LSTM Model for Sepsis Detection and Classification Using PPG Signals

Sepsis is a severe medical illness with over 1.7 million cases reported each year in the United States. This condition is the result of an inflated immunological response to infection. Early diagnosis of sepsis remains a major challenge in healthcare due to initial symptoms being nonspecific and the lack of currently available biomarkers that demonstrate sufficient specificity or sensitivity suitable for clinical practice. Wearable technologies, such as photoplethysmography (PPG), have led to the development of improved diagnostic instruments. PPG uses optical technology to measure changes in blood volume in peripheral tissues, enabling continuous monitoring. Identifying modest physiological changes that indicate sepsis can be challenging since they occur without a body reaction. Deep Learning (DL) models can help overcome the diagnostic gap in sepsis diagnosis and intervention. This study analyzes sepsis-related characteristics in PPG signals utilizing a collection of waveform records from both sepsis and control cases. The proposed model consists of five layers: input sequence, long short-term memory (LSTM), fully-connected, softmax, and classification. The LSTM layer is chosen to extract and filter features from cycles of PPG signals; then, the features pass through a fully-connected layer to be classified. We tested our LSTM-based model on 915 one-second intervals to identify and classify sepsis severity. Our LSTM-based model accurately detected sepsis (91.30% for training and 89.74% for testing). The sepsis severity categorization achieved an accuracy of 85.9% in training and 81.4% in testing. Multiple training attempts were conducted to validate the model’s detecting capabilities. Preliminary results show that a deep learning model utilizing an LSTM layer can detect and categorize sepsis using PPG data, potentially allowing for real-time diagnosis and monitoring within a single cycle.