Meredith C Winter, Alice X Zhou, Eugene Laksana, Melissa D Aczon, David R Ledbetter, Michael Avesar, Kimberly Burkiewicz, Harsha K Chandnani, Nina Fainberg, Stephanie Hsu, Michael C McCrory, Katie R Morrow, Anna Noguchi, Caitlin E O'Brien, Apoorva Ojha, Charlene Pringle, Patrick A Ross, Jui Shah, Sareen Shah, Leonid Shpaner, Linda B Siegel, Sandeep Tripathi, Randall C Wetzel
{"title":"儿童终末拔管后1小时死亡：多中心队列中预测停止维持生命治疗后心脏性死亡的机器学习模型验证，2009-2021","authors":"Meredith C Winter, Alice X Zhou, Eugene Laksana, Melissa D Aczon, David R Ledbetter, Michael Avesar, Kimberly Burkiewicz, Harsha K Chandnani, Nina Fainberg, Stephanie Hsu, Michael C McCrory, Katie R Morrow, Anna Noguchi, Caitlin E O'Brien, Apoorva Ojha, Charlene Pringle, Patrick A Ross, Jui Shah, Sareen Shah, Leonid Shpaner, Linda B Siegel, Sandeep Tripathi, Randall C Wetzel","doi":"10.1097/PCC.0000000000003772","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>In the PICU, predicting death within 1 hour after terminal extubation (TE) is valuable in augmenting family counseling and in identifying suitable candidates for organ donation after circulatory determination of death (DCDD). The objective of this study was to train and validate a machine learning model to predict death within 1 hour after TE.</p><p><strong>Design: </strong>The Death One Hour After Terminal Extubation (DONATE) database was generated using multicenter retrospective data from 2009 to 2021. Data covering demographics, clinical features, vital signs, laboratory values, ventilator settings, medications, and procedures were collected. Machine learning models were trained to predict whether a pediatric patient would die within 1 hour after TE and evaluated on a holdout set.</p><p><strong>Setting: </strong>Ten U.S. PICUs.</p><p><strong>Patients: </strong>Children and adolescents, 0-21 years old, who died after TE ( n = 957).</p><p><strong>Interventions: </strong>None.</p><p><strong>Measurements and main results: </strong>The final model was a parsimonious extra-trees model with 21 input features. It was trained on the 2009-2018 data from eight sites ( n = 634) and evaluated on a holdout set comprised of the 2019-2021 data of all ten sites ( n = 323), representing temporal and external validation. The area under the receiver operating characteristic curve and 95% CI was 0.84 (95% CI, 0.81-0.87). At a sensitivity of 90%, the positive predictive value (PPV) was 88%, the negative predictive value (NPV) was 70%, and the number needed to alert (NNA) was 1.14. Among potential organ donors, at the same sensitivity level, the PPV was 86%, the NPV was 74%, and the NNA was 1.17.</p><p><strong>Conclusions: </strong>Our model, trained and validated on multisite data, predicted whether a child will die within 1 hour of TE with high discrimination and a low false alarm rate. This finding has important applications to end-of-life counseling and institutional resource utilization when families wish to attempt DCDD.</p>","PeriodicalId":19760,"journal":{"name":"Pediatric Critical Care Medicine","volume":" ","pages":"e997-e1008"},"PeriodicalIF":4.5000,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Death One Hour After Terminal Extubation in Children: Validation of a Machine Learning Model to Predict Cardiac Death After Withdrawal of Life-Sustaining Treatment in a Multicenter Cohort, 2009-2021.\",\"authors\":\"Meredith C Winter, Alice X Zhou, Eugene Laksana, Melissa D Aczon, David R Ledbetter, Michael Avesar, Kimberly Burkiewicz, Harsha K Chandnani, Nina Fainberg, Stephanie Hsu, Michael C McCrory, Katie R Morrow, Anna Noguchi, Caitlin E O'Brien, Apoorva Ojha, Charlene Pringle, Patrick A Ross, Jui Shah, Sareen Shah, Leonid Shpaner, Linda B Siegel, Sandeep Tripathi, Randall C Wetzel\",\"doi\":\"10.1097/PCC.0000000000003772\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objectives: </strong>In the PICU, predicting death within 1 hour after terminal extubation (TE) is valuable in augmenting family counseling and in identifying suitable candidates for organ donation after circulatory determination of death (DCDD). The objective of this study was to train and validate a machine learning model to predict death within 1 hour after TE.</p><p><strong>Design: </strong>The Death One Hour After Terminal Extubation (DONATE) database was generated using multicenter retrospective data from 2009 to 2021. Data covering demographics, clinical features, vital signs, laboratory values, ventilator settings, medications, and procedures were collected. Machine learning models were trained to predict whether a pediatric patient would die within 1 hour after TE and evaluated on a holdout set.</p><p><strong>Setting: </strong>Ten U.S. PICUs.</p><p><strong>Patients: </strong>Children and adolescents, 0-21 years old, who died after TE ( n = 957).