a novel approach to capturing transient molecular signals that reflect physiological and pathological states. This technological leap stands to revolutionize patient monitoring, diagnostics, and personalized care methodologies, with broad implications across medicine, environmental health, and beyond.

As wearable technology continues to evolve, embracing such non-invasive and decoupled sensing strategies will be critical for overcoming existing limitations. By enabling continuous, precise, and non-disruptive monitoring, this platform paves the way toward a future where wearable devices become integral, seamless components of healthcare ecosystems. The research reflects an inspiring intersection of materials science, engineering, and biomedical applications, illustrating the powerful impact of interdisciplinary innovation.

This landmark study, detailed comprehensively in Nature, invites further exploration and refinement, while capturing imaginations with its clever use of physical decoupling to open a window into the body’s molecular landscape without ever touching it. The promise of such technology to transform how clinicians and researchers quantify and interpret epidermal molecular flux marks a new chapter in wearable biosensors and personalized medicine.

Subject of Research: Non-contact wearable device platforms for monitoring epidermal molecular flux.

Article Title: A non-contact wearable device for monitoring epidermal molecular flux.

Article References:
Shin, J., Song, J.W., Flavin, M.T. et al. A non-contact wearable device for monitoring epidermal molecular flux. Nature 640, 375–383 (2025). https://doi.org/10.1038/s41586-025-08825-2

Image Credits: AI Generated

DOI: https://doi.org/10.1038/s41586-025-08825-2