DRIFT: Direct-Recursive Intervention-Conditioned Forecasting of ICU Physiological Trajectories

• URL: http://arxiv.org/abs/2607.25864v1
• Date: Tue, 28 Jul 2026 15:31:22 GMT
• Title: DRIFT: Direct-Recursive Intervention-Conditioned Forecasting of ICU Physiological Trajectories
• Abstract summary: DRIFT is a hybrid framework in which a direct model produces the primary forecast and an action-conditioned model contributes constrained corrections.<n>Averaged across the 8-, 24-, and 48-hour forecast endpoints, DRIFT reduces mean absolute error for mean arterial pressure (MAP) by 0.673%.
• Score: 5.522311210914546
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many time-series forecasts depend not only on prior observations but also on actions specified during the forecast period. In intensive care units (ICUs), future vital signs and laboratory values are influenced by treatments such as vasopressors. However, models that predict the full future sequence all at once make little use of these treatments, whereas autoregressive models can accumulate errors. We introduce DRIFT, a hybrid framework in which a direct model produces the primary forecast and a recursive, action-conditioned model contributes constrained corrections. We evaluate DRIFT on 6,046 admissions from MIMIC-IV and 8,345 admissions from eICU-CRD. Averaged across the 8-, 24-, and 48-hour forecast endpoints, DRIFT reduces mean absolute error for mean arterial pressure (MAP) by 0.673% relative to an action-conditioned Temporal Fusion Transformer (TFT-action) on MIMIC-IV and achieves the lowest corresponding error among the compared models on eICU-CRD. Although the overall accuracy improvement is modest, a MIMIC-IV audit restricted to windows in which the supplied treatment sequence was altered showed that DRIFT achieved lower observed-target MAP error than TFT-action at 8 and 24 hours. Treatment-sequence alteration increased DRIFT's MAP error by 0.21-0.26 mmHg more than it increased TFT-action's error, with prediction changes occurring primarily after the supplied paths diverged. In a separate robustness experiment, the MAP advantage persisted under three shared checkpoint-selection rules emphasizing overall endpoint error, MAP error, or both equally.

