Curriculum-Aware Interpolate-then-Refine: Learned Physiological Time-Series Imputation under Realistic Missingness

• URL: http://arxiv.org/abs/2608.21207v1
• Date: Fri, 21 Aug 2026 15:21:36 GMT
• Title: Curriculum-Aware Interpolate-then-Refine: Learned Physiological Time-Series Imputation under Realistic Missingness
• Abstract summary: Imputing physiological time series is essential for addressing the missingness that pervades clinical data.<n>A benchmark found that simple linear outperformed every learned imputer on real-world clinical signals with realistic gaps.<n>We show that this reflects two properties of physiological missingness that generic imputers ignore.
• Score: 39.80184723814808
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Imputing physiological time series (arterial blood pressure, blood glucose, etc.) is essential for addressing the missingness that pervades clinical data. Yet modern imputation methods perform poorly in this domain: a recent benchmark found that simple linear interpolation outperformed every learned imputer on real-world clinical signals with realistic gaps. We show that this reflects two properties of physiological missingness that generic imputers ignore: gaps may occur when the signal is clinically extreme rather than typical, and gap lengths can easily span orders of magnitude. To this end, we introduce Curriculum-Aware Interpolate-then-Refine (CAIR), a two-stage framework for physiological time-series imputation. Our key motivation is to learn a coarse base curve and then repeatedly correct it toward physiological realism, rather than predict a gap in a single pass. Consequently, CAIR couples a bidirectional-GRU interpolator with a Transformer refiner that corrects its own estimate over three successive passes, trained jointly under a broad, signal-agnostic random-gap curriculum. We evaluate imputers stratified by gap length and missingness mechanism (MCAR, MAR, NMAR) rather than by a single average, and CAIR is the most accurate under every mechanism on continuous glucose monitoring (AI-READI) and arterial pressure in intensive care (MIMIC-III). Its margin over the strongest baseline grows with difficulty, from 9% under MCAR to 19% under value-dependent dropout, where generic learned imputers are weakest. We further show low reconstruction error alone does not recover the burden metrics clinicians act on: interpolants matching CAIR's error fail to preserve those metrics, imputers that recover them are far less accurate, and CAIR alone ranks among the best on both axes.

Related papers

• TRUE-Colon: Exposing a Consistent Transfer Asymmetry in Real-Time Polyp Detection [5.961408803838967]
  Computer-aided detection systems for colonoscopy promise to reduce clinical miss rates, yet reliable real-world deployment remains elusive.<n>We establish a standardized benchmarking protocol that measures key deployment characteristics alongside localization accuracy.<n>We observe a consistent transfer asymmetry: models trained strictly on curated clips suffer a severe performance collapse when evaluated on full procedures.<n>We find that the Transformer detector attains the strongest sensitivity and the earliest, most persistent detections, while the convolutional detectors stay competitive at a higher throughput.
  arXiv  Detail & Related papers  (2026-08-13T19:13:54Z)
• Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports [49.5225801722164]
  Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar.<n>We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance.
  arXiv  Detail & Related papers  (2026-06-17T08:10:30Z)
• FlatASCEND: Autoregressive Clinical Sequence Generation with Continuous Time Prediction and Association-Based Pharmacological Testing [1.7865154997539017]
  We present FlatASCEND, a 14.5M- parameter autoregressive clinical sequence model using flat composite tokens and a zero-inflated log-normal time head.<n>A prompt-shuffle ablation shows patient-specific conditioning amplifies mechanistic pharmacological effects.<n>Generative evidence is strongest for short-horizon ICU data; outpatient temporal fidelity is weaker.
  arXiv  Detail & Related papers  (2026-04-13T11:43:51Z)
• Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering [94.37535002230504]
  We develop a training-free, inference-time control framework termed Semantically Decoupled Latent Steering.<n>Our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition.<n>We show that our approach significantly reduces the probability of historical hallucinations.
  arXiv  Detail & Related papers  (2026-02-27T04:49:01Z)
• The Stationarity Bias: Stratified Stress-Testing for Time-Series Imputation in Regulated Dynamical Systems [0.098314893665023]
  Time-series imputation benchmarks use random masking and shape-agnostic metrics.<n>We formalize this bias and propose a emphStratified Stress-Test that partitions evaluation into Stationary and Transient regimes.
  arXiv  Detail & Related papers  (2026-02-17T15:05:56Z)
• Neural Architecture for Fast and Reliable Coagulation Assessment in Clinical Settings: Leveraging Thromboelastography [11.141462411413059]
  Real-time coagulation monitoring can enable early detection and prompt remediation of risks.<n>Traditional Thromboelastography (TEG) can only provide such outputs after nearly 1 hour of measurement.<n>We present Physiological State Reconstruc-tion (PSR), a new algorithm specifically designed to take ad-vantage of dynamic changes between individuals.
  arXiv  Detail & Related papers  (2026-01-12T15:03:53Z)
• Residual GRU+MHSA: A Lightweight Hybrid Recurrent Attention Model for Cardiovascular Disease Detection [1.267904597444312]
  We propose Residual GRU with Multi-Head Self-Attention, a compact deep learning architecture for clinical records.<n>We evaluate the model on the UCI Heart Disease dataset using 5-fold stratified cross-validation.<n>The proposed model achieves an accuracy of 0.861, macro-F1 of 0.860, ROC-AUC of 0.908, and PR-AUC of 0.904, outperforming all baselines.
  arXiv  Detail & Related papers  (2025-12-16T16:33:59Z)
• Semantic Latent Space Regression of Diffusion Autoencoders for Vertebral Fracture Grading [72.45699658852304]
  This paper proposes a novel approach to train a generative Diffusion Autoencoder model as an unsupervised feature extractor. We model fracture grading as a continuous regression, which is more reflective of the smooth progression of fractures. Importantly, the generative nature of our method allows us to visualize different grades of a given vertebra, providing interpretability and insight into the features that contribute to automated grading.
  arXiv  Detail & Related papers  (2023-03-21T17:16:01Z)
• Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies [62.840338941861134]
  We propose to leverage transfer learning from large datasets annotated by radiologists, to predict the histological score available on a small annex dataset. We compare different pretraining methods, namely weakly-supervised and self-supervised ones, to improve the prediction of the cirrhosis. This method outperforms the baseline classification of the METAVIR score, reaching an AUC of 0.84 and a balanced accuracy of 0.75.
  arXiv  Detail & Related papers  (2023-02-16T17:06:23Z)
• Are we certain it's anomalous? [57.729669157989235]
  Anomaly detection in time series is a complex task since anomalies are rare due to highly non-linear temporal correlations. Here we propose the novel use of Hyperbolic uncertainty for Anomaly Detection (HypAD) HypAD learns self-supervisedly to reconstruct the input signal.
  arXiv  Detail & Related papers  (2022-11-16T21:31:39Z)

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.