Interpreting Forecasted Vital Signs Using N-BEATS in Sepsis Patients

TL;DR

This paper explores the use of an interpretable deep learning model, N-BEATS, to forecast vital signs in sepsis patients, aiding early detection of septic shock and understanding drug effects in ICU settings.

Contribution

It applies the N-BEATS model to predict vital sign trends in sepsis patients and evaluates its interpretability and accuracy using real ICU data.

Findings

Achieved low error metrics (MSE, MAPE, DTW) in vital sign forecasting.

Found higher mortality rates when forecasted and actual trends matched closely.

Provided insights into drug impacts on vital sign changes.

Abstract

Detecting and predicting septic shock early is crucial for the best possible outcome for patients. Accurately forecasting the vital signs of patients with sepsis provides valuable insights to clinicians for timely interventions, such as administering stabilizing drugs or optimizing infusion strategies. Our research examines N-BEATS, an interpretable deep-learning forecasting model that can forecast 3 hours of vital signs for sepsis patients in intensive care units (ICUs). In this work, we use the N-BEATS interpretable configuration to forecast the vital sign trends and compare them with the actual trend to understand better the patient's changing condition and the effects of infused drugs on their vital signs. We evaluate our approach using the publicly available eICU Collaborative Research Database dataset and rigorously evaluate the vital sign forecasts using out-of-sample evaluation criteria. We present the performance of our model using error metrics, including mean squared error (MSE), mean average percentage error (MAPE), and dynamic time warping (DTW), where the best scores achieved are 18.52e-4, 7.60, and 17.63e-3, respectively. We analyze the samples where the forecasted trend does not match the actual trend and study the impact of infused drugs on changing the actual vital signs compared to the forecasted trend. Additionally, we examined the mortality rates of patients where the actual trend and the forecasted trend did not match. We observed that the mortality rate was higher (92%) when the actual and forecasted trends closely matched, compared to when they were not similar (84%).