Related papers

• RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases [58.92094935632493]
  Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate.<n>We introduce Research Attention Prediction (RAP), a rolling benchmark covering 278 AI/ML fields and 1,390 episodes.<n>At each cut-off, an LLM agent searches a temporally restricted arXiv corpus and predicts the next six months' paper shares across eight frozen research directions.
  arXiv  Detail & Related papers  (2026-09-09T12:15:14Z)
• Large-Small Model Collaboration for Zero-Shot Surgical Phase Recognition [45.191945465591374]
  Task-specific lightweight models for surgical phase recognition excel at capturing temporal dynamics but generalize poorly under domain shift.<n>We propose textbfLarge-textbfSmall textbfTemporal adaptation (textbfLaST), a novel large-small collaborative framework that enables zero-shot adaptation to unseen clinical domains.
  arXiv  Detail & Related papers  (2026-08-24T07:06:52Z)
• The Granularity Paradox: How Temporal Disaggregation Inflates In-Sample Fit and Compounds Out-of-Sample Error [0.0]
  "Granularity Paradox" in time-series forecasting, wherein finer temporal disaggregation improves in-sample diagnostics and dataset size.<n>We formalize this trade-off and benchmark 10 models across six granularities using a 13-year public procurement dataset.
  arXiv  Detail & Related papers  (2026-07-05T11:52:08Z)
• t-STEP: An interpretable model for Total Electron Content predictions and irregularities estimations [8.965320425114603]
  GPS communications are affected by ionospheric Total Electron Content (TEC) gradients.<n>To address this gap, we introduce an interpretable ML-based model, t-STEP, designed to predict TEC at a 30-second resolution.<n>The model is developed using GPS observations from solar cycle 24 at a station located at 5.49S, 47.49W.
  arXiv  Detail & Related papers  (2026-06-28T23:21:37Z)
• Adaptive Temporal Gating of Longitudinal Magnetic Resonance Imaging for Alzheimer's Prediction [4.549831511476248]
  We introduce the Temporal Adaptive Fusion Network (TAF-Net), a hybrid CNN-Transformer architecture that models longitudinal 3D MRI scans.<n> evaluated on the Alzheimer's Disease Neuroimaging Initiative cohort for three-year MCI-to-AD conversion prediction.
  arXiv  Detail & Related papers  (2026-05-27T12:33:46Z)
• UTOPYA: A Multimodal Deep Learning Framework for Physics-Informed Anomaly Detection and Time-Series Prediction [42.532335022354545]
  Anomaly detection in batch processes is hindered by transient dynamics, scarce fault labels, and reliance on singlemodality sensor data.<n>This work introduces UTOPYA, a multimodal framework that jointly addresses anomaly detection, time-series prediction, and phase classification in batch distillation.<n>A physics-informed regularisation scheme introduced in this work enforces temporal smoothness and thermodynamic monotonicity.
  arXiv  Detail & Related papers  (2026-05-18T10:28:15Z)
• Hierarchical Flow Decomposition for Turning Movement Prediction at Signalized Intersections [4.885966337065846]
  This study proposes HFD-TM (Hierarchical Flow-Decomposition for Turning Movement Prediction), a hierarchical deep learning framework.<n>It predicts turning movements by first forecasting corridor through-movements and then expanding these predictions to individual turning streams.<n> Evaluated on six months of 15-minute interval LiDAR data from a six-intersection corridor in Nashville, Tennessee, HFD-TM achieves a mean absolute error of 2.49 vehicles per interval.
  arXiv  Detail & Related papers  (2026-04-10T14:03:29Z)
• Transparent Early ICU Mortality Prediction with Clinical Transformer and Per-Case Modality Attribution [42.85462513661566]
  We present a lightweight, transparent multimodal ensemble that fuses physiological time-series measurements with unstructured clinical notes from the first 48 hours of an ICU stay.<n>A logistic regression model combines predictions from two modality-specific models: a bidirectional LSTM for vitals and a finetuned ClinicalModernBERT transformer for notes.<n>On the MIMIC-III benchmark, our late-fusion ensemble improves discrimination over the best single model while maintaining well-calibrated predictions.
  arXiv  Detail & Related papers  (2025-11-19T20:11:49Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• Leveraging Support Vector Regression, Radiomics and Dosiomics for Outcome Prediction in Personalized Ultra-fractionated Stereotactic Adaptive Radiotherapy (PULSAR) [5.497745780154633]
  This study aims to develop a multi-omics based support vector regression (SVR) model for predicting gross tumor volume (GTV) change.<n>A retrospective cohort of 39 patients with 69 brain metastases was analyzed.<n>Delta-radiomic features play a critical role in enhancing prediction accuracy relative to features at single time points.
  arXiv  Detail & Related papers  (2025-09-09T15:57:21Z)
• A Generative Framework for Causal Estimation via Importance-Weighted Diffusion Distillation [55.53426007439564]
  Estimating individualized treatment effects from observational data is a central challenge in causal inference.<n>In inverse probability weighting (IPW) is a well-established solution to this problem, but its integration into modern deep learning frameworks remains limited.<n>We propose Importance-Weighted Diffusion Distillation (IWDD), a novel generative framework that combines the pretraining of diffusion models with importance-weighted score distillation.
  arXiv  Detail & Related papers  (2025-05-16T17:00:52Z)
• CRTRE: Causal Rule Generation with Target Trial Emulation Framework [47.2836994469923]
  We introduce a novel method called causal rule generation with target trial emulation framework (CRTRE) CRTRE applies randomize trial design principles to estimate the causal effect of association rules. We then incorporate such association rules for the downstream applications such as prediction of disease onsets.
  arXiv  Detail & Related papers  (2024-11-10T02:40:06Z)
• Automated Precision Localization of Peripherally Inserted Central Catheter Tip through Model-Agnostic Multi-Stage Networks [3.5255361096618523]
  Peripherally inserted central catheters (PICCs) have been widely used as one of the representative central venous lines (CVCs) due to their long-term intravascular access with low infectivity. PICCs have a fatal drawback of a high frequency of tip mispositions, increasing the risk of puncture, embolism, and complications such as cardiac arrhythmias. Various attempts have been made by using the latest deep learning (DL) technologies to automatically and precisely detect it. This study aimed to develop a system generally applied to existing models and to restore the PICC line more exactly by removing the
  arXiv  Detail & Related papers  (2022-06-14T10:26:47Z)

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.