Carl F Sabottke1,2, Marc A Breaux3,4, Bradley M Spieler4. 1. Department of Internal Medicine, University Hospital and Clinics, Lafayette, LA, USA. cfs121090@gmail.com. 2. Department of Radiology, Louisiana State University Health Sciences Center, New Orleans, LA, USA. cfs121090@gmail.com. 3. Department of Internal Medicine, University Hospital and Clinics, Lafayette, LA, USA. 4. Department of Radiology, Louisiana State University Health Sciences Center, New Orleans, LA, USA.
Abstract
PURPOSE: Patient age has important clinical utility for refining a differential diagnosis in radiology. Here, we evaluate the potential for convolutional neural network models to predict patient age based on anterior-posterior chest radiographs for instances where patients may present for emergency services without the ability to provide this identifying information. METHODS: We used the CheXpert dataset of 224,316 chest radiographs from 65,240 patients to train CNN regression models with ResNet50 and DenseNet121 architectures for prediction of patient age based on anterior-posterior (AP) view chest radiographs. We evaluate these models on both the CheXpert validation dataset and a local hospital case in which a patient initially presented for emergency services intubated and without identification. RESULTS: Mean absolute error (MAE) for our ResNet50 model on the CheXpert dataset is 4.94 years for predicting patient age based on AP chest radiographs. MAE for our DenseNet121 model is 4.69 years. Both models have a correlation coefficient between true patient ages and predicted ages of 0.944. Wilcoxon rank-sum comparison between the two model architectures shows no significant difference (p = 0.33), but both show improvement over a baseline demographic-driven estimation (p < 0.001). CONCLUSIONS: For circumstances in which patients present for healthcare services without readily accessible identification such as in the setting trauma or altered mental status, CNN regression models for age prediction have potential clinical utility for refining estimates related to this missing patient information.
PURPOSE:Patient age has important clinical utility for refining a differential diagnosis in radiology. Here, we evaluate the potential for convolutional neural network models to predict patient age based on anterior-posterior chest radiographs for instances where patients may present for emergency services without the ability to provide this identifying information. METHODS: We used the CheXpert dataset of 224,316 chest radiographs from 65,240 patients to train CNN regression models with ResNet50 and DenseNet121 architectures for prediction of patient age based on anterior-posterior (AP) view chest radiographs. We evaluate these models on both the CheXpert validation dataset and a local hospital case in which a patient initially presented for emergency services intubated and without identification. RESULTS: Mean absolute error (MAE) for our ResNet50 model on the CheXpert dataset is 4.94 years for predicting patient age based on AP chest radiographs. MAE for our DenseNet121 model is 4.69 years. Both models have a correlation coefficient between true patient ages and predicted ages of 0.944. Wilcoxon rank-sum comparison between the two model architectures shows no significant difference (p = 0.33), but both show improvement over a baseline demographic-driven estimation (p < 0.001). CONCLUSIONS: For circumstances in which patients present for healthcare services without readily accessible identification such as in the setting trauma or altered mental status, CNN regression models for age prediction have potential clinical utility for refining estimates related to this missing patient information.
Entities:
Keywords:
Chest radiography; Convolutional neural networks; Deep learning; Emergency medicine
Authors: Paul H Yi; Jinchi Wei; Tae Kyung Kim; Jiwon Shin; Haris I Sair; Ferdinand K Hui; Gregory D Hager; Cheng Ting Lin Journal: Emerg Radiol Date: 2021-06-05