Your browser doesn't support javascript.
loading
Development and Temporal Validation of a Machine Learning Model to Predict Clinical Deterioration.
Foote, Henry P; Shaikh, Zohaib; Witt, Daniel; Shen, Tong; Ratliff, William; Shi, Harvey; Gao, Michael; Nichols, Marshall; Sendak, Mark; Balu, Suresh; Osborne, Karen; Kumar, Karan R; Jackson, Kimberly; McCrary, Andrew W; Li, Jennifer S.
Afiliação
  • Foote HP; Divisions of Pediatric Cardiology.
  • Shaikh Z; Duke Institute for Health Innovation.
  • Witt D; Department of Medicine, Weill Cornell Medical Center, New York, New York.
  • Shen T; Duke Institute for Health Innovation.
  • Ratliff W; Mayo Clinic Alix School of Medicine, Rochester, Minnesota.
  • Shi H; Department of Biomedical Engineering.
  • Gao M; Duke Institute for Health Innovation.
  • Nichols M; Duke Institute for Health Innovation.
  • Sendak M; Duke Institute for Health Innovation.
  • Balu S; Duke Institute for Health Innovation.
  • Osborne K; Duke Institute for Health Innovation.
  • Kumar KR; Duke Institute for Health Innovation.
  • Jackson K; Duke University Health System, Duke University, Durham, North Carolina.
  • McCrary AW; Pediatric Critical Care Medicine.
  • Li JS; Pediatric Critical Care Medicine.
Hosp Pediatr ; 14(1): 11-20, 2024 Jan 01.
Article em En | MEDLINE | ID: mdl-38053467
OBJECTIVES: Early warning scores detecting clinical deterioration in pediatric inpatients have wide-ranging performance and use a limited number of clinical features. This study developed a machine learning model leveraging multiple static and dynamic clinical features from the electronic health record to predict the composite outcome of unplanned transfer to the ICU within 24 hours and inpatient mortality within 48 hours in hospitalized children. METHODS: Using a retrospective development cohort of 17 630 encounters across 10 388 patients, 2 machine learning models (light gradient boosting machine [LGBM] and random forest) were trained on 542 features and compared with our institutional Pediatric Early Warning Score (I-PEWS). RESULTS: The LGBM model significantly outperformed I-PEWS based on receiver operating characteristic curve (AUROC) for the composite outcome of ICU transfer or mortality for both internal validation and temporal validation cohorts (AUROC 0.785 95% confidence interval [0.780-0.791] vs 0.708 [0.701-0.715] for temporal validation) as well as lead-time before deterioration events (median 11 hours vs 3 hours; P = .004). However, LGBM performance as evaluated by precision recall curve was lesser in the temporal validation cohort with associated decreased positive predictive value (6% vs 29%) and increased number needed to evaluate (17 vs 3) compared with I-PEWS. CONCLUSIONS: Our electronic health record based machine learning model demonstrated improved AUROC and lead-time in predicting clinical deterioration in pediatric inpatients 24 to 48 hours in advance compared with I-PEWS. Further work is needed to optimize model positive predictive value to allow for integration into clinical practice.
Assuntos

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Deterioração Clínica / Escore de Alerta Precoce Limite: Child / Humans Idioma: En Revista: Hosp Pediatr Ano de publicação: 2024 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Deterioração Clínica / Escore de Alerta Precoce Limite: Child / Humans Idioma: En Revista: Hosp Pediatr Ano de publicação: 2024 Tipo de documento: Article