UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Multimodal Diagnosis for Pulmonary Embolism from EHR Data and CT Images

Zhi, Zhuo; Elbadawi, Moe; Daneshmend, Adam; Orlu, Mine; Basit, Abdul; Demosthenous, Andreas; Rodrigues, Miguel; (2022) Multimodal Diagnosis for Pulmonary Embolism from EHR Data and CT Images. In: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). (pp. pp. 2053-2057). IEEE: Glasgow, Scotland, United Kingdom. Green open access

[thumbnail of Zhi_root.pdf]
Preview
PDF
Zhi_root.pdf - Accepted Version

Download (1MB) | Preview

Abstract

Pulmonary Embolism (PE) is a severe medical condition that can pose a significant risk to life. Traditional deep learning methods for PE diagnosis are based on Computed Tomography (CT) images and do not consider the patient's clinical context. To make full use of patient's clinical information, this article presents a multimodal fusion model ingesting Electronic Health Record (EHR) data and CT images for PE diagnosis. The proposed model is based on multilayer perception and convolutional neural networks. To remove the invalid information in the EHR data, the multidimensional scaling algorithm is performed for feature dimension reduction. The EHR data and CT images of 600 patients are used for experiments. The experiment results show that the proposed models outperform existing methods and the multimodal fusion model shows better performance than the single-input model.

Type: Proceedings paper
Title: Multimodal Diagnosis for Pulmonary Embolism from EHR Data and CT Images
Event: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Dates: 11 Jul 2022 - 15 Jul 2022
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/embc48229.2022.9871041
Publisher version: https://doi.org/10.1109/EMBC48229.2022.9871041
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Solid modeling, Three-dimensional displays, Medical conditions, Computational modeling, Computed tomography, Biological system modeling, Pulmonary diseases
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
URI: https://discovery.ucl.ac.uk/id/eprint/10155835
Downloads since deposit
0Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item