</p><p><strong>Interventions: </strong>None.</p><p><strong>Measurements and main results: </strong>The final model was a parsimonious extra-trees model with 21 input features. It was trained on the 2009-2018 data from eight sites ( n = 634) and evaluated on a holdout set comprised of the 2019-2021 data of all ten sites ( n = 323), representing temporal and external validation. The area under the receiver operating characteristic curve and 95% CI was 0.84 (95% CI, 0.81-0.87). At a sensitivity of 90%, the positive predictive value (PPV) was 88%, the negative predictive value (NPV) was 70%, and the number needed to alert (NNA) was 1.14. Among potential organ donors, at the same sensitivity level, the PPV was 86%, the NPV was 74%, and the NNA was 1.17.</p><p><strong>Conclusions: </strong>Our model, trained and validated on multisite data, predicted whether a child will die within 1 hour of TE with high discrimination and a low false alarm rate. This finding has important applications to end-of-life counseling and institutional resource utilization when families wish to attempt DCDD.</p>\",\"PeriodicalId\":19760,\"journal\":{\"name\":\"Pediatric Critical Care Medicine\",\"volume\":\" \",\"pages\":\"e997-e1008\"},\"PeriodicalIF\":4.5000,\"publicationDate\":\"2025-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Pediatric Critical Care Medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1097/PCC.0000000000003772\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/6/25 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"CRITICAL CARE MEDICINE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pediatric Critical Care Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/PCC.0000000000003772","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/6/25 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"CRITICAL CARE MEDICINE","Score":null,"Total":0}
Death One Hour After Terminal Extubation in Children: Validation of a Machine Learning Model to Predict Cardiac Death After Withdrawal of Life-Sustaining Treatment in a Multicenter Cohort, 2009-2021.
Objectives: In the PICU, predicting death within 1 hour after terminal extubation (TE) is valuable in augmenting family counseling and in identifying suitable candidates for organ donation after circulatory determination of death (DCDD). The objective of this study was to train and validate a machine learning model to predict death within 1 hour after TE.
Design: The Death One Hour After Terminal Extubation (DONATE) database was generated using multicenter retrospective data from 2009 to 2021. Data covering demographics, clinical features, vital signs, laboratory values, ventilator settings, medications, and procedures were collected. Machine learning models were trained to predict whether a pediatric patient would die within 1 hour after TE and evaluated on a holdout set.
Setting: Ten U.S. PICUs.
Patients: Children and adolescents, 0-21 years old, who died after TE ( n = 957).
Interventions: None.
Measurements and main results: The final model was a parsimonious extra-trees model with 21 input features. It was trained on the 2009-2018 data from eight sites ( n = 634) and evaluated on a holdout set comprised of the 2019-2021 data of all ten sites ( n = 323), representing temporal and external validation. The area under the receiver operating characteristic curve and 95% CI was 0.84 (95% CI, 0.81-0.87). At a sensitivity of 90%, the positive predictive value (PPV) was 88%, the negative predictive value (NPV) was 70%, and the number needed to alert (NNA) was 1.14. Among potential organ donors, at the same sensitivity level, the PPV was 86%, the NPV was 74%, and the NNA was 1.17.
Conclusions: Our model, trained and validated on multisite data, predicted whether a child will die within 1 hour of TE with high discrimination and a low false alarm rate. This finding has important applications to end-of-life counseling and institutional resource utilization when families wish to attempt DCDD.
期刊介绍：
Pediatric Critical Care Medicine is written for the entire critical care team: pediatricians, neonatologists, respiratory therapists, nurses, and others who deal with pediatric patients who are critically ill or injured. International in scope, with editorial board members and contributors from around the world, the Journal includes a full range of scientific content, including clinical articles, scientific investigations, solicited reviews, and abstracts from pediatric critical care meetings. Additionally, the Journal includes abstracts of selected articles published in Chinese, French, Italian, Japanese, Portuguese, and Spanish translations - making news of advances in the field available to pediatric and neonatal intensive care practitioners worldwide.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
