Lune

ACL Findings2021

Predicting in-hospital mortality by combining clinical notes with time-series data

Iman Deznabi, Mohit Iyyer, Madalina Fiterau

Abstract

In intensive care units (ICUs), patient health is monitored through (1) continuous vital signals from various medical devices, and (2) clinical notes consisting of opinions and summaries from doctors which are recorded in electronic health records (EHR). It is difficult to jointly model these two sources of information because clinical notes, unlike vital signals, are collected at irregular intervals and their contents are relatively unstructured. In this paper, we present a model that combines both sources of information about ICU patients to make accurate in-hospital mortality predictions. We apply a fine-tuned BERT model to each of the patient's clinical notes. The resulting embeddings are then combined to obtain the overall embedding for the entire text part of the data. This is then combined with the output of an LSTM model that encodes patients' vital signals. Our model improves upon the state of the art for mortality prediction, attaining an AUC score of 0.9, compared to the previous 0.87, setting a new standard for mortality prediction on the MIMIC III benchmark. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

5 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling cites Set Functions for Time Series
  • Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling cites Multi-Time Attention Networks for Irregularly Sampled Time Series
  • Building Massively Multimodal Foundation Models with Interaction-aware Mixture-of-Experts cites Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling
  • Building Massively Multimodal Foundation Models with Interaction-aware Mixture-of-Experts cites Multi-Time Attention Networks for Irregularly Sampled Time Series
  • Building Massively Multimodal Foundation Models with Interaction-aware Mixture-of-Experts cites FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
  • Multi-Time Attention Networks for Irregularly Sampled Time Series cites Set Functions for Time Series
  • FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion cites Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling
  • FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion cites Set Functions for Time Series
  • FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion cites Multi-Time Attention Networks for Irregularly Sampled Time Series
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers5

  1. FuseMoE: Mixture-of-Experts Transformers for Fleximodal FusionXing Han, Huy Nguyen, Carl Harris, Nhat Ho et al.NeurIPS 2024 · 129 citations
  2. Improving Medical Predictions by Irregular Multimodal Electronic Health Records ModelingXinlu Zhang, Shiyang Li, Zhiyu Chen, Xifeng Yan et al.ICML 2023 · 54 citations
  3. Clinical Note Owns its Hierarchy: Multi-Level Hypergraph Neural Networks for Patient-Level Representation LearningNayeon Kim, Yinhua Piao, Sun KimACL 2023 · 3 citations
  4. Building Massively Multimodal Foundation Models with Interaction-aware Mixture-of-ExpertsXing Han, Hsing-Huan Chung, Joydeep Ghosh, Paul Pu Liang et al.ICLR 2026 · 1 citation
  5. CrisisTS: Coupling Social Media Textual Data and Meteorological Time Series for Urgency ClassificationRomain Meunier, Farah Benamara, Véronique Moriceau, Zhongzheng Qiao et al.ACL 2025 · 1 citation

Builds on2

  1. Multi-Time Attention Networks for Irregularly Sampled Time SeriesSatya Narayan Shukla, Benjamin M. MarlinICLR 2021 · 301 citations
  2. Set Functions for Time SeriesMax Horn, Michael Moor, Christian Bock, Bastian Rieck et al.ICML 2020 · 199 citations

Related papers

  1. P²²N: Patient Multi-view Multi-modal Feature Fusion Networks for Clinical Outcome PredictionYing Zhang, Baohang Zhou, Kehui Song, Xuhui Sui et al.EMNLP Findings 2022 · 9 citations
  2. How to leverage the multimodal EHR data for better medical prediction?Bo Yang, Lijun WuEMNLP 2021 · 22 citations
  3. Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative MissingnessZihan Liang, Ziwen Pan, Ruoxuan XiongACL Findings 2026
  4. Characterizing the Value of Information in Medical NotesChao-Chun Hsu, Shantanu Karnwal, Sendhil Mullainathan, Ziad Obermeyer et al.EMNLP Findings 2020 · 14 citations
  5. Explainable Clinical Decision Support from TextJinyue Feng, Chantal Shaib, Frank RudziczEMNLP 2020 · 19 citations
Dusk over the sea between two cliffs drawn in fine vertical lines