Challenge: Traditional approaches to predicting the duration of a patient's stay in an Intensive Care Unit (ICU) rely on structured clinical data, but recent advances in language models offer significant potential to utilize unstructured text data for ICU length-of-stay (LoS) predictions.
Approach: They propose a method for analyzing nursing notes to predict ICU length-of-stay of patients.
Outcome: The proposed model outperforms baseline models on the MIMIC-III dataset and shows that it significantly outperformed existing models.

Similar Papers

Using Clinical Notes with Time Series Data for ICU Management (D19-1)

Copied to clipboard

Challenge: Existing work on monitoring patients in ICU has focused on using time series signals from medical instruments.
Approach: They propose to add clinical notes to the time-series data to improve model performance for three benchmark tasks: in-hospital mortality prediction, modeling decompensation, and length of stay forecasting.
Outcome: The proposed model improves on three benchmark tasks: in-hospital mortality prediction, modeling decompensation, and length of stay forecasting.
Predicting in-hospital mortality by combining clinical notes with time-series data (2021.findings-acl)

Copied to clipboard

Challenge: In intensive care units, patient health is monitored through vital signals and clinical notes . previous work focused on predicting patient health using time-series data gathered from medical devices .
Approach: They propose a model that combines clinical notes and vital data to make accurate mortality predictions.
Outcome: The proposed model achieves an AUC score of 0.9, compared to the previous 0.87 . it can be used to make accurate in-hospital mortality predictions .
Making the Most Out of the Limited Context Length: Predictive Power Varies with Clinical Note Type and Note Section (2023.acl-srw)

Copied to clipboard

Challenge: Clinical notes have a long time span over multiple long documents.
Approach: They propose a framework to analyze clinical notes with high predictive power . they propose to combine different types of notes to improve performance .
Outcome: The proposed framework could be used to extract information from clinical notes . it shows that the sample size can be optimized for large contexts .
A Corpus for Detecting High-Context Medical Conditions in Intensive Care Patient Notes Focusing on Frequently Readmitted Patients (2020.lrec-1)

Copied to clipboard

Challenge: Currently, most medical data is generated and stored in unstructured, text-based format.
Approach: They propose to use a patient phenotyping dataset to identify whether a given medical condition is present in their notes.
Outcome: The proposed dataset contains 1102 Discharge Summaries and 1000 Nursing Progress Notes.
Modelling Temporal Document Sequences for Clinical ICD Coding (2023.eacl-main)

Copied to clipboard

Challenge: Existing studies on the ICD coding task focus on extracting codes from the discharge summary, but there is potential to automate the task by identifying relevant information from clinical notes.
Approach: They propose a hierarchical transformer architecture that uses text across the entire sequence of clinical notes in each hospital stay for ICD coding.
Outcome: The proposed model exceeds the state-of-the-art when using only discharge summaries as input and achieves performance improvements when all clinical notes are used as input.
Data Drift in Clinical Outcome Prediction from Admission Notes (2024.lrec-main)

Copied to clipboard

Challenge: a pivotal dataset for clinical NLP research was released in 2016 . public access to such datasets is limited due to privacy and ethical concerns .
Approach: They propose a novel clinical outcome prediction dataset based on MIMIC-IV . they provide initial insights into the performance of models trained on MIDIC-III .
Outcome: The proposed dataset aims to probe the robustness and generalization of clinical outcome prediction models . the study focuses on challenges tied to evolving documentation standards and changing codes in the ICD taxonomy .
Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration (2021.eacl-main)

Copied to clipboard

Challenge: Clinical decision support systems can help in situations where the patient's development is predicted based on textual data.
Approach: They propose to use clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources into the models.
Outcome: The proposed model improves performance against several baselines and demonstrates that it is transferable and can be used in clinical decision support systems.
Less is More: Explainable and Efficient ICD Code Prediction with Clinical Entities (2025.acl-long)

Copied to clipboard

Challenge: Clinical coding is labor-intensive and prone to delays, leading to global backlogs.
Approach: They propose an approach that combines Named Entity Recognition (NER) and Assertion Classification (AC) to filter for clinically important content before supervised code prediction.
Outcome: The proposed approach reduces training time by over half on a standard evaluation dataset compared to current methods . it uses Named Entity Recognition (NER) and Assertion Classification (AC) to filter for clinically important content before supervised code prediction.
Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods to accommodate missingness in clinical time series, but how to extract and use information carried by the observation process itself remains underexplored.
Approach: They propose a patient representation learning framework that leverages informative missingness to learn multimodal clinical time series from structured and textual data.
Outcome: The proposed framework improves offline treatment policy learning and adverse outcome prediction on ICU sepsis cohorts from MIMIC-III, MIMIC IV, and eICU.
Analyzing Code Embeddings for Coding Clinical Narratives (2021.findings-acl)

Copied to clipboard

Challenge: Recent work on automated ICD coding learn mappings between low-dimensional representations of clinical text reports and codes.
Approach: They propose novel neural networks for encoding medical codes based on textual, structural and statistical characteristics using a single deep learning baseline model.
Outcome: The proposed methods improve the accuracy of medical codes based on their textual, structural and statistical characteristics.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations