Missingness as Signal: Channel-Independent Spectrogram Learning for Clinical Time Series Prediction

• URL: http://arxiv.org/abs/2607.02938v1
• Date: Fri, 03 Jul 2026 04:21:19 GMT
• Title: Missingness as Signal: Channel-Independent Spectrogram Learning for Clinical Time Series Prediction
• Abstract summary: This work presents CISM, a Channel-Independent Spectrogram framework with a Missingness stream for clinical time series prediction.<n>Experiments on an in-hospital mortality task derived from MIMIC-IV show that CISM achieves the highest mean AUROC (0.7225), AUPRC (0.3308), and F1 (0.3808) among the compared time series, missingness-aware, vision, and time-frequency baselines.
• Score: 6.42984920182754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Clinical time series prediction in intensive care units remains challenging due to heterogeneous physiological variables and informative missingness. The presence or absence of a measurement can reflect clinical decisions and patient severity, and thus missingness can serve as a predictive signal rather than a simple data artifact. This work presents CISM, a Channel-Independent Spectrogram framework with a Missingness stream for clinical multivariate time series prediction. CISM converts each clinical variable into a variable-wise time-frequency spectrogram, preserves variable identity through variable-aligned encoding, and aligns an explicit missingness stream with the spectrogram representation. Experiments on an in-hospital mortality task derived from MIMIC-IV show that CISM achieves the highest mean AUROC (0.7225), AUPRC (0.3308), and F1 (0.3808) among the compared time series, missingness-aware, vision, and time-frequency baselines. Ablation studies further show that observation patterns provide a meaningful informative signal. Pixel-level mask injection improves performance over plain spectrogram inputs and recovers much of this predictive value. The aligned missingness stream contributes a further, complementary gain in both AUROC and AUPRC. These results highlight the importance of modeling observation patterns as structured signals in clinical time series prediction.

