Your browser doesn't support javascript.
loading
Artificial intelligence-based pulmonary embolism classification: Development and validation using real-world data.
Silva, Luan Oliveira da; Silva, Maria Carolina Bueno da; Ribeiro, Guilherme Alberto Sousa; Camargo, Thiago Fellipe Ortiz de; Santos, Paulo Victor Dos; Mendes, Giovanna de Souza; Paiva, Joselisa Peres Queiroz de; Soares, Anderson da Silva; Reis, Márcio Rodrigues da Cunha; Loureiro, Rafael Maffei; Calixto, Wesley Pacheco.
Afiliação
  • Silva LOD; Department of Radiology, Hospital Israelita Albert Einstein, Sao Paulo, Brazil.
  • Silva MCBD; Institute of Informatics (INF), Federal University of Goias, Goiania, Brazil.
  • Ribeiro GAS; Department of Radiology, Hospital Israelita Albert Einstein, Sao Paulo, Brazil.
  • Camargo TFO; Department of Radiology, Hospital Israelita Albert Einstein, Sao Paulo, Brazil.
  • Santos PVD; Department of Radiology, Hospital Israelita Albert Einstein, Sao Paulo, Brazil.
  • Mendes GS; Electrical, Mechanical & Computer Engineering School, Federal University of Goias, Goiania, Brazil.
  • Paiva JPQ; Department of Radiology, Hospital Israelita Albert Einstein, Sao Paulo, Brazil.
  • Soares ADS; Electrical, Mechanical & Computer Engineering School, Federal University of Goias, Goiania, Brazil.
  • Reis MRDC; Department of Radiology, Hospital Israelita Albert Einstein, Sao Paulo, Brazil.
  • Loureiro RM; Department of Radiology, Hospital Israelita Albert Einstein, Sao Paulo, Brazil.
  • Calixto WP; Institute of Informatics (INF), Federal University of Goias, Goiania, Brazil.
PLoS One ; 19(8): e0305839, 2024.
Article em En | MEDLINE | ID: mdl-39167612
ABSTRACT
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 V2 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.
Assuntos

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Embolia Pulmonar / Inteligência Artificial / Redes Neurais de Computação / Angiografia por Tomografia Computadorizada Limite: Adult / Aged / Female / Humans / Male / Middle aged Idioma: En Ano de publicação: 2024 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Embolia Pulmonar / Inteligência Artificial / Redes Neurais de Computação / Angiografia por Tomografia Computadorizada Limite: Adult / Aged / Female / Humans / Male / Middle aged Idioma: En Ano de publicação: 2024 Tipo de documento: Article