Lujie Chen1, Olufunmilayo Ogundele2, Gilles Clermont3, Marilyn Hravnak4, Michael R Pinsky3, Artur W Dubrawski1. 1. 1 Auton Laboratory, School of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania. 2. 2 LifeBridge Critical Care, Sinai Hospital Baltimore, Baltimore, Maryland. 3. 3 Department of Critical Care Medicine, School of Medicine, University of Pittsburgh, Pennsylvania; and. 4. 4 Department of Acute and Tertiary Care, University of Pittsburgh School of Nursing, Pittsburgh, Pennsylvania.
Abstract
RATIONALE: Cardiorespiratory insufficiency (CRI) is a term applied to the manifestations of loss of normal cardiorespiratory reserve and portends a bad outcome. CRI occurs commonly in hospitalized patients, but its risk escalation patterns are unexplored. OBJECTIVES: To describe the dynamic and personal character of CRI risk evolution observed through continuous vital sign monitoring of individual step-down unit patients. METHODS: Using a machine learning model, we estimated risk trends for CRI (defined as exceedance of vital sign stability thresholds) for each of 1,971 admissions (1,880 unique patients) to a 24-bed adult surgical trauma step-down unit at an urban teaching hospital in Pittsburgh, Pennsylvania using continuously recorded vital signs from standard bedside monitors. We compared and contrasted risk trends during initial 4-hour periods after step-down unit admission, and again during the 4 hours immediately before the CRI event, between cases (ever had a CRI) and control subjects (never had a CRI). We further explored heterogeneity of risk escalation patterns during the 4 hours before CRI among cases, comparing personalized to nonpersonalized risk. MEASUREMENTS AND MAIN RESULTS: Estimated risk was significantly higher for cases (918) than control subjects (1,053; P ≤ 0.001) during the initial 4-hour stable periods. Among cases, the aggregated nonpersonalized risk trend increased 2 hours before the CRI, whereas the personalized risk trend became significantly different from control subjects 90 minutes ahead. We further discovered several unique phenotypes of risk escalation patterns among cases for nonpersonalized (14.6% persistently high risk, 18.6% early onset, 66.8% late onset) and personalized risk (7.7% persistently high risk, 8.9% early onset, 83.4% late onset). CONCLUSIONS: Insights from this proof-of-concept analysis may guide design of dynamic and personalized monitoring systems that predict CRI, taking into account the triage and real-time monitoring utility of vital signs. These monitoring systems may prove useful in the dynamic allocation of technological and clinical personnel resources in acute care hospitals.
RATIONALE: Cardiorespiratory insufficiency (CRI) is a term applied to the manifestations of loss of normal cardiorespiratory reserve and portends a bad outcome. CRI occurs commonly in hospitalized patients, but its risk escalation patterns are unexplored. OBJECTIVES: To describe the dynamic and personal character of CRI risk evolution observed through continuous vital sign monitoring of individual step-down unit patients. METHODS: Using a machine learning model, we estimated risk trends for CRI (defined as exceedance of vital sign stability thresholds) for each of 1,971 admissions (1,880 unique patients) to a 24-bed adult surgical trauma step-down unit at an urban teaching hospital in Pittsburgh, Pennsylvania using continuously recorded vital signs from standard bedside monitors. We compared and contrasted risk trends during initial 4-hour periods after step-down unit admission, and again during the 4 hours immediately before the CRI event, between cases (ever had a CRI) and control subjects (never had a CRI). We further explored heterogeneity of risk escalation patterns during the 4 hours before CRI among cases, comparing personalized to nonpersonalized risk. MEASUREMENTS AND MAIN RESULTS: Estimated risk was significantly higher for cases (918) than control subjects (1,053; P ≤ 0.001) during the initial 4-hour stable periods. Among cases, the aggregated nonpersonalized risk trend increased 2 hours before the CRI, whereas the personalized risk trend became significantly different from control subjects 90 minutes ahead. We further discovered several unique phenotypes of risk escalation patterns among cases for nonpersonalized (14.6% persistently high risk, 18.6% early onset, 66.8% late onset) and personalized risk (7.7% persistently high risk, 8.9% early onset, 83.4% late onset). CONCLUSIONS: Insights from this proof-of-concept analysis may guide design of dynamic and personalized monitoring systems that predict CRI, taking into account the triage and real-time monitoring utility of vital signs. These monitoring systems may prove useful in the dynamic allocation of technological and clinical personnel resources in acute care hospitals.
Authors: Lujie Chen; Artur Dubrawski; Donghan Wang; Madalina Fiterau; Mathieu Guillame-Bert; Eliezer Bose; Ata M Kaynar; David J Wallace; Jane Guttendorf; Gilles Clermont; Michael R Pinsky; Marilyn Hravnak Journal: Crit Care Med Date: 2016-07 Impact factor: 7.598
Authors: Stephanie Helman; Martha Ann Terry; Tiffany Pellathy; Andrew Williams; Artur Dubrawski; Gilles Clermont; Michael R Pinsky; Salah Al-Zaiti; Marilyn Hravnak Journal: Int J Med Inform Date: 2021-11-11 Impact factor: 4.730
Authors: Marilyn Hravnak; Tiffany Pellathy; Lujie Chen; Artur Dubrawski; Anthony Wertz; Gilles Clermont; Michael R Pinsky Journal: J Electrocardiol Date: 2018-07-29 Impact factor: 1.438
Authors: Anthony Wertz; Andre L Holder; Mathieu Guillame-Bert; Gilles Clermont; Artur Dubrawski; Michael R Pinsky Journal: Crit Care Explor Date: 2019-10-30
Authors: Joo Heung Yoon; Vincent Jeanselme; Artur Dubrawski; Marilyn Hravnak; Michael R Pinsky; Gilles Clermont Journal: Crit Care Date: 2020-11-25 Impact factor: 9.097
Authors: Walter Nelson; Shuang Di; Sankavi Muralitharan; Michael McGillion; P J Devereaux; Neil Grant Barr; Jeremy Petch Journal: J Med Internet Res Date: 2021-02-04 Impact factor: 5.428
Authors: Jacob P Kimball; Omer T Inan; Victor A Convertino; Sylvain Cardin; Michael N Sawka Journal: Sensors (Basel) Date: 2022-01-07 Impact factor: 3.576