Pediatric septic shock estimation using deep learning and electronic medical records
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Background: Diagnosing pediatric septic shock is difficult due to the complex and often impractical traditional criteria, such as systemic inflammatory response syndrome (SIRS), which result in delays and higher risks. This study aims to develop a deep learning-based model using SIRS data for early diagnosis in pediatric septic shock cases.Methods: The study analyzed data from pediatric patients (<18 years old) admitted to a tertiary hospital from January 2010 to July 2023. Vital signs, lab tests, and clinical information were collected. Septic shock cases were identified using SIRS criteria and inotrope use. A deep learning model was trained and evaluated using the area under the receiver operating characteristics curve (AUROC) and area under the precision-recall curve (AUPRC). Variable contributions were analyzed using the Shapley additive explanation value.Results: The analysis, involving 9,616,115 measurements, identified 34,696 septic shock cases (0.4%). Oxygen supply was crucial for 41.5% of the control group and 20.8% of the septic shock group. The final model showed strong performance, with an AUROC of 0.927 and AUPRC of 0.879. Key influencers were age, oxygen supply, sex, and partial pressure of carbon dioxide, while body temperature had minimal impact on estimation.Conclusions: The proposed deep learning model simplifies early septic shock diagnosis in pediatric patients, reducing the diagnostic workload. Its high accuracy allows timely treatment, but external validation through prospective studies is needed.
Abstract
Background: Diagnosing pediatric septic shock is difficult due to the complex and often impractical traditional criteria, such as systemic inflammatory response syndrome (SIRS), which result in delays and higher risks. This study aims to develop a deep learning-based model using SIRS data for early diagnosis in pediatric septic shock cases.Methods: The study analyzed data from pediatric patients (<18 years old) admitted to a tertiary hospital from January 2010 to July 2023. Vital signs, lab tests, and clinical information were collected. Septic shock cases were identified using SIRS criteria and inotrope use. A deep learning model was trained and evaluated using the area under the receiver operating characteristics curve (AUROC) and area under the precision-recall curve (AUPRC). Variable contributions were analyzed using the Shapley additive explanation value.Results: The analysis, involving 9,616,115 measurements, identified 34,696 septic shock cases (0.4%). Oxygen supply was crucial for 41.5% of the control group and 20.8% of the septic shock group. The final model showed strong performance, with an AUROC of 0.927 and AUPRC of 0.879. Key influencers were age, oxygen supply, sex, and partial pressure of carbon dioxide, while body temperature had minimal impact on estimation.Conclusions: The proposed deep learning model simplifies early septic shock diagnosis in pediatric patients, reducing the diagnostic workload. Its high accuracy allows timely treatment, but external validation through prospective studies is needed.
참고문헌 (29)
- Bauer M, "Mortality in sepsis and septic shock in Europe, North America and Australia between 2009 and 2019 : results from a systematic review and meta-analysis", Crit Care, 24, pp.239~ (2020)
- Evans IV, "Association between the New York sepsis care mandate and in-hospital mortality for pediatric sepsis", JAMA, 320, pp.358~367 (2018)
- Balamuth F, "Pediatric severe sepsis in U.S. children’s hospitals", Pediatr Crit Care Med, 15, pp.798~805 (2014)
- Singer M, "The Third International Consensus Definitions for Sepsis and Septic Shock(Sepsis-3)", JAMA, 315, pp.801~810 (2016)
- Rhee C, "Incidence and trends of sepsis in US hospitals using clinical vs claims data, 2009-2014", JAMA, 318, pp.1241~1249 (2017)
- Kim HI, "Sepsis : early recognition and optimized treatment", Tuberc Respir Dis(Seoul), 82, pp.6~14 (2019)
- Goldstein B, "International pediatric sepsis consensus conference : definitions for sepsis and organ dysfunction in pediatrics", Pediatr Crit Care Med, 6, pp.2~8 (2005)
- Levy MM, "2001 SCCM", ESICM, ATS, pp.SIS International Sepsis Definitions Conference, Crit Care Med[DOI]
- Weiss SL, "Surviving Sepsis Campaign International Guidelines for the management of septic shock and sepsis-associated organ dysfunction in children", Pediatr Crit Care Med, 21, pp.e52~e106 (2020)
- Schlapbach LJ, "Prognostic accuracy of age-adapted SOFA, SIRS, PELOD-2, and qSOFA for in-hospital mortality among children with suspected infection admitted to the intensive care unit", Intensive Care Med, 44, pp.179~188 (2018)
- Matics TJ, "Adaptation and validation of a pediatric sequential organ failure assessment score and evaluation of the sepsis-3 definitions in critically ill children", JAMA Pediatr, 171, pp.e172352~ (2017)
- Schlapbach LJ, "Defining pediatric sepsis", JAMA Pediatr, 172, pp.312~314 (2018)
- Bone RC, "Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis. The ACCP", SCCM Consensus Conference Committee. American College of Chest Physicians, Chest, pp.1992, 101[DOI]
- Shankar-Hari M, "Developing a new definition and assessing new clinical criteria for septic shock : for the Third International Consensus Definitions for Sepsis and Septic Shock(Sepsis-3)", JAMA, 315, pp.775~787 (2016)
- Storozuk SA, "A survey of sepsis knowledge among Canadian emergency department registered nurses", Australas Emerg Care, 22, pp.119~125 (2019)
- Rahman NI, "Knowledge and attitude towards identification of systemic inflammatory response syndrome(SIRS)and sepsis among emergency personnel in tertiary teaching hospital", Australas Emerg Care, 22, pp.13~21 (2019)
- Hwang S, "Machine learning-based prediction of critical illness in children visiting the emergency department", PLoS One, 17, pp.e0264184~ (2022)
- Rigby RA, "Automatic smoothing parameter selection in GAMLSS with an application to centile estimation", Stat Methods Med Res, 23, pp.318~332 (2014)
- Cole TJ, "SITAR : a useful instrument for growth curve analysis", Int J Epidemiol, 39, pp.1558~1566 (2010)
- Rigby RA, "Smooth centile curves for skew and kurtotic data modelled using the Box-Cox power exponential distribution", Stat Med, 23, pp.3053~3076 (2004)
- Pedregosa F, "Scikit-learn : machine learning in Python", J Mach Learn Res, 12, pp.2825~2830 (2011)
- Paszke A, "Pytorch: an imperative style, high-performance deep learning library", Adv Neural Inf Process Syst, 32 (2019)
- Rodríguez-Pérez R, "Interpretation of machine learning models using shapley values : application to compound potency and multi-target activity predictions", J Comput Aided Mol Des, 34, pp.1013~1026 (2020)
- Liu R, "Prediction of impending septic shock in children with sepsis", Crit Care Explor, 3, pp.e0442~ (2021)
- Leteurtre S, "PELOD-2 : an update of the PEdiatric logistic organ dysfunction score", Crit Care Med, 41, pp.1761~1773 (2013)
- Le S, "Pediatric severe sepsis prediction using machine learning", Front Pediatr, 7, pp.413~ (2019)
- Scott HF, "Development and validation of a predictive model of the risk of pediatric septic shock using data known at the time of hospital arrival", J Pediatr, 217, pp.145~151 (2020)
- Giannini HM, "A machine learning algorithm to predict severe sepsis and septic shock : development, implementation, and impact on clinical practice", Crit Care Med, 47, pp.1485~1492 (2019)
- Fleuren LM, "Machine learning for the prediction of sepsis : a systematic review and meta-analysis of diagnostic test accuracy", Intensive Care Med, 46, pp.383~400 (2020)