mlsanityData to 14 Oct 2026

A Clinical Point Cloud Paradigm for In-Hospital Mortality Prediction from Multi-Level Incomplete Multimodal EHRs

arXiv 2604.04614 ↗First posted 6 Apr 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning-based modeling of multimodal Electronic Health Records (EHRs) has become an important approach for clinical diagnosis and risk prediction. However, due to diverse clinical workflows and privacy constraints, raw EHRs are inherently multi-level incomplete, including irregular sampling, missing modalities, and sparse labels. These issues cause temporal misalignment, modality imbalance, and limited supervision. Most existing multimodal methods assume relatively complete data, and even methods designed for incompleteness usually address only one or two of these issues in isolation. As a result, they often rely on rigid temporal/modal alignment or discard incomplete data, which may distort raw clinical semantics. To address this problem, we propose HealthPoint (HP), a unified clinical point cloud paradigm for multi-level incomplete EHRs. HP represents heterogeneous clinical events as points in a continuous 4D space defined by content, time, modality, and case. To model interactions between arbitrary point pairs, we introduce a Low-Rank Relational Attention mechanism that efficiently captures high-order dependencies across these four dimensions. We further develop a hierarchical interaction and sampling strategy to balance fine-grained modeling and computational efficiency. Built on this framework, HP enables flexible event-level interaction and fine-grained self-supervision, supporting robust modality recovery and effective use of unlabeled data. Experiments on large-scale EHR datasets for risk prediction show that HP consistently achieves state-of-the-art performance and strong robustness under varying degrees of incompleteness.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 48 references that are in the map. First posted on arXiv 6 Apr 2026.

Builds on

30 of 48 references.

References · 30

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  4. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,013
  5. 2019Multimodal Transformer for Unaligned Multimodal Language Sequencescited by 645
  6. 2020Contrastive Learning of Medical Visual Representations from Paired Images and Textcited by 641
  7. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  8. 2017Multitask learning and benchmarking with clinical time series datacited by 290
  9. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  10. 2018MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcarecited by 72
  11. 2022M3Care: Learning with Missing Modalities in Multimodal Healthcare Datacited by 72
  12. 2022Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequencescited by 69
18 more
  1. 2020On the limits of cross-domain generalization in automated X-ray predictioncited by 62
  2. 2023Self-Supervised Multimodal Learning: A Surveycited by 58
  3. 2023Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Seriescited by 55
  4. 2024DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistencycited by 53
  5. 2019Using Clinical Notes with Time Series Data for ICU Managementcited by 38
  6. 2022Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modelingcited by 33
  7. 2023Learning Missing Modal Electronic Health Records with Unified Multi-modal Data Embedding and Modality-Aware Attentioncited by 25
  8. 2023Multi-task Paired Masking with Alignment Modeling for Medical Vision-Language Pre-trainingcited by 22
  9. 2023Multimodal Pretraining of Medical Time Series and Notescited by 22
  10. 2023RedCore: Relative Advantage Aware Cross-modal Representation Learning for Missing Modalities with Imbalanced Missing Ratescited by 15
  11. 2023Hierarchical Pretraining on Multimodal Electronic Health Recordscited by 11
  12. 2025MoE-Health: A Mixture of Experts Framework for Robust Multimodal Healthcare Predictioncited by 7
  13. 2024FlexCare: Leveraging Cross-Task Synergy for Flexible Multimodal Healthcare Predictioncited by 6
  14. 2024CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysiscited by 6
  15. 2024Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcitycited by 5
  16. 2024Multi-task Heterogeneous Graph Learning on Electronic Health Recordscited by 5
  17. 2025Towards Robust Multimodal Representation: A Unified Approach with Adaptive Experts and Alignmentcited by 2
  18. 2025Diffmv: A Unified Diffusion Framework for Healthcare Predictions with Random Missing Views and View Lazinesscited by 2

Built on by

Not cited yet.