Severity Trajectories of Pediatric Inpatients Using the Criticality Index

被引:10
作者
Rivera, Eduardo A. Trujillo [1 ]
Patel, Anita K. [2 ]
Zeng-Treitler, Qing [1 ]
Chamberlain, James M. [3 ]
Bost, James E. [4 ]
Heneghan, Julia A. [2 ,6 ]
Morizono, Hiroki [5 ]
Pollack, Murray M. [2 ]
机构
[1] George Washington Univ, Sch Med & Hlth Sci, Washington, DC 20052 USA
[2] George Washington Univ, Childrens Natl Hosp, Dept Pediat, Div Crit Care Med,Sch Med & Hlth Sci, Washington, DC 20052 USA
[3] George Washington Univ, Childrens Natl Hosp, Dept Pediat, Div Emergency Med,Sch Med & Hlth Sci, Washington, DC USA
[4] George Washington Univ, Childrens Natl Hosp, Sch Med & Hlth Sci, Washington, DC USA
[5] George Washington Univ, Childrens Natl Res Inst, Associate Res Prof Genom & Precis Med, Sch Med & Hlth Sci, Washington, DC USA
[6] Univ Minnesota, Dept Pediat, Div Crit Care Med, Masonic Childrens Hosp, Minneapolis, MN USA
基金
美国国家卫生研究院;
关键词
dynamic modeling; intensive care; machine learning; pediatric intensive care unit; pediatrics; severity of illness; END-OF-LIFE; INTENSIVE-CARE; ACUTE PHYSIOLOGY; MORTALITY; SCORE; PREDICTION; RISK; VALIDATION; NETWORKS; OUTCOMES;
D O I
10.1097/PCC.0000000000002561
中图分类号
R4 [临床医学];
学科分类号
1002 ; 100602 ;
摘要
Objectives: To assess severity of illness trajectories described by the Criticality Index for survivors and deaths in five patient groups defined by the sequence of patient care in ICU and routine patient care locations. Design: The Criticality Index developed using a calibrated, deep neural network, measures severity of illness using physiology, therapies, and therapeutic intensity. Criticality Index values in sequential 6-hour time periods described severity trajectories. Setting: Hospitals with pediatric inpatient and ICU care. Patients: Pediatric patients never cared for in an ICU (n = 20,091), patients only cared for in the ICU (n = 2,096) and patients cared for in both ICU and non-ICU care locations (n = 17,023) from 2009 to 2016 Health Facts database (Cerner Corporation, Kansas City, MO). Interventions: None. Measurements and Main Results: Criticality Index values were consistent with clinical experience. The median (25-75th percentile) ICU Criticality Index values (0.878 [0.696-0.966]) were more than 80-fold higher than the non-ICU values (0.010 [0.002-0.099]). Non-ICU Criticality Index values for patients transferred to the ICU were 40-fold higher than those never transferred to the ICU (0.164 vs 0.004). The median for ICU deaths was higher than ICU survivors (0.983 vs 0.875) (p < 0.001). The severity trajectories for the five groups met expectations based on clinical experience. Survivors had increasing Criticality Index values in non-ICU locations prior to ICU admission, decreasing Criticality Index values in the ICU, and decreasing Criticality Index values until hospital discharge. Deaths had higher Criticality Index values than survivors, steeper increases prior to the ICU, and worsening values in the ICU. Deaths had a variable course, especially those who died in non-ICU care locations, consistent with deaths associated with both active therapies and withdrawals/limitations of care. Conclusions: Severity trajectories measured by the Criticality Index showed strong validity, reflecting the expected clinical course for five diverse patient groups.
引用
收藏
页码:E19 / E32
页数:14
相关论文
共 39 条
  • [1] Evaluation of ICU Risk Models Adapted for Use as Continuous Markers of Severity of Illness Throughout the ICU Stay*
    Badawi, Omar
    Liu, Xinggang
    Hassan, Erkan
    Amelung, Pamela J.
    Swami, Sunil
    [J]. CRITICAL CARE MEDICINE, 2018, 46 (03) : 361 - 367
  • [2] Bang S-J, PHASED LSTM BASED PR
  • [3] APACHE OUTCOMES ACROSS VENUES: PREDICTING INPATIENT MORTALITY USING ELECTRONIC MEDICAL RECORD DATA
    Bryant, Corey
    Johnson, Alistair
    Henson, Kathy
    Freeseman-Freeman, Laura
    Stark, Maureen
    Higgins, Thomas
    [J]. CRITICAL CARE MEDICINE, 2018, 46 (01) : 8 - 8
  • [4] Epidemiology of Death in the PICU at Five US Teaching Hospitals
    Burns, Jeffrey P.
    Sellers, Deborah E.
    Meyer, Elaine C.
    Lewis-Newby, Mithya
    Truog, Robert D.
    [J]. CRITICAL CARE MEDICINE, 2014, 42 (09) : 2101 - 2108
  • [5] Temporal convolutional networks allow early prediction of events in critical care
    Catling, Finneas J. R.
    Wolff, Anthony H.
    [J]. JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2020, 27 (03) : 355 - 365
  • [6] Recurrent Neural Networks for Multivariate Time Series with Missing Values
    Che, Zhengping
    Purushotham, Sanjay
    Cho, Kyunghyun
    Sontag, David
    Liu, Yan
    [J]. SCIENTIFIC REPORTS, 2018, 8
  • [7] Machine Learning and Prediction in Medicine - Beyond the Peak of Inflated Expectations
    Chen, Jonathan H.
    Asch, Steven M.
    [J]. NEW ENGLAND JOURNAL OF MEDICINE, 2017, 376 (26) : 2507 - 2509
  • [8] Chollet F, 2019, **DATA OBJECT**
  • [9] Chollet F., 2018, DEEP LEARNING WITH R
  • [10] Dynamic multi-outcome prediction after injury: Applying adaptive machine learning for precision medicine in trauma
    Christie, S. Ariane
    Conroy, Amanda S.
    Callcut, Rachael A.
    Hubbard, Alan E.
    Cohen, Mitchell J.
    [J]. PLOS ONE, 2019, 14 (04):