Machine Learning-Based Prediction of Hospital Admission Among Children in an Emergency Care Center.
Journal
Pediatric emergency care
ISSN: 1535-1815
Titre abrégé: Pediatr Emerg Care
Pays: United States
ID NLM: 8507560
Informations de publication
Date de publication:
01 Feb 2023
01 Feb 2023
Historique:
entrez:
31
1
2023
pubmed:
1
2
2023
medline:
3
2
2023
Statut:
ppublish
Résumé
Machine learning-based prediction of hospital admissions may have the potential to optimize patient disposition and improve clinical outcomes by minimizing both undertriage and overtriage in crowded emergency care. We developed and validated the predictive abilities of machine learning-based predictions of hospital admissions in a pediatric emergency care center. A prognostic study was performed using retrospectively collected data of children younger than 16 years who visited a single pediatric emergency care center in Osaka, Japan, between August 1, 2016, and October 15, 2019. Generally, the center treated walk-in children and did not treat trauma injuries. The main outcome was hospital admission as determined by the physician. The 83 potential predictors available at presentation were selected from the following categories: demographic characteristics, triage level, physiological parameters, and symptoms. To identify predictive abilities for hospital admission, maximize the area under the precision-recall curve, and address imbalanced outcome classes, we developed the following models for the preperiod training cohort (67% of the samples) and also used them in the 1-year postperiod validation cohort (33% of the samples): (1) logistic regression, (2) support vector machine, (3) random forest, and (4) extreme gradient boosting. Among 88,283 children who were enrolled, the median age was 3.9 years, with 47,931 (54.3%) boys and 1985 (2.2%) requiring hospital admission. Among the models, extreme gradient boosting achieved the highest predictive abilities (eg, area under the precision-recall curve, 0.26; 95% confidence interval, 0.25-0.27; area under the receiver operating characteristic curve, 0.86; 95% confidence interval, 0.84-0.88; sensitivity, 0.77; and specificity, 0.82). With an optimal threshold, the positive and negative likelihood ratios were 4.22, and 0.28, respectively. Machine learning-based prediction of hospital admissions may support physicians' decision-making for hospital admissions. However, further improvements are required before implementing these models in real clinical settings.
Identifiants
pubmed: 36719388
doi: 10.1097/PEC.0000000000002648
pii: 00006565-202302000-00003
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
80-86Informations de copyright
Copyright © 2022 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
Disclosure: The authors declare no conflict of interest.
Références
Pines JM, Hilton JA, Weber EJ, et al. International perspectives on emergency department crowding. Acad Emerg Med . 2011;18:1358–1370.
Hostetler MA, Mace S, Brown K, et al. Emergency department overcrowding and children. Pediatr Emerg Care . 2007;23:507–515.
Doan Q, Genuis ED, Yu A. Trends in use in a Canadian pediatric emergency department. CJEM . 2014;16:405–410.
Sills MR, Fairclough D, Ranade D, et al. Emergency department crowding is associated with decreased quality of care for children. Pediatr Emerg Care . 2011;27:837–845.
Kennebeck SS, Timm NL, Kurowski EM, et al. The association of emergency department crowding and time to antibiotics in febrile neonates. Acad Emerg Med . 2011;18:1380–1385.
Timm NL, Ho ML, Luria JW. Pediatric emergency department overcrowding and impact on patient flow outcomes. Acad Emerg Med . 2008;15:832–837.
Doan Q, Wong H, Meckler G, et al. The impact of pediatric emergency department crowding on patient and health care system outcomes: a multicentre cohort study. CMAJ . 2019;191:E627–E635.
Bernstein SL, Aronsky D, Duseja R, et al. The effect of emergency department crowding on clinically oriented outcomes. Acad Emerg Med . 2009;16:1–10.
Aeimchanbanjong K, Pandee U. Validation of different pediatric triage systems in the emergency department. World J Emerg Med . 2017;8:223–227.
Seiger N, Maconochie I, Oostenbrink R, et al. Validity of different pediatric early warning scores in the emergency department. Pediatrics . 2013;132:e841–e850.
Gouin S, Gravel J, Amre DK, et al. Evaluation of the paediatric Canadian triage and acuity scale in a pediatric ED. Am J Emerg Med . 2005;23:243–247.
van Veen M, Moll HA. Reliability and validity of triage systems in paediatric emergency care. Scand J Trauma Resusc Emerg Med . 2009;17:38.
Fernandes M, Vieira SM, Leite F, et al. Clinical decision support systems for triage in the emergency department using intelligent systems: a review. Artif Intell Med . 2020;102:101762.
Kirubarajan A, Taher A, Khan S, et al. Artificial intelligence in emergency medicine: a scoping review. J Am Coll Emerg Physicians Open . 2020;1:1691–1702.
Shafaf N, Malek H. Applications of machine learning approaches in emergency medicine; a review article. Arch Acad Emerg Med . 2019;7:34.
