Machine learning to predict cardiac death within 1 hour after terminal extubation
artificial; data science; intensive care units; machine learning; palliative care; pediatric; respiration; terminal care
Objectives: Accurate prediction of time to death after withdrawal of life-sustaining therapies may improve counseling for families and help identify candidates for organ donation after cardiac death. The study objectives were to: 1) train a long short-term memory model to predict cardiac death within 1 hour after terminal extubation, 2) calculate the positive predictive value of the model and the number needed to alert among potential organ donors, and 3) examine associations between time to cardiac death and the patient's characteristics and physiologic variables using Cox regression. Design(s): Retrospective cohort study. Setting(s): PICU and cardiothoracic ICU in a tertiary-care academic children's hospital. Patient(s): Patients 0-21 years old who died after terminal extubation from 2011 to 2018 (n = 237). Intervention(s): None. Measurements and Main Results: The median time to death for the cohort was 0.3 hours after terminal extubation (interquartile range, 0.16-1.6 hr); 70% of patients died within 1 hour. The long short-term memory model had an area under the receiver operating characteristic curve of 0.85 and a positive predictive value of 0.81 at a sensitivity of 94% when predicting death within 1 hour of terminal extubation. About 39% of patients who died within 1 hour met organ procurement and transplantation network criteria for liver and kidney donors. The long short-term memory identified 93% of potential organ donors with a number needed to alert of 1.08, meaning that 13 of 14 prepared operating rooms would have yielded a viable organ. A Cox proportional hazard model identified independent predictors of shorter time to death including low Glasgow Coma Score, high Pao<inf>2</inf>-to-Fio<inf>2</inf>ratio, low-pulse oximetry, and low serum bicarbonate. Conclusion(s): Our long short-term memory model accurately predicted whether a child will die within 1 hour of terminal extubation and may improve counseling for families. Our model can identify potential candidates for donation after cardiac death while minimizing unnecessarily prepared operating rooms. Copyright © 2021 Lippincott Williams and Wilkins. All rights reserved.
Winter MC; Day TE; Ledbetter DR; Aczon MD; Newth CJL; Wetzel RC; Ross PA
Pediatric Critical Care Medicine
2021
Article information provided for research and reference use only. PedPalASCNET does not hold any rights over the resource listed here. All rights are retained by the journal listed under publisher and/or the creator(s).
<a href="http://doi.org/10.1097/PCC.0000000000002612" target="_blank" rel="noreferrer noopener">10.1097/PCC.0000000000002612</a>
Feasibility and Perceived Benefits of a Framework for Physician-Parent Follow-Up Meetings After a Child's Death in the PICU
OBJECTIVE:: To evaluate the feasibility and perceived benefits of conducting physician-parent follow-up meetings after a child's death in the PICU according to a framework developed by the Collaborative Pediatric Critical Care Research Network. DESIGN:: Prospective observational study. SETTING:: Seven Collaborative Pediatric Critical Care Research Network-affiliated children's hospitals. SUBJECTS:: Critical care attending physicians, bereaved parents, and meeting guests (i.e., parent support persons, other health professionals). INTERVENTIONS:: Physician-parent follow-up meetings using the Collaborative Pediatric Critical Care Research Network framework. MEASUREMENTS AND MAIN RESULTS:: Forty-six critical care physicians were trained to conduct follow-up meetings using the framework. All meetings were video recorded. Videos were evaluated for the presence or absence of physician behaviors consistent with the framework. Present behaviors were evaluated for performance quality using a 5-point scale (1 = low, 5 = high). Participants completed meeting evaluation surveys. Parents of 194 deceased children were mailed an invitation to a follow-up meeting. Of these, one or both parents from 39 families (20%) agreed to participate, 80 (41%) refused, and 75 (39%) could not be contacted. Of 39 who initially agreed, three meetings were canceled due to conflicting schedules. Thirty-six meetings were conducted including 54 bereaved parents, 17 parent support persons, 23 critical care physicians, and 47 other health professionals. Physician adherence to the framework was high; 79% of behaviors consistent with the framework were rated as present with a quality score of 4.3 ± 0.2. Of 50 evaluation surveys completed by parents, 46 (92%) agreed or strongly agreed the meeting was helpful to them and 40 (89%) to others they brought with them. Of 36 evaluation surveys completed by critical care physicians (i.e., one per meeting), 33 (92%) agreed or strongly agreed the meeting was beneficial to parents and 31 (89%) to them. CONCLUSIONS:: Follow-up meetings using the Collaborative Pediatric Critical Care Research Network framework are feasible and viewed as beneficial by meeting participants. Future research should evaluate the effects of follow-up meetings on bereaved parents' health outcomes.
