Author
Listed:
- Sona G.
- Anitha D.
- Narmatha B.
Abstract
Sepsis develops whenever our immune system's response to an infection becomes dysregulated, leading to extensive inflammation and organ damage. It is a severe immune system imbalance that, if ignored, can cause tissue damage, various organ failures, and death. Using multivariate clinical time-series data, a hybrid deep learning system combining a Temporal Convolutional Network (TCN) and a Tabular Transformer is developed for early prediction. The Sepsis Prediction Dataset is used in this work. The dataset consists of 40 clinical variables that have been gathered continuously in Intensive Care Unit (ICU) settings, which include vital signs, laboratory results, and demographic data. Two parallel branches are used for designing the proposed structure. The first branch, named the Tabular Transformer branch, learns the representations and interactions of variables through the handling of dynamic and categorical data. The Temporal Convolutional Network branch processes the sequential inputs by using dilated temporal convolution to detect long-range patterns within physiological signals. After concatenating both outputs and passing them into a fully connected layer, it makes predictions regarding the early phases of sepsis. With regard to its early predictions four to six hours before the clinical diagnoses, its sensitivity, specificity, accuracy, and F1-score were found to be 96.65%, 98.32%, 98.9%, and 96.3% respectively. These results indicate that the early detection of sepsis would improve as a result of integrating continuous patient data along with temporal patterns. Further validation of the developed model needs to be made on other clinical datasets.
Suggested Citation
Handle:
RePEc:gvu:iroiip:v:8:y:2026:i:2:id:2181
DOI: 10.36548/jiip.2026.2.005
Download full text from publisher
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gvu:iroiip:v:8:y:2026:i:2:id:2181. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Journal Manager (email available below). General contact details of provider: https://irojournals.com/iroiip .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.