Humans; Child; Child, Preschool; Infant; Adolescent; Male; Female; Infant, Newborn; Machine Learning; Heart Rate/physiology; Body Temperature/physiology; Intensive Care Units, Pediatric; Signal Processing, Computer-Assisted; body temperature; heart rate; PICU; quantile regression; Gradient boosting; Heart-rate; Intensive care; Linear modeling; Lower body; Machine-learning; Pediatric intensive care unit; Temperature range; Biomedical Engineering; Temperature measurement; Pediatrics; Pain; Monitoring; Biomedical monitoring; Temperature distribution; Temperature sensors; Data mining; Predictive models
Abstract :
[en] [en] UNLABELLED: Vital signs are crucial clinical measures, with body temperature (BT) and heart rate (HR) being particularly significant. While their association has been studied in adults and children, research in Pediatric Intensive Care Unit (PICU) settings remains limited despite the critical conditions of these patients.
OBJECTIVE: This study examines the relationship between HR and BT in children aged 0 to 18 admitted to the PICU at CHU Sainte-Justine (CHUSJ) Hospital.
METHODS: Machine learning (ML) techniques, including Gradient Boosting Machines (GBM) with Quantile Regression (QR), were applied to capture the relationship between HR, BT, and age, optimizing model performance through hyperparameter tuning.
RESULTS: Analyzing data from 4006 children, we observed a consistent trend of decreasing HR with increasing age and rising HR with higher BT ranges. Linear models often underestimated HR at lower BT ranges and overestimated it at higher ranges, especially in younger age groups. The GBM model demonstrated improved accuracy and supported a user-friendly interface for HR predictions based on BT, age, and HR percentiