Efficient clinical decision-making process via AI-based multimodal data fusion: A COVID-19 case study
COVID-19 is an infectious disease that caused a global pandemic in 2020. In the critical moments of this healthcare emergencies, the medical staff needs to take important decisions in a context of limited resources that must be carefully managed. To this end, the computer-aided diagnosis methods are...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-10-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024146737 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846170208671105024 |
|---|---|
| author | Daniel I. Morís Joaquim de Moura Pedro J. Marcos Enrique Míguez Rey Jorge Novo Marcos Ortega |
| author_facet | Daniel I. Morís Joaquim de Moura Pedro J. Marcos Enrique Míguez Rey Jorge Novo Marcos Ortega |
| author_sort | Daniel I. Morís |
| collection | DOAJ |
| description | COVID-19 is an infectious disease that caused a global pandemic in 2020. In the critical moments of this healthcare emergencies, the medical staff needs to take important decisions in a context of limited resources that must be carefully managed. To this end, the computer-aided diagnosis methods are extremely powerful and help them to better recognize the evidences of high-risk patients. This can be done with the support of relevant information extracted from electronic health records, lab tests and imaging studies. In this work, we present a novel fully-automatic efficient method to help the clinical decision-making process in the context of COVID-19 risk estimation, using multimodal data fusion of clinical features and deep features extracted from chest X-ray images. The risk estimation is studied in two of the most relevant and critical encountered scenarios: the risk of hospitalization and mortality. This study shows which are the most important features for each scenario, the ratio of clinical and imaging features present in the top ranking and the performance of the used machine learning models. The results demonstrate a great performance by the classifiers, estimating the risk of hospitalization with an AUC-ROC of 0.8452 ± 0.0133 and the risk of death with an AUC-ROC of 0.8285 ± 0.0210, only using a subset of the original features, and highlight the significant contribution of imaging features to hospitalization risk assessment, while clinical features become more crucial for mortality risk evaluation. Furthermore, multimodal data fusion can outperform the approaches that use one data source. Despite the model's complexity, it requires fewer features, an advantage in scenarios with limited computational resources. This streamlined, fully-automated method shows promising potential to improve the clinical decision-making process and better manage medical resources, not only in the context of COVID-19, but also in other clinical scenarios. |
| format | Article |
| id | doaj-art-09fae7192f1a4158afb73abe068a6bb2 |
| institution | Kabale University |
| issn | 2405-8440 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-09fae7192f1a4158afb73abe068a6bb22024-11-12T05:19:09ZengElsevierHeliyon2405-84402024-10-011020e38642Efficient clinical decision-making process via AI-based multimodal data fusion: A COVID-19 case studyDaniel I. Morís0Joaquim de Moura1Pedro J. Marcos2Enrique Míguez Rey3Jorge Novo4Marcos Ortega5Varpa Group, Biomedical Research Institute A Coruña (INIBIC), University of A Coruña, 15006, A Coruña, Spain; Department of Computer Science and Information Technologies, University of A Coruña, 15071, A Coruña, SpainVarpa Group, Biomedical Research Institute A Coruña (INIBIC), University of A Coruña, 15006, A Coruña, Spain; Department of Computer Science and Information Technologies, University of A Coruña, 15071, A Coruña, Spain; Corresponding author at: Varpa Group, Biomedical Research Institute A Coruña (INIBIC), University of A Coruña, 15006, A Coruña, Spain.Dirección Asistencial y Servicio de Neumología, Complejo Hospitalario Universitario de A Coruña (CHUAC), Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Sergas, 15006 A Coruña, SpainGrupo de Investigación en Virología Clínica, Sección de Enfermedades Infecciosas, Servicio de Medicina Interna, Instituto de Investigación Biomédica de A Coruña (INIBIC), Área Sanitaria A Coruña y CEE (ASCC), SERGAS, 15006 A Coruña, SpainVarpa Group, Biomedical