Pith. sign in

REVIEW 2 cited by

Integrating Physiological Time Series and Clinical Notes with Deep Learning for Improved ICU Mortality Prediction

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2003.11059 v2 pith:Q3Q5KIH2 submitted 2020-03-24 cs.LG cs.CYstat.ML

Satya Narayan Shukla , Benjamin M. Marlin This is my paper · ORCID
classification cs.LGcs.CYstat.ML
keywords clinicaldataphysiologicaltimemortalitynotespredictionseries
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Intensive Care Unit Electronic Health Records (ICU EHRs) store multimodal data about patients including clinical notes, sparse and irregularly sampled physiological time series, lab results, and more. To date, most methods designed to learn predictive models from ICU EHR data have focused on a single modality. In this paper, we leverage the recently proposed interpolation-prediction deep learning architecture(Shukla and Marlin 2019) as a basis for exploring how physiological time series data and clinical notes can be integrated into a unified mortality prediction model. We study both early and late fusion approaches and demonstrate how the relative predictive value of clinical text and physiological data change over time. Our results show that a late fusion approach can provide a statistically significant improvement in mortality prediction performance over using individual modalities in isolation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    Ontology-aware contrastive pretraining plus note-to-vitals distillation improves MIMIC ICU risk and length-of-stay prediction using only vital signs at inference.

  2. MORE-CLEAR: Multimodal Offline Reinforcement learning for Clinical notes Leveraged Enhanced State Representation

    cs.LG 2025-08 conditional novelty 5.0 of 10

    A multimodal offline RL framework that fuses LLM-encoded clinical notes with structured vitals and labs modestly improves sepsis policy scores on some datasets, with evaluation caveats.

Pith tools