Corticosteroid treatment prediction using chest X-ray and clinical data

Background and Objective: Severe courses of COVID-19 disease can lead to long-term complications. The post-acute phase of COVID-19 refers to the persistent or new symptoms. This problem is becoming more relevant with the increasing number of patients who have contracted COVID-19 and the emergence of...

Full description

Saved in:
Bibliographic Details
Main Authors: Anzhelika Mezina, Samuel Genzor, Radim Burget, Vojtech Myska, Jan Mizera, Aleksandr Ometov
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Computational and Structural Biotechnology Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2001037023004713
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850054857131556864
author Anzhelika Mezina
Samuel Genzor
Radim Burget
Vojtech Myska
Jan Mizera
Aleksandr Ometov
author_facet Anzhelika Mezina
Samuel Genzor
Radim Burget
Vojtech Myska
Jan Mizera
Aleksandr Ometov
author_sort Anzhelika Mezina
collection DOAJ
description Background and Objective: Severe courses of COVID-19 disease can lead to long-term complications. The post-acute phase of COVID-19 refers to the persistent or new symptoms. This problem is becoming more relevant with the increasing number of patients who have contracted COVID-19 and the emergence of new virus variants. In this case, preventive treatment with corticosteroids can be applied. However, not everyone benefits from the treatment, moreover, it can have severe side effects. Currently, no study would analyze who benefits from the treatment. Methods: This work introduces a novel approach to the recommendation of Corticosteroid (CS) treatment for patients in the post-acute phase. We have used a novel combination of clinical data, including blood tests, spirometry, and X-ray images from 273 patients. These are very challenging to collect, especially from patients in the post-acute phase of COVID-19. To our knowledge, no similar dataset exists in the literature. Moreover, we have proposed a unique methodology that combines machine learning and deep learning models based on Vision Transformer (ViT) and InceptionNet, preprocessing techniques, and pretraining strategies to deal with the specific characteristics of our data. Results: The experiments have proved that combining clinical data with CXR images achieves 8% higher accuracy than independent analysis of CXR images. The proposed method reached 80.0% accuracy (78.7% balanced accuracy) and a ROC-AUC of 0.89. Conclusions: The introduced system for CS treatment prediction using our neural network and learning algorithm is unique in this field of research. Here, we have shown the efficiency of using mixed data and proved it on real-world data. The paper also introduces the factors that could be used to predict long-term complications. Additionally, this system was deployed to the hospital environment as a recommendation tool, which admits the clinical application of the proposed methodology.
format Article
id doaj-art-3853ebc88caf4caeb1add7cecaedadb4
institution DOAJ
issn 2001-0370
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Computational and Structural Biotechnology Journal
spelling doaj-art-3853ebc88caf4caeb1add7cecaedadb42025-08-20T02:52:08ZengElsevierComputational and Structural Biotechnology Journal2001-03702024-12-0124536510.1016/j.csbj.2023.11.057Corticosteroid treatment prediction using chest X-ray and clinical dataAnzhelika Mezina0Samuel Genzor1Radim Burget2Vojtech Myska3Jan Mizera4Aleksandr Ometov5Brno University of Technology, FEEC, Dept. of Telecommunications, Technicka 12, Brno, 616 00, Czech Republic; Corresponding authors.Center for Digital Health, Palacky Univesity Olomouc, Faculty of Medicine and Dentistry, Hnevotinska 976/3, Olomouc 779 00, Czech Republic; Corresponding authors.Brno University of Technology, FEEC, Dept. of Telecommunications, Technicka 12, Brno, 616 00, Czech RepublicBrno University of Technology, FEEC, Dept. of Telecommunications, Technicka 12, Brno, 616 00, Czech RepublicCenter for Digital Health, Palacky Univesity Olomouc, Faculty of Medicine and Dentistry, Hnevotinska 976/3, Olomouc 779 00, Czech RepublicElectrical Engineering Unit, Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, 33720, FinlandBackground and Objective: Severe courses of COVID-19 disease can lead to long-term complications. The post-acute phase of COVID-19 refers to the persistent or new symptoms. This problem is becoming more relevant with the increasing number of patients who have contracted COVID-19 and the emergence of new virus variants. In this case, preventive treatment with corticosteroids can be applied. However, not everyone benefits from the treatment, moreover, it can have severe side effects. Currently, no study would analyze who benefits from the treatment. Methods: This work introduces a novel approach to the recommendation of Corticosteroid (CS) treatment for patients in the post-acute phase. We have used a novel combination of clinical data, including blood tests, spirometry, and X-ray images from 273 patients. These are very challenging to collect, especially from patients in the post-acute phase of COVID-19. To our knowledge, no similar dataset exists in the literature. Moreover, we have proposed a unique methodology that combines machine learning and deep learning models based on Vision Transformer (ViT) and InceptionNet, preprocessing techniques, and pretraining strategies to deal with the specific characteristics of our data. Results: The experiments have proved that combining clinical data with CXR images achieves 8% higher accuracy than independent analysis of CXR images. The proposed method reached 80.0% accuracy (78.7% balanced accuracy) and a ROC-AUC of 0.89. Conclusions: The introduced system for CS treatment prediction using our neural network and learning algorithm is unique in this field of research. Here, we have shown the efficiency of using mixed data and proved it on real-world data. The paper also introduces the factors that could be used to predict long-term complications. Additionally, this system was deployed to the hospital environment as a recommendation tool, which admits the clinical application of the proposed methodology.http://www.sciencedirect.com/science/article/pii/S2001037023004713Image classificationChest X-ray imagesVision transformerTreatment predictionClinical dataPost-acute COVID-19
spellingShingle Anzhelika Mezina
Samuel Genzor
Radim Burget
Vojtech Myska
Jan Mizera
Aleksandr Ometov
Corticosteroid treatment prediction using chest X-ray and clinical data
Computational and Structural Biotechnology Journal
Image classification
Chest X-ray images
Vision transformer
Treatment prediction
Clinical data
Post-acute COVID-19
title Corticosteroid treatment prediction using chest X-ray and clinical data
title_full Corticosteroid treatment prediction using chest X-ray and clinical data
title_fullStr Corticosteroid treatment prediction using chest X-ray and clinical data
title_full_unstemmed Corticosteroid treatment prediction using chest X-ray and clinical data
title_short Corticosteroid treatment prediction using chest X-ray and clinical data
title_sort corticosteroid treatment prediction using chest x ray and clinical data
topic Image classification
Chest X-ray images
Vision transformer
Treatment prediction
Clinical data
Post-acute COVID-19
url http://www.sciencedirect.com/science/article/pii/S2001037023004713
work_keys_str_mv AT anzhelikamezina corticosteroidtreatmentpredictionusingchestxrayandclinicaldata
AT samuelgenzor corticosteroidtreatmentpredictionusingchestxrayandclinicaldata
AT radimburget corticosteroidtreatmentpredictionusingchestxrayandclinicaldata
AT vojtechmyska corticosteroidtreatmentpredictionusingchestxrayandclinicaldata
AT janmizera corticosteroidtreatmentpredictionusingchestxrayandclinicaldata
AT aleksandrometov corticosteroidtreatmentpredictionusingchestxrayandclinicaldata