SHIFT-M3: Pre-fusion Alignment-based Consistency Screening for Multimodal ECG Record Integrity

• URL: http://arxiv.org/abs/2609.13874v1
• Date: Sat, 12 Sep 2026 10:58:02 GMT
• Title: SHIFT-M3: Pre-fusion Alignment-based Consistency Screening for Multimodal ECG Record Integrity
• Abstract summary: Multimodal clinical AI typically assumes that the waveform, report, metadata, and downstream predictions attached to a record belong to the same patient.<n>We study this problem as multimodal record integrity triage: given an assembled record, should its modalities be trusted to belong together?<n>We introduce SHIFT-M3, a lightweight text-based pre-fusion screen that measures alignment-based consistency between two separately produced ECG text views.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal clinical AI typically assumes that the waveform, report, metadata, and downstream predictions attached to a record belong to the same patient. In practice, linkage failures can silently assemble individually plausible but cross-patient components, creating a safety problem that standard predictive models are not designed to detect. We study this problem as multimodal record integrity triage: given an assembled record, should its modalities be trusted to belong together? We introduce SHIFT-M3, a lightweight text-based pre-fusion screen that measures alignment-based consistency between two separately produced ECG text views: an LLM-generated interpretation and a clinical report summary. On 784,680 MEETI ECG records, SHIFT-M3 achieves 97.6% TPR@5% FPR for full text-view swaps (AUROC 0.996), 90.3% for partial swaps (AUROC 0.974), and 97.7% for label-matched hard negatives (AUROC 0.996) with only 573,569 parameters. Compared with same-dataset lexical baselines, the gains are largest on partial swaps and hard negatives, suggesting that the model is learning more than surface overlap. We also introduce the CMST (Conflict-type Multimodal Stress Test) evaluation taxonomy, a three-seed stability study, a loss ablation, a temporal-tolerance sweep, and a shared-token masking control. The main remaining failure mode is longitudinal ambiguity: at the default operating point, same-patient cross-visit pairs still produce 87.0% Type-II false positives.

Related papers

• Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection [66.44527094471619]
  We present RECAL, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns.<n>On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99%, 99.93%, and 99.99%, outperforming the best baseline on each dataset by 0.88, 0.82, and 0.42 percentage points, respectively.
  arXiv  Detail & Related papers  (2026-09-15T00:31:01Z)
• Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRI [0.0]
  Deep networks trained on structural MRI for Alzheimer's disease often reach reasonable accuracy while attending to anatomically irrelevant regions.<n>We use FastSurfer segmentations as an anatomical reference.<n>We adapt a CLIP-style image and organize ADNIMERGE variables along a label-leakage spectrum.
  arXiv  Detail & Related papers  (2026-09-14T17:13:12Z)
• Modalities Should Talk to Each Other: Dual-Stream Multimodal Learning for Long-Horizon Influenza Forecasting [1.2599533416395763]
  Publicly available surveillance datasets typically pair numeric epidemiological signals with noisy, loosely structured, only indirectly related to near-term trends, and often lagged relative to the numeric signal.<n>We propose Dual-Stream Attention (DSA), a multimodal deep learning framework that forecasts 12-week-ahead ILI activity from a 36-week multimodal history by letting the numerical and textual streams condition each other.
  arXiv  Detail & Related papers  (2026-08-24T15:20:01Z)
• Post-Operative Glioma Segmentation via Loss Stabilization, Normalization and Subspace Attention [46.03321798937855]
  We show that the standard Generalized Dice Loss (GDL) is unstable under domain shift.<n>We propose a Subspace-Aware Class Attention (SACA) module that re-calibrates the bottleneck features and raises Enhancing Tumor (ET) sensitivity by 8%.
  arXiv  Detail & Related papers  (2026-07-23T09:59:30Z)
• TMF-RSE: Tri-Modal Fusion with Regional Semantics and Evidential Uncertainty for Lung Severity Scoring [11.785230718509196]
  We propose a tri-modal deep learning framework, TMF-RSE, that combines appearance features from two-dimensional chest inputs, structural features from lung segmentation masks, and semantic features from vision-language models for severity quantification.<n>Our approach employs complementary fusion mechanisms that integrate semantic guidance, structural priors, and hierarchical interactions across modalities.<n> Experiments on the Per-COVID-19 CT and RALO datasets show that TMF-RSE outperforms recent transformer-based baselines.
  arXiv  Detail & Related papers  (2026-07-07T14:54:40Z)
• Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems [47.027290803102666]
  Normal behaviour is the union of many imbalanced, curved, thin-fringed operating regimes.<n>We model the normal law with a jointly learned latent representation plus explicit Gaussian-mixture mode clustering.<n>We evaluate under a deliberately fair protocol: raw point-wise metrics with no point adjustment, a trivial-detector difficulty split, prevalence-matched F1, and train-normal-only calibration.
  arXiv  Detail & Related papers  (2026-07-07T10:10:00Z)
• CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift [0.10742675209112622]
  Updating a deployed model for a new imaging modality can fail silently in two ways that harm patients.<n>We study parameter-efficient continual adaptation through these two properties rather than forgetting leaderboard accuracy.<n>We present CADRE: a frozen-backbone framework combining low-rank adaptation (LoRA) with an online, self-scaling, similarity-aware elastic weight consolidation term.
  arXiv  Detail & Related papers  (2026-06-22T15:34:32Z)
• Maximum Matching Accuracy: An Instance Segmentation Evaluation Metric Utilizing Globally Optimal Matching [39.3098730337656]
  We propose a threshold-free continuous metric that finds a globally optimal one-to-one matching between predicted and ground truth objects.<n>MMA produces scores that are more stable, more sensitive, and more interpretable than existing alternatives.
  arXiv  Detail & Related papers  (2026-06-08T19:36:28Z)
• MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion [37.86089523035199]
  We present MuteBench, a benchmark covering 9 datasets from 7 clinical domains.<n>We find that architecture family is the strongest predictor of robustness, outweighing parameter count.<n>Channel-independent models tolerate modality missing well but can be sensitive to within-modality missing.
  arXiv  Detail & Related papers  (2026-05-13T19:32:11Z)
• Multimodal Functional Maximum Correlation for Emotion Recognition [41.64451298000105]
  Emotional states manifest as coordinated yet heterogeneous physiological responses across central and autonomic systems.<n>We propose Multimodal Functional Maximum Correlation (MFMC) to maximize higher-order multimodal dependence.<n>MFMC consistently state-of-the-art or competitive under both subject-dependent and subject-independent evaluation protocols.
  arXiv  Detail & Related papers  (2025-12-28T20:48:02Z)
• 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)

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.