AI-Powered Early Detection of Sepsis using Infrared Image Multi-Target based Faster Region-based Convolutional Neural Network

Sepsis is a complex and heterogeneous syndrome that continues to pose significant challenges to healthcare globally, particularly in realm of Al-powered early detection. The increasing demand for Intensive Care Unit (ICU) admissions and associated rising costs have urged the need for effective management strategies. The problem of the sepsis addresses the issues of misclassification and insurance organizations that arise from inefficient the medical recorder. This paper, proposed Infrared Image multi-target based Faster Region-based Convolutional Neural Network (FR-CNN) technique efficiently achieve better performance in the sepsis detection. Initially data obtained from the Best care database at KAMC with a focus on patient care in ICU through analysis of medical records. The pre-processing utilized min-max normalization and enhance the image quality which is uniformly to process the feature vector. The FR-CNN architecture is involved to identify the sepsis in multiple within infrared image. The model is trained using labelled data that include various infrared image depicting sepsis related feature and detection the complex patterns associated with sepsis, which is achieve better accuracy. The performance of proposed method is evaluated with various metrics such as accuracy, precision, recall and f1-score metrics on Best care database.