Parsimonious waveform-derived features consisting of pulse arrival time and heart rate variability predicts the onset of septic shock

Moamen M. Soliman*, Curtis Marshall, Jacob P. Kimball, Tilendra Choudhary, Gilles Clermont, Michael R. Pinsky, Timothy G. Buchman, Craig M. Coopersmith, Omer T. Inan, Rishikesan Kamaleswaran

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


Sepsis is a major public health emergency and one of the leading causes of morbidity and mortality in critically ill patients. For each hour treatment is delayed, shock-related mortality increases, so early diagnosis and intervention is of utmost importance. However, earlier recognition of shock requires active monitoring, which may be delayed due to subclinical manifestations of the disease at the early phase of onset. Machine learning systems can increase timely detection of shock onset by exploiting complex interactions among continuous physiological waveforms. We use a dataset consisting of high-resolution physiological waveforms from intensive care unit (ICU) of a tertiary hospital system. We investigate the use of mean arterial blood pressure (MAP), pulse arrival time (PAT), heart rate variability (HRV), and heart rate (HR) for the early prediction of shock onset. Using only five minutes of the aforementioned vital signals from 239 ICU patients, our developed models can accurately predict septic shock onset 6 to 36 h prior to clinical recognition with area under the receiver operating characteristic (AUROC) of 0.84 and 0.8 respectively. This work lays foundations for a robust, efficient, accurate and early prediction of septic shock onset which may help clinicians in their decision-making processes. This study introduces machine learning models that provide fast and accurate predictions of septic shock onset times up to 36 h in advance. BP, PAT and HR dynamics can independently predict septic shock onset with a look-back period of only 5 mins.

Original languageEnglish
Article number105974
JournalBiomedical Signal Processing and Control
StatePublished - Jun 2024
Externally publishedYes


  • Early warning score
  • Fast sepsis detection
  • Intensive care unit
  • Machine learning for Sepsis
  • Septic shock prediction


Dive into the research topics of 'Parsimonious waveform-derived features consisting of pulse arrival time and heart rate variability predicts the onset of septic shock'. Together they form a unique fingerprint.

Cite this