Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2611.00008

Neonatal EEG Seizure Prediction with Quantum Inspired Continuous-Variable (Bosonic) Reservoir Computing

Krishna Bhatia·Chun-Yu Lin
View original source ↗Read source document ↗Export metadata ↓

Abstract

We study short-horizon neonatal seizure prediction on Helsinki-style (HUH) preprocessed EEG feature tables using quantum-inspired reservoir computing. Under strict subject-wise cross-validation on imbalanced preictal--interictal windows, we test whether reservoir constructions shaped after (i) gate-based qubit dynamics and (ii) continuous-variable (bosonic/photonic) dynamics provide a practical sequence encoder relative to strong classical baselines. Both reservoirs are executed here purely in classical simulation on a single GPU; accordingly, we do not claim quantum advantage, but rather evaluate whether quantum-shaped dynamics act as useful, low-footprint random feature maps with a trained linear readout. We compare against Random Forests and RBF--SVMs, and report AUROC, AUPRC, per-subject AUPRC, expected calibration error, and stratified bootstrap confidence intervals. Across our experiments, the CV/bosonic reservoir is consistently competitive and can improve AUPRC over the baselines, while the gate-style reservoir is more sensitive to hyperparameters. These results suggest that quantum-inspired, photonics-motivated reservoirs can be practical sequence encoders for neonatal EEG feature tables under conservative subject-wise evaluation.

Explore related subjects

physics.med-phcs.LGquant-ph

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Krishna Bhatia, Chun-Yu Lin. 2026-08-26. Neonatal EEG Seizure Prediction with Quantum Inspired Continuous-Variable (Bosonic) Reservoir Computing. https://arxiv.org/abs/2611.00008

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

KEEP EXPLORING

Related papers

arXiv2026

Probabilistic Modeling of Photon Interaction Chains in a Silicon Detector

Compton camera imaging relies on the positions and energies of multiple photon interactions recorded in the detector. In silicon detectors that resolve individual interactions, these measurements do not directly provide the causal interaction order, and in nuclear medicine applications the photon may also have scattered in the object before entering the detector. We present a probabilistic model for photon interaction chains in a silicon detector and use it for two inference tasks at the event level: interaction order inference and classification of primary versus object-scattered photons. The model combines photon transport based on Compton scattering and attenuation with a detector response model. It is evaluated on Monte Carlo data for monoenergetic point sources at 140~keV and 511~keV, with and without a cylindrical water phantom. For interaction chains of length two to four, the maximum a posteriori order estimate gives high accuracy in the case without a phantom, exceeding 0.95 for all chain lengths at 511~keV, and decreasing with increasing phantom radius. The gap between the two highest posterior order probabilities provides a confidence measure for the ordering estimate and can be used to increase accuracy at the cost of reduced retention. For scatter classification, likelihood-ratio testing yields receiver operating characteristic curves with area under the curve above 0.85 across all phantom radii considered. These results support the use of probabilistic modeling of measured interaction sequences for inference directly at the event level, and show that both interaction ordering and scatter discrimination can be treated within a common framework.

physics.med-ph↗
arXiv2026

Perioperative shear wave elastography for the evaluation of spinal cord release in pediatric dysraphism: first experience in 21 patients

OBJECTIVE Shear wave elastography (SWE) is a recent method for evaluating soft tissue stiffness. Its application to the spinal cord is limited by the ultrasound bone barrier. Spinal dysraphism can cause neurological symptoms impairing bladder, bowel, and lower limb function due to a mechanical stress known as tethered cord syndrome. Detethering of the spinal cord is a part of surgical treatment. This study aimed to assess the feasibility of intraoperative elastography to guide surgery in patients with spinal dysraphism involving traction of the spinal cord. METHODS This single-center retrospective study included all patients who underwent surgery for spinal dysraphism between November 2023 and July 2024. SWE was performed under general anesthesia with the patient in the prone position before and after spinal cord detethering. All SWE measurements were performed using the Aixplorer system. Demographic, clinical, and radiological data (age at surgery, neurological status, and MRI findings) were collected. RESULTS Twenty-one patients with a mean $\pm$ SD (range) age of 3.7 $\pm$ 5.3 (0--17.5) years were included. Etiologies included open saccular dysraphism (n = 3), spinal cord conus lipoma (n = 6), limited dorsal myeloschisis (n = 3), and fibrolipomatous filum (n = 9). In 85% of patients, at least 1 clip was of sufficient quality for analysis both before and after release. The mean $\pm$ SD (range) spinal cord stiffness at the beginning of surgery was 25.2 $\pm$ 9.2 (12.3--39.1) kPa and 11.2 $\pm$ 3.8 (6.2--16.5) kPa at the end of release, with a significant stiffness decrease (p = 0.018). No complications attributable to SWE were observed. CONCLUSIONS SWE of the spinal cord in patients with spinal dysraphism is a safe and feasible imaging method. This technique may assist in assessing the adequacy of untethering during surgery. However, no established normative SWE values for the pediatric spinal cord currently exist. Until it does, the intraoperative interpretability and clinical utility of this technique remain limited.

physics.med-ph↗
arXiv2026

Influence of Geometry and Tissue Damage on the Mechanical Behaviour of Skin Meshing

Skin meshing increases graft coverage, yet the clinically achieved expansion often falls below the manufacturer's nominal meshing ratio. Previous elastic analyses have demonstrated that mesh topology and skin anisotropy strongly influence graft expansion; however, the effect of progressive damage at larger deformation remains unexplored. This study therefore investigates how progressive damage affects the expansion and mechanical response of skin meshes. The performance of auxetic mesh geometries is compared with conventional Zimmer mesher (ZM) geometry. Human back skin was modelled using a one-term Ogden ground matrix and a Gasser Ogden Holzapfel (GOH) collagen network, with separate scalar Kachanov-type continuum damage variables for each constituent. The auxetic geometries, including 1st- and 2nd-order alternative slits (AS1 and AS2), I-shaped (IS) and H-shaped (HS) re-entrant patterns, and ZM, were analysed with Langer's lines oriented either parallel or perpendicular to the loading direction. Hyperelastic and damage-based formulations were compared up to 25% strain, and the damage-based simulations were subsequently extended to 40% strain. ZM was further loaded to 155% strain; the area ratios attained by HS at 40% strain were matched by ZM at 142.1% and 124.7% strain for Langer's lines parallel and perpendicular to loading, respectively. Results indicate that HS achieves greater coverage than ZM for a given stretch, whereas its damage advantage depends on the orientation of Langer's lines.

physics.med-ph↗