2013-10
Meert KL; Eggly S; Berg RA; Wessel DL; Newth CJL; Shanley TP; Harrison R; Dalton H; Clark AE; Dean JM; Doctor Allan; Nicholson CE; Eunice Kennedy Shriver National Institute of Child Health; Human Development Collaborative Pediatric Critical Care Research Network
Critical Care Medicine
2013
Article information provided for research and reference use only. PedPalASCNET does not hold any rights over the resource listed here. All rights are retained by the journal listed under publisher and/or the creator(s).
Journal Article
<a href="http://doi.org/10.1097/CCM.0b013e3182a26ff3" target="_blank" rel="noreferrer">10.1097/CCM.0b013e3182a26ff3</a>
End-of-life Practices Among Tertiary Care Picus In The United States: A Multicenter Study
Adolescent;Cause Of Death;Child;Child Preschool;Female;Hospital Mortality;Humans;Infant;Intensive Care Units Pediatric;Length Of Stay;Male;Practice Patterns Physicians';Prospective Studies;Terminal Care/methods;Terminal Care/statistics & Numerical Data;Tertiary Healthcare;Tissue And Organ Procurement/statistics & Numerical Data;United States
OBJECTIVE: To describe variability in end-of-life practices among tertiary care PICUs in the United States. DESIGN: Secondary analysis of data prospectively collected from a random sample of patients (n = 10,078) admitted to PICUs affiliated with the Collaborative Pediatric Critical Care Research Network between December 4, 2011, and April 7, 2013. SETTING: Seven clinical centers affiliated with the Collaborative Pediatric Critical Care Research Network. PATIENTS: Patients included in the primary study were less than 18 years old, admitted to a PICU, and not moribund on PICU admission. Patients included in the secondary analysis were those who died during their hospital stay. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Two hundred and seventy-five (2.7%; range across sites, 1.3-5.0%) patients died during their hospital stay; of these, 252 (92%; 76-100%) died in a PICU. Discussions with families about limitation or withdrawal of support occurred during the initial PICU stay for 173 patients (63%; 47-76%; p = 0.27) who died. Of these, palliative care was consulted for 67 (39%; 12-46%); pain service for 11 (6%; 10 of which were at a single site); and ethics committee for six (3%, from three sites). Mode of death was withdrawal of support for 141 (51%; 42-59%), failed cardiopulmonary resuscitation for 53 (19%; 12-28%), limitation of support for 46 (17%; 7-24%), and brain death for 35 (13%; 8-20%); mode of death did not differ across sites (p = 0.58). Organ donation was requested from 101 families (37%; 17-88%; p < 0.001). Of these, 20 donated (20%; 0-64%). Sixty-two deaths (23%; 10-53%; p < 0.001) were medical examiner cases. Of nonmedical examiner cases (n = 213), autopsy was requested for 79 (37%; 17-75%; p < 0.001). Of autopsies requested, 53 (67%; 50-100%) were performed. CONCLUSIONS: Most deaths in Collaborative Pediatric Critical Care Research Network-affiliated PICUs occur after life support has been limited or withdrawn. Wide practice variation exists in requests for organ donation and autopsy.
Meert KL; Keele L; Morrison W; Berg RA; Dalton H; Newth CJL; Harrison R; Wessel DL; Shanley T; Carcillo J; Clark A; Holubkov R; Jenkins T L; Doctor A; Dean JM; Pollack M
Pediatric Critical Care Medicine
2015
Article information provided for research and reference use only. PedPalASCNET does not hold any rights over the resource listed here. All rights are retained by the journal listed under publisher and/or the creator(s).
10.1097/PCC.0000000000000520