Research Institute A Coruña (INIBIC), University of A Coruña, 15006, A Coruña, Spain; Department of Computer Science and Information Technologies, University of A Coruña, 15071, A Coruña, SpainVarpa Group, Biomedical Research Institute A Coruña (INIBIC), University of A Coruña, 15006, A Coruña, Spain; Department of Computer Science and Information Technologies, University of A Coruña, 15071, A Coruña, SpainCOVID-19 is an infectious disease that caused a global pandemic in 2020. In the critical moments of this healthcare emergencies, the medical staff needs to take important decisions in a context of limited resources that must be carefully managed. To this end, the computer-aided diagnosis methods are extremely powerful and help them to better recognize the evidences of high-risk patients. This can be done with the support of relevant information extracted from electronic health records, lab tests and imaging studies. In this work, we present a novel fully-automatic efficient method to help the clinical decision-making process in the context of COVID-19 risk estimation, using multimodal data fusion of clinical features and deep features extracted from chest X-ray images. The risk estimation is studied in two of the most relevant and critical encountered scenarios: the risk of hospitalization and mortality. This study shows which are the most important features for each scenario, the ratio of clinical and imaging features present in the top ranking and the performance of the used machine learning models. The results demonstrate a great performance by the classifiers, estimating the risk of hospitalization with an AUC-ROC of 0.8452 ± 0.0133 and the risk of death with an AUC-ROC of 0.8285 ± 0.0210, only using a subset of the original features, and highlight the significant contribution of imaging features to hospitalization risk assessment, while clinical features become more crucial for mortality risk evaluation. Furthermore, multimodal data fusion can outperform the approaches that use one data source. Despite the model's complexity, it requires fewer features, an advantage in scenarios with limited computational resources. This streamlined, fully-automated method shows promising potential to improve the clinical decision-making process and better manage medical resources, not only in the context of COVID-19, but also in other clinical scenarios.http://www.sciencedirect.com/science/article/pii/S2405844024146737Information fusionRisk estimationClinical dataDeep featuresCOVID-19Chest X-ray |
| spellingShingle | Daniel I. Morís Joaquim de Moura Pedro J. Marcos Enrique Míguez Rey Jorge Novo Marcos Ortega Efficient clinical decision-making process via AI-based multimodal data fusion: A COVID-19 case study Heliyon Information fusion Risk estimation Clinical data Deep features COVID-19 Chest X-ray |
| title | Efficient clinical decision-making process via AI-based multimodal data fusion: A COVID-19 case study |
| title_full | Efficient clinical decision-making process via AI-based multimodal data fusion: A COVID-19 case study |
| title_fullStr | Efficient clinical decision-making process via AI-based multimodal data fusion: A COVID-19 case study |
| title_full_unstemmed | Efficient clinical decision-making process via AI-based multimodal data fusion: A COVID-19 case study |
| title_short | Efficient clinical decision-making process via AI-based multimodal data fusion: A COVID-19 case study |
| title_sort | efficient clinical decision making process via ai based multimodal data fusion a covid 19 case study |
| topic | Information fusion Risk estimation Clinical data Deep features COVID-19 Chest X-ray |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024146737 |
| work_keys_str_mv | AT danielimoris efficientclinicaldecisionmakingprocessviaaibasedmultimodaldatafusionacovid19casestudy AT joaquimdemoura efficientclinicaldecisionmakingprocessviaaibasedmultimodaldatafusionacovid19casestudy AT pedrojmarcos efficientclinicaldecisionmakingprocessviaaibasedmultimodaldatafusionacovid19casestudy AT enriquemiguezrey efficientclinicaldecisionmakingprocessviaaibasedmultimodaldatafusionacovid19casestudy AT jorgenovo efficientclinicaldecisionmakingprocessviaaibasedmultimodaldatafusionacovid19casestudy AT marcosortega efficientclinicaldecisionmakingprocessviaaibasedmultimodaldatafusionacovid19casestudy |