Roquette BP, Nagano H, Marujo EC, et al. Prediction of admission in pediatric emergency department with deep neural networks and triage textual data. Neural Netw . 2020;126:170–177.
Kopitar L, Kocbek P, Cilar L, et al. Early detection of type 2 diabetes mellitus using machine learning–based prediction models. Sci Rep . 2020;10:11981.
Jain S, Elon LK, Johnson BA, et al. Physician practice variation in the pediatric emergency department and its impact on resource use and quality of care. Pediatr Emerg Care . 2010;26:902–908.
Gaucher N, Bailey B, Gravel J. Impact of physicians' characteristics on the admission risk among children visiting a pediatric emergency department. Pediatr Emerg Care . 2012;28:120–124.
Goto T, Camargo CA Jr., Faridi MK, et al. Machine learning–based prediction of clinical outcomes for children during emergency department triage. JAMA Netw Open . 2019;2:e186937.
Zhang X, Kim J, Patzer RE, et al. Prediction of emergency department hospital admission based on natural language processing and neural networks. Methods Inf Med . 2017;56:377–389.
Kwon JM, Jeon KH, Lee M, et al. Deep learning algorithm to predict need for critical care in pediatric emergency departments. Pediatr Emerg Care . 2021;37:e988–e994.
Cheung DS, Grubenhoff JA. Machine learning in clinical medicine still finding its way. JAMA Netw Open . 2019;2:e186926.
Fu GH, Yi LZ, Pan J. Tuning model parameters in class-imbalanced learning with precision-recall curve. Biom J . 2019;61:652–664.
Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One . 2015;10:e0118432.
Bullard MJ, Musgrave E, Warren D, et al. Revisions to the Canadian emergency department triage and acuity scale (CTAS) guidelines 2016. CJEM . 2017;19:S18–S27.
Hamamoto J, Yamase H, Yamase Y. Impacts of the introduction of a triage system in Japan: a time series study. Int Emerg Nurs . 2014;22:153–158.
O'Leary F, Hayen A, Lockie F, et al. Defining normal ranges and centiles for heart and respiratory rates in infants and children: a cross-sectional study of patients attending an Australian tertiary hospital paediatric emergency department. Arch Dis Child . 2015;100:733–737.
Sarganas G, Schaffrath Rosario A, Berger S, et al. An unambiguous definition of pediatric hypotension is still lacking: gaps between two percentile-based definitions and pediatric advanced life support/advanced trauma life support guidelines. J Trauma Acute Care Surg . 2019;86:448–453.
Miles J, Turner J, Jacques R, et al. Using machine-learning risk prediction models to triage the acuity of undifferentiated patients entering the emergency care system: a systematic review. Diagn Progn Res . 2020;4:16.
Huang S, Cai N, Pacheco PP, et al. Applications of support vector machine (SVM) learning in cancer genomics. Cancer Genomics Proteomics . 2018;15:41–51.
Hanley JA, McNeil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology . 1982;143:29–36.
Youden WJ. Index for rating diagnostic tests. Cancer . 1950;3:32–35.
Zamanipoor Najafabadi AH, Ramspek CL, Dekker FW, et al. TRIPOD statement: a preliminary pre-post analysis of reporting and methods of prediction models. BMJ Open . 2020;10:e041537.
Anand A, Pugalenthi G, Fogel GB, et al. An approach for classification of highly imbalanced data using weighting and undersampling. Amino Acids . 2010;39:1385–1391.
Heckerling PS, Gerber BS, Tape TG, et al. Entering the black box of neural networks. Methods Inf Med . 2003;42:287–296.
Nicholson E, McDonnell T, De Brún A, et al. Factors that influence family and parental preferences and decision making for unscheduled paediatric healthcare—systematic review. BMC Health Serv Res . 2020;20:663.
Calado CS, Pereira AG, Santos VN, et al. What brings newborns to the emergency department?: A 1-year study. Pediatr Emerg Care . 2009;25:244–248.
Lucini FR, Fogliatto FS, da Silveira GJC, et al. Text mining approach to predict hospital admissions using early medical records from the emergency department. Int J Med Inform . 2017;100:1–8.
Tahayori B, Chini-Foroush N, Akhlaghi H. Advanced natural language processing technique to predict patient disposition based on emergency triage notes [published online October 11, 2020]. Emerg Med Australas . 2020. doi:10.1111/1742-6723.13656.
doi: 10.1111/1742-6723.13656
Sterling NW, Patzer RE, Di M, et al. Prediction of emergency department patient disposition based on natural language processing of triage notes. Int J Med Inform . 2019;129:184–188.
Chen CH, Hsieh JG, Cheng SL, et al. Emergency department disposition prediction using a deep neural network with integrated clinical narratives and structured data. Int J Med Inform . 2020;139:104146.