The paper presents a Time-Aware transformer-based model designed to predict Acute Exacerbation of Chronic Obstructive Pulmonary Disease (AECOPD) using only respiratory data from daily-use ventilators. By capturing symptom patterns and their temporal progression, the model generates meaningful patient representations and outperforms traditional methods across multiple classification tasks. This approach aims to provide timely detection of AECOPD while minimizing latency associated with clinical and laboratory data.
arXiv:2608. 19578v1 Announce Type: new Abstract: Acute exacerbation of chronic obstructive pulmonary disease (AECOPD) can worsen rapidly, making timely prediction a clinical priority.
The paper introduces a response‑aware patient dynamics model that explicitly captures how respiratory support alters a patient’s short‑term physiological trajectory. By decomposing predicted physiological change into baseline dynamics and support‑associated deviations anchored to room‑air reference, the model updates latent patient states across a forecast horizon. Experiments on ICU cohorts from two institutions show that the model matches baseline trajectory predictions overall and consistently improves performance when physiological states are changing.
The study introduces TRACER, a Transformer-based model that uses contrastive event representation to predict timelines leading to heart failure hospitalizations from low-resolution, irregularly sampled telemonitoring data. TRACER incorporates time-aware embeddings, contrastive pre‑training for anomaly detection, and independent binary classifiers, and was evaluated on biomarker sequences from 276 heart failure patients. The model achieved 66.7% accuracy in predicting hospitalization timelines with a 7.9% overestimation, outperforming other tested models by reformulating training as an event detection problem.
arXiv:2607. 15447v1 Announce Type: new Abstract: Recent research in clinical machine learning, focusing on outcome predictions in intensive care unit (ICU), has shifted from bespoke supervised models to foundation models, utilising modern representation learning methods.
WIPSNet is a 3D ResNet that processes stacked continuous wavelet transform scalograms of overnight impedance pneumography (IP) signals to detect paediatric wheeze. In a study of 15 patients (60 nights, 281 hours), it achieved an AUC of 0.783 ± 0.026, outperforming the traditional Expiratory Variability Index, a state‑space model, and two modern sleep‑staging architectures. The model’s best performance occurs with a 32‑minute temporal context, highlighting the importance of multi‑scale temporal aggregation for nocturnal respiratory dynamics.
arXiv:2607. 28035v1 Announce Type: new Abstract: Irregular multivariate time series are widely encountered in applications such as healthcare monitoring, human activity recognition, and environmental sensing.
NOAH is a generative transformer that models the entire multimodal patient journey by integrating bidirectional time and a variational latent space to capture continuous, stochastic clinical trajectories. Trained on over 559 million events from 431,000 hospital visits, it processes medical images, time‑series, numeric signals, categorical events, and both structured and unstructured records. The model supports autoregressive forecasting, zero‑shot classification, and counterfactual simulations, yielding strong predictive performance across 15 ICD chapters, 29 comorbidities, and time‑to‑event outcomes.
SepsisLens is a new model for early sepsis warning that preserves the structure of individual physiological signals while predicting risk. It uses observation-aware representations to encode each variable’s dynamics and a shared temporal encoder to maintain variable axes, then composes multi-horizon risk through a StructuredRiskHead that includes variable-level and organ-level components. The model was evaluated on three public ICU cohorts and one private-hospital cohort, achieving strong discrimination and lower alert burden at matched recall on MIMIC-IV, with ablations confirming the design choices.
arXiv:2511. 02340v3 Announce Type: replace Abstract: Chronic Kidney Disease (CKD) affects nearly 10\% of the global population and often progresses to end-stage renal failure.
NOAH is a generative transformer that learns the full multimodal patient journey by integrating bidirectional time and a variational latent space. Trained on over 559 million clinical events from 431,000 hospital visits, it processes medical images, time‑series, numeric signals, categorical events, and both structured and unstructured records. The model supports autoregressive forecasting, zero‑shot classification, and counterfactual intervention simulation, yielding strong performance on clinical outcomes, ICD chapters, comorbidities, and time‑to‑event prediction.
Mr.Dec is a new Transformer‑decoder model that predicts 30‑day hospital readmission by treating each admission as a chronological sequence of daily multimodal events, integrating Electronic Health Record updates and Chest X‑ray findings. It uses disease‑specific supervised contrastive learning to shape a diagnosis‑aware latent space and preserves day‑level clinical signals that other methods often compress. Experiments on MIMIC‑IV and MIMIC‑CXR datasets show state‑of‑the‑art performance and the model can highlight "Critical Days" for actionable real‑time risk stratification.
arXiv:2509. 24118v2 Announce Type: replace Abstract: Electronic health Records (EHRs) have become a cornerstone in modern-day healthcare.