Open Access iconOpen Access

ARTICLE

crossmark

Sepsis Prediction Using CNNBDLSTM and Temporal Derivatives Feature Extraction in the IoT Medical Environment

Sapiah Sakri1, Shakila Basheer1, Zuhaira Muhammad Zain1, Nurul Halimatul Asmak Ismail2,*, Dua’ Abdellatef Nassar1, Manal Abdullah Alohali1, Mais Ayman Alharaki1

1 Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh, 11671, Kingdom of Saudi Arabia
2 Department of Computer Science and Information Technology, Applied College, Princess Nourah Bint Abdulrahman University, Riyadh, 11671, Kingdom of Saudi Arabia

* Corresponding Author: Nurul Halimatul Asmak Ismail. Email: email

Computers, Materials & Continua 2024, 79(1), 1157-1185. https://doi.org/10.32604/cmc.2024.048051

Abstract

Background: Sepsis, a potentially fatal inflammatory disease triggered by infection, carries significant health implications worldwide. Timely detection is crucial as sepsis can rapidly escalate if left undetected. Recent advancements in deep learning (DL) offer powerful tools to address this challenge. Aim: Thus, this study proposed a hybrid CNNBDLSTM, a combination of a convolutional neural network (CNN) with a bi-directional long short-term memory (BDLSTM) model to predict sepsis onset. Implementing the proposed model provides a robust framework that capitalizes on the complementary strengths of both architectures, resulting in more accurate and timelier predictions. Method: The sepsis prediction method proposed here utilizes temporal feature extraction to delineate six distinct time frames before the onset of sepsis. These time frames adhere to the sepsis-3 standard requirement, which incorporates 12-h observation windows preceding sepsis onset. All models were trained using the Medical Information Mart for Intensive Care III (MIMIC-III) dataset, which sourced 61,522 patients with 40 clinical variables obtained from the IoT medical environment. The confusion matrix, the area under the receiver operating characteristic curve (AUCROC) curve, the accuracy, the precision, the F1-score, and the recall were deployed to evaluate the models. Result: The CNNBDLSTM model demonstrated superior performance compared to the benchmark and other models, achieving an AUCROC of 99.74% and an accuracy of 99.15% one hour before sepsis onset. These results indicate that the CNNBDLSTM model is highly effective in predicting sepsis onset, particularly within a close proximity of one hour. Implication: The results could assist practitioners in increasing the potential survival of the patient one hour before sepsis onset.

Keywords


Cite This Article

APA Style
Sakri, S., Basheer, S., Zain, Z.M., Ismail, N.H.A., Nassar, D.A. et al. (2024). Sepsis prediction using CNNBDLSTM and temporal derivatives feature extraction in the iot medical environment. Computers, Materials & Continua, 79(1), 1157-1185. https://doi.org/10.32604/cmc.2024.048051
Vancouver Style
Sakri S, Basheer S, Zain ZM, Ismail NHA, Nassar DA, Alohali MA, et al. Sepsis prediction using CNNBDLSTM and temporal derivatives feature extraction in the iot medical environment. Comput Mater Contin. 2024;79(1):1157-1185 https://doi.org/10.32604/cmc.2024.048051
IEEE Style
S. Sakri et al., "Sepsis Prediction Using CNNBDLSTM and Temporal Derivatives Feature Extraction in the IoT Medical Environment," Comput. Mater. Contin., vol. 79, no. 1, pp. 1157-1185. 2024. https://doi.org/10.32604/cmc.2024.048051



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 198

    View

  • 117

    Download

  • 0

    Like

Share Link