Journal Article

Artificial intelligence-based pulmonary embolism classification: Development and validation using real-world data

Ribeiro, Guilherme Alberto Sousa, Santos, Paulo Victor dos, Soares, Anderson da Silva, Camargo, Thiago Fellipe Ortiz de, Reis, Márcio Rodrigues da Cunha, Mendes, Giovanna de Souza, Silva, Luan Oliveira da, Paiva, Joselisa Peres Queiroz de, Silva, Maria Carolina Bueno da, Calixto, Wesley Pacheco, Loureiro, Rafael Maffei

2024

Overview

This paper presents an artificial intelligence-based classification model for the detection of pulmonary embolism in computed tomography angiography. The proposed model, developed from public data and validated on a large dataset from a tertiary hospital, uses a two-dimensional approach that integrates temporal series to classify each slice of the examination and make predictions at both slice and examination levels. The training process consists of two stages: first using a convolutional neural network InceptionResNet V 2 and then a recurrent neural network long short-term memory model. This approach achieved an accuracy of 93% at the slice level and 77% at the examination level. External validation using a hospital dataset resulted in a precision of 86% for positive pulmonary embolism cases and 69% for negative pulmonary embolism cases. Notably, the model excels in excluding pulmonary embolism, achieving a precision of 73% and a recall of 82%, emphasizing its clinical value in reducing unnecessary interventions. In addition, the diverse demographic distribution in the validation dataset strengthens the model’s generalizability. Overall, this model offers promising potential for accurate detection and exclusion of pulmonary embolism, potentially streamlining diagnosis and improving patient outcomes.

• Publisher: Public Library of Science,Public Library of Science (PLoS)
• Subject: Accuracy / Adult / Aged / Algorithms / Analysis / Angiography / Artificial Intelligence / Artificial neural networks / Biology and Life Sciences / Care and treatment / Classification / Computational linguistics / Computed tomography / Computed Tomography Angiography - methods / Computer and Information Sciences / CT imaging / Datasets / Deep learning / Diagnosis / Embolism / Female / Geospatial data / Health aspects / Hospitals / Humans / Language processing / Long short-term memory / Male / Medical imaging equipment / Medicine and Health Sciences / Middle Aged / Mortality / Natural language interfaces / Neural networks / Neural Networks, Computer / People and Places / Public health / Pulmonary arteries / Pulmonary embolism / Pulmonary Embolism - classification / Pulmonary Embolism - diagnosis / Pulmonary Embolism - diagnostic imaging / Pulmonary embolisms / Recurrent neural networks / Research and Analysis Methods / Scintigraphy / Tomography