MIMIC-IV-Ext-PE: Using a large language model to predict pulmonary embolism phenotype in the MIMIC-IV dataset

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lam, B. D., Ma, S., Kovalenko, I., Wang, P., Jafari, O., Li, A., Horng, S.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916464278110208
author Lam, B. D.
Ma, S.
Kovalenko, I.
Wang, P.
Jafari, O.
Li, A.
Horng, S.
author_facet Lam, B. D.
Ma, S.
Kovalenko, I.
Wang, P.
Jafari, O.
Li, A.
Horng, S.
contents Pulmonary embolism (PE) is a leading cause of preventable in-hospital mortality. Advances in diagnosis, risk stratification, and prevention can improve outcomes. There are few large publicly available datasets that contain PE labels for research. Using the MIMIC-IV database, we extracted all available radiology reports of computed tomography pulmonary angiography (CTPA) scans and two physicians manually labeled the results as PE positive (acute PE) or PE negative. We then applied a previously finetuned Bio_ClinicalBERT transformer language model, VTE-BERT, to extract labels automatically. We verified VTE-BERT's reliability by measuring its performance against manual adjudication. We also compared the performance of VTE-BERT to diagnosis codes. We found that VTE-BERT has a sensitivity of 92.4% and positive predictive value (PPV) of 87.8% on all 19,942 patients with CTPA radiology reports from the emergency room and/or hospital admission. In contrast, diagnosis codes have a sensitivity of 95.4% and PPV of 83.8% on the subset of 11,990 hospitalized patients with discharge diagnosis codes. We successfully add nearly 20,000 labels to CTPAs in a publicly available dataset and demonstrate the external validity of a semi-supervised language model in accelerating hematologic research.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00044
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MIMIC-IV-Ext-PE: Using a large language model to predict pulmonary embolism phenotype in the MIMIC-IV dataset
Lam, B. D.
Ma, S.
Kovalenko, I.
Wang, P.
Jafari, O.
Li, A.
Horng, S.
Computation and Language
Machine Learning
Pulmonary embolism (PE) is a leading cause of preventable in-hospital mortality. Advances in diagnosis, risk stratification, and prevention can improve outcomes. There are few large publicly available datasets that contain PE labels for research. Using the MIMIC-IV database, we extracted all available radiology reports of computed tomography pulmonary angiography (CTPA) scans and two physicians manually labeled the results as PE positive (acute PE) or PE negative. We then applied a previously finetuned Bio_ClinicalBERT transformer language model, VTE-BERT, to extract labels automatically. We verified VTE-BERT's reliability by measuring its performance against manual adjudication. We also compared the performance of VTE-BERT to diagnosis codes. We found that VTE-BERT has a sensitivity of 92.4% and positive predictive value (PPV) of 87.8% on all 19,942 patients with CTPA radiology reports from the emergency room and/or hospital admission. In contrast, diagnosis codes have a sensitivity of 95.4% and PPV of 83.8% on the subset of 11,990 hospitalized patients with discharge diagnosis codes. We successfully add nearly 20,000 labels to CTPAs in a publicly available dataset and demonstrate the external validity of a semi-supervised language model in accelerating hematologic research.
title MIMIC-IV-Ext-PE: Using a large language model to predict pulmonary embolism phenotype in the MIMIC-IV dataset
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2411.00044