Session ID: 

Who’s Sick? Predictive Analytics Monitoring at the Bedside

3:00pm - 4:00pm Tuesday, March 10
Orlando - Orange County Convention Center


Big data and predictive analytics can meet the need for early detection of patient deterioration due to subacute potentially catastrophic illnesses. Clinicians are challenged to detect patient deterioration based on current monitoring, which is only a display of present values and limited views of trends. Physicians suspect that better analysis of the existing multiple streams of data could detect subclinical changes of deterioration and allow earlier diagnosis and therapy, leading to improved outcomes. Experienced clinicians would be hard-pressed to quantify their intuition or to be continuously present at every bedside. Based on these assumptions, we have developed bedside monitoring that detects physiology going wrong that clinicians can’t see. The basic ideas are that potentially catastrophic medical and surgical illnesses have subclinical phases during which early diagnosis and treatment might have life-saving effects. These phases are characterized by signatures of illness in the clinical and continuous monitoring data.

Learning Objectives

  • Recognize the incidence and impact of unanticipated clinical deterioration in floor and ICU patients
  • Describe the role of predictive analytics monitoring in healthcare as a means for early identification of patients at increasing risk of clinical deterioration
  • Describe the importance of using continuous cardiorespiratory monitoring data along with vital signs and lab tests for predictive analytics monitoring
  • Recognize the unique value of presenting clinicians with a visual indicator of clinical deterioration


Professor of Medicine, Physiology and Biomedical Engineering,
University of Virginia


Chief Quality, Chief Clin Transformation Officer
Nurse or Nurse Practitioner
Physician or Physician’s Assistant