Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure

Ziyi Chen, Mengyuan Zhang, Mustafa Mohammed Ahmed, Yi Guo, Thomas J. George +2 more
3/18/2024
cs.LGcs.CL

No official code found. Best implementation: uf-hobi-informatics-lab/GatorTron-Prediction (6 stars, MIT, last commit 2025-11-06).

Abstract

Cancer treatments are known to introduce cardiotoxicity, negatively impacting outcomes and survivorship. Identifying cancer patients at risk of heart failure (HF) is critical to improving cancer treatment outcomes and safety. This study examined machine learning (ML) models to identify cancer patients at risk of HF using electronic health records (EHRs), including traditional ML, Time-Aware long short-term memory (T-LSTM), and large language models (LLMs) using novel narrative features derived from the structured medical codes. We identified a cancer cohort of 12,806 patients from the University of Florida Health, diagnosed with lung, breast, and colorectal cancers, among which 1,602 individuals developed HF after cancer. The LLM, GatorTron-3.9B, achieved the best F1 scores, outperforming the traditional support vector machines by 39%, the T-LSTM deep learning model by 7%, and a widely used transformer model, BERT, by 5.6%. The analysis shows that the proposed narrative features remarkably increased feature density and improved performance.

View on arXivView PDF

Code Implementations(1)

uf-hobi-informatics-lab/GatorTron-PredictionCommunity100%
MIT

This is the official implementation of "Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure"

61Shell, PythonAug 14, 202411 months agoMIT

Similar Papers

Automatic Cardiac Risk Management Classification using large-context Electronic Patients Health Records

85% match2026

Integrating Machine Learning Ensembles and Large Language Models for Heart Disease Prediction Using Voting Fusion

84% match2026

Is Clinical Text Enough? A Multimodal Study on Mortality Prediction in Heart Failure Patients

84% match2026

Large Language Models versus Classical Machine Learning: Performance in COVID-19 Mortality Prediction Using High-Dimensional Tabular Data

83% match2 repos12024

The Power of Combining Data and Knowledge: GPT-4o is an Effective Interpreter of Machine Learning Models in Predicting Lymph Node Metastasis of Lung Cancer

83% match2024

When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation for Medical Machine Learning Applications?

83% match2024

Cite this paper

@article{chen2024narrative,
  title  = {Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure},
  author = {Ziyi Chen and Mengyuan Zhang and Mustafa Mohammed Ahmed and Yi Guo and Thomas J. George and Jiang Bian and Yonghui Wu},
  year   = {2024},
  eprint = {2403.11425},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.11425v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.11425.svg)](https://codeofpaper.com/paper/2403.11425)

Discussion