Related papers

• The Impact of Temporal Context Length and Encoding Strategies on Self-Supervised ECG Representation Learning [0.8411385346896411]
  Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal.<n>It remains unclear whether these choices sacrifice information needed for rhythm inference and longitudinal consistency.<n>We present a controlled study on the Icentia11k single-lead dataset.
  arXiv  Detail & Related papers  (2026-08-13T01:18:39Z)
• GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care [5.469342914844525]
  We present Attention-based Graph Learning for Intensive Care (GARLIC) model.<n>GARLIC imputes missing data through exponential learnable neural network architecture.<n>On three ICU benchmarks, GARLIC sets the new state of the art in outcome prediction.
  arXiv  Detail & Related papers  (2026-08-11T14:29:48Z)
• Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations [59.34593956287438]
  Aionoscope is a diagnostic tool for inspecting latent-state accessibility in frozen time-series representations.<n>Aionoscope separates process generation from observation rendering, producing seeded synthetic streams with exact categorical and dense labels.
  arXiv  Detail & Related papers  (2026-07-01T13:54:20Z)
• ReTAMamba: Reliability-Aware Temporal Aggregation with Mamba for Irregular Clinical Time Series Prediction [3.5795275871379704]
  Clinical time-series data are difficult to model because they exhibit irregular sampling, frequent missing values, and heterogeneous observation patterns.<n>Existing approaches commonly use observation masks and time-gap information, but they do not continuously capture the decaying reliability of past observations.<n>We propose Reliability-aware Temporal Aggregation with Mamba, which reconstructs clinical time series as time-variable token sequences.
  arXiv  Detail & Related papers  (2026-05-11T02:39:33Z)
• LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection [53.191369031661885]
  Unsupervised time series anomaly detection aims to build a model for identifying abnormal timestamps without assuming the availability of annotations.<n>We present Learnable Fusion of Tri-view Tokens (LEFT), a unified unsupervised TSAD framework that models anomalies as inconsistencies across complementary representations.<n>Experiments on real-world benchmarks show that LEFT yields the best detection accuracy against SOTA baselines, while achieving a 5x reduction on FLOPs and 8x speed-up for training.
  arXiv  Detail & Related papers  (2026-02-09T13:33:49Z)
• Digital FAST: An AI-Driven Multimodal Framework for Rapid and Early Stroke Screening [0.7136933021609076]
  This study presents a fast, non-invasive multimodal deep learning framework for automatic binary stroke screening based on data collected during the F.A.S.T. assessment.<n>The proposed approach integrates complementary information from facial expressions, speech signals, and upper-body movements to enhance diagnostic robustness.
  arXiv  Detail & Related papers  (2026-01-17T03:35:39Z)
• MEET-Sepsis: Multi-Endogenous-View Enhanced Time-Series Representation Learning for Early Sepsis Prediction [50.74903497515021]
  Sepsis is a life-threatening infectious syndrome associated with high mortality in intensive care units (ICUs)<n>Early and accurate sepsis prediction (SP) is critical for timely intervention, yet remains challenging due to subtle early manifestations and rapidly escalating mortality.<n>This paper introduces a Multi-Endogenous-view Representation Enhancement (MERE) mechanism to construct enriched feature views, coupled with a Cascaded Dual-convolution Time-series Attention (CDTA) module for temporal representation learning.<n>The proposed MEET-Sepsis framework achieves competitive prediction accuracy using only 20% of the ICU monitoring time required by SOTA methods, significantly advancing
  arXiv  Detail & Related papers  (2025-10-13T13:38:29Z)
• Cross-Representation Benchmarking in Time-Series Electronic Health Records for Clinical Outcome Prediction [44.23284500920266]
  This benchmark standardises data curation and evaluation across two distinct clinical settings.<n>Experiments reveal that event stream models consistently deliver the strongest performance.<n>We find that feature selection strategies must be adapted to the clinical setting.
  arXiv  Detail & Related papers  (2025-10-10T09:03:47Z)
• Mind the Missing: Variable-Aware Representation Learning for Irregular EHR Time Series using Large Language Models [0.6554326244334866]
  VITAL is a variable-aware, large language model (LLM) based framework tailored for learning from irregularly sampled physiological time series.<n>It reprograms vital signs into the language space, enabling the LLM to capture temporal context and reason over missing values.<n>It maintains robust performance under high levels of missingness, which is prevalent in real world clinical scenarios.
  arXiv  Detail & Related papers  (2025-09-26T09:44:16Z)
• CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis [50.56875995511431]
  We introduce a Cross-Modal Temporal Pattern Discovery (CTPD) framework, designed to efficiently extract meaningful cross-modal temporal patterns from multimodal EHR data.<n>Our approach introduces shared initial temporal pattern representations which are refined using slot attention to generate temporal semantic embeddings.
  arXiv  Detail & Related papers  (2024-11-01T15:54:07Z)
• TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing [17.86697534018046]
  We present a Time series (medical signal) Representation Learning framework via Spectrogram (TRLS) to get more informative representations. We transform the input time-domain medical signals into spectrograms and design a time-frequency encoder named Time Frequency RNN (TFRNN) to capture more robust multi-scale representations.
  arXiv  Detail & Related papers  (2024-01-06T02:26:02Z)
• Multimodal Pretraining of Medical Time Series and Notes [45.89025874396911]
  Deep learning models show promise in extracting meaningful patterns, but they require extensive labeled data. We propose a novel approach employing self-supervised pretraining, focusing on the alignment of clinical measurements and notes. In downstream tasks, including in-hospital mortality prediction and phenotyping, our model outperforms baselines in settings where only a fraction of the data is labeled.
  arXiv  Detail & Related papers  (2023-12-11T21:53:40Z)
• A complex network approach to time series analysis with application in diagnosis of neuromuscular disorders [1.9659095632676098]
  This paper proposes a new approach to network development named GraphTS to overcome the limited accuracy of existing methods. For this purpose, EMG signals are pre-processed and mapped to a complex network by a standard visibility graph algorithm. The resulting networks can differentiate between healthy and patient samples.
  arXiv  Detail & Related papers  (2021-08-16T06:44:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.