Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2408.08316

SepAl: Sepsis Alerts On Low Power Wearables With Digital Biomarkers and On-Device Tiny Machine Learning

Marco Giordano·Kanika Dheman·Michele Magno
View original source ↗Read source document ↗Export metadata ↓

Abstract

Sepsis is a lethal syndrome of organ dysfunction that is triggered by an infection and claims 11 million lives per year globally. Prognostic algorithms based on deep learning have shown promise in detecting the onset of sepsis hours before the actual event but use a large number of bio-markers, including vital signs and laboratory tests. The latter makes the deployment of such systems outside hospitals or in resource-limited environments extremely challenging. This paper introduces SepAl, an energy-efficient and lightweight neural network, using only data from low-power wearable sensors, such as photoplethysmography (PPG), inertial measurement units (IMU), and body temperature sensors, designed to deliver alerts in real-time. SepAl leverages only six digitally acquirable vital signs and tiny machine learning algorithms, enabling on-device real-time sepsis prediction. SepAl uses a lightweight temporal convolution neural network capable of providing sepsis alerts with a median predicted time to sepsis of 9.8 hours. The model has been fully quantized, being able to be deployed on any low-power processors, and evaluated on an ARM Cortex-M33 core. Experimental evaluations show an inference efficiency of 0.11MAC/Cycle and a latency of 143ms, with an energy per inference of 2.68mJ. This work aims at paving the way toward accurate disease prediction, deployable in a long-lasting multi-vital sign wearable device, suitable for providing sepsis onset alerts at the point of care. The code used in this work has been open-sourced and is available at https://github.com/mgiordy/sepsis-prediction

Explore related subjects

q-bio.TOcs.LG

Keep this discovery

BibTeXRIS

Marco Giordano, Kanika Dheman, Michele Magno. 2024-07-31. SepAl: Sepsis Alerts On Low Power Wearables With Digital Biomarkers and On-Device Tiny Machine Learning. https://doi.org/10.1109/jsen.2024.3424655

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Adaptive therapy under parametric, structural, and measurement uncertainty

Adaptive therapy has emerged as a promising treatment strategy that exploits within-tumour competition to delay disease progression. Implementation, however, typically relies on indirect measurements of tumour burden and must account for potentially substantial patient heterogeneity. In this work, we capture patient-to-patient variability, parameter uncertainty, and imperfect biomarker measurements with a mathematical and statistical model that we calibrate to clinical prostate cancer data using a Bayesian inference framework. We use the resulting virtual cohort to demonstrate that, within the simple but now well-established Lotka-Volterra-based model, adaptive therapy robustly improves time-to-progression for the subset of patients that are predicted to eventually progress by the model. To account for other risk factors associated with larger tumour volumes, we introduce a new metric based on the risk of metastasis that demonstrates how adaptive therapy may be disadvantageous when sustained tumour burden is also considered. Given the ubiquity of uncertainty in oncology, we then describe several future modelling directions that also capture uncertainty in the temporal evolution of the underlying tumour or biomarker dynamics. Finally, we demonstrate how model misspecification and non-identifiability can lead to unreliable predictions, especially if uncertainty is inadequately captured.

q-bio.TO↗
arXiv2026

Head Impact Characterization and Cellular Response of a Live-neuron cell-integrated Biomechanical Full-body Surrogate Model

In this study, we develop a novel integrated framework that links the impact response with cellular dynamics using a live-neuron cell-integrated biomechanical full-body surrogate model. The impact event is simulated by allowing the surrogate model to fall from controlled seated release angles of 30-degree, 60-degree, and 90-degree. Three vertically stacked cell-culture Petri dishes, each containing live SH-SY5Y neuroblastoma cells, were placed inside the head of a commercially available surrogate model. The dynamic response of the impact event was evaluated using acceleration measurements from six accelerometers, comprising three sensors mounted on the head surface and three embedded in series with the cell stacks, along with kinematic measurements of the fall and deformation of the head model. In parallel, an OpenSim-based modified musculoskeletal model was used to simulate the fall experiment. We found that variation in contact stiffness produced the largest change in the predicted head acceleration in the simulation. When the cellular response and the measured accelerations are compared, oxidative stress and cell viability showed trends consistent with the regional acceleration and angle of fall. At the 90-degree fall, where median peak linear accelerations ranged from 170-258g, and the maximum headform deformation was approximately 9.4 mm, oxidative stress increased to approximately twice that of the control sample. We also quantified the cellular drift of SH-SY5Y cells, which is focal in nature for the 90-degree impact condition. The corresponding fall scenarios were also simulated in OpenSim and a preliminary calibration relationship was developed to compare the kinematic responses of the physical surrogate and musculoskeletal model. Finally, the framework provides a basis for relating experimental surrogate measurements to human head-neck response during impact.

q-bio.TO↗
arXiv2026

History Matters: Damage-Mediated Amplification of Brain Deformation and Injury Risk under Repeated Head Impacts

Computational head models are typically applied to isolated impacts, leaving repeated head loading largely unexplored. An Ogden-Roxburgh Mullins damage formulation was implemented in a high-fidelity finite element head model to represent loading-history-dependent softening during cyclic brain-tissue deformation. Repeated-loading histories derived from mixed martial arts head-impact data were applied and compared with damage-free hyperelastic (HE) and linear visco-hyperelastic (LVHE) model variants. Under five identical single-axis cycles, Mullins-type softening progressively increased strain and strain rate metrics relative to the HE model. Mullins-based injury probabilities progressively exceeded strain-based HE predictions and diverged from unchanged kinematics-based predictions, indicating that neglecting prior softening may underestimate injury risk. In a randomized twenty-cycle multiaxial sequence, cycles of similar kinematic intensity produced different deformation and injury-risk estimates depending on prior softening. HE and LVHE models predicted higher injury probabilities initially, whereas the Mullins-based model produced the largest later-cycle estimates and highest probability of at least one injury over the sequence. Regional amplification depended on loading direction and prior softening, with no direction-independent trend among brain substructures. Gyral elements exhibited higher cumulative maximum principal strain than sulcal elements, which showed greater amplification relative to initial responses. These findings demonstrate that short-term damage-mediated softening can substantially amplify tissue deformation and injury-risk estimates beyond damage-free head models under the same loading histories. Further experimental characterization of cyclic brain-tissue softening is needed to improve models of repeated head loading and traumatic brain injury.

q-bio.TO↗