Multi-Modal Deep Learning for COVID-19 Severity Assessment via Gene Expression and Clinical Data Integration 


Vol. 14,  No. 7, pp. 548-554, Jul.  2025
https://doi.org/10.3745/TKIPS.2025.14.7.548


PDF
  Abstract

Accurately predicting the severity of severe acute respiratory syndrome (SARS-CoV-2) infection is crucial for effective patient management and resource allocation. Building on the ExPDrug model, which utilizes gene expression data and gene-pathway relationships for severity prediction, we develop a novel multi-modal model that integrates an additional modality by incorporating a projection layer to align heterogeneous data sources including clinical patient information. The experimental results demonstrate that the multimodal model outperforms ExPDrug in terms of the area under the curve (AUC), accuracy, and precision, particularly for CD8+ T cells. To enhance the interpretability of the findings, the Local Interpretable Model-agnostic Explanations (LIME) method was employed, which identified respiration rate and SpO2 as pivotal clinical indicators. These features may help explain the model’s strong performance for CD8+ T cells, based on their relationship with specific immune cell activities. These observations underscore the synergistic value of integrating gene expression and clinical data for severity prediction in COVID-19.

  Statistics
  Cite this article

[IEEE Style]

S. Ha, J. Park, K. Jo, "Multi-Modal Deep Learning for COVID-19 Severity Assessment via Gene Expression and Clinical Data Integration," The Transactions of the Korea Information Processing Society, vol. 14, no. 7, pp. 548-554, 2025. DOI: https://doi.org/10.3745/TKIPS.2025.14.7.548.

[ACM Style]

Soojung Ha, Juho Park, and Kyuri Jo. 2025. Multi-Modal Deep Learning for COVID-19 Severity Assessment via Gene Expression and Clinical Data Integration. The Transactions of the Korea Information Processing Society, 14, 7, (2025), 548-554. DOI: https://doi.org/10.3745/TKIPS.2025.14.7.548.

Forms

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

Old Journals

Indexing

All publications of TKIPS is indexed in DOI, EBSCO, Google Scholar, Crossref, and CrossCheck.

TKIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).

Related Journals