Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Ziyi, Zhang, Mengyuan, Ahmed, Mustafa Mohammed, Guo, Yi, George, Thomas J., Bian, Jiang, Wu, Yonghui
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2403.11425
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909374883037184
author Chen, Ziyi
Zhang, Mengyuan
Ahmed, Mustafa Mohammed
Guo, Yi
George, Thomas J.
Bian, Jiang
Wu, Yonghui
author_facet Chen, Ziyi
Zhang, Mengyuan
Ahmed, Mustafa Mohammed
Guo, Yi
George, Thomas J.
Bian, Jiang
Wu, Yonghui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11425
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure
Chen, Ziyi
Zhang, Mengyuan
Ahmed, Mustafa Mohammed
Guo, Yi
George, Thomas J.
Bian, Jiang
Wu, Yonghui
Machine Learning
Computation and Language
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.
title Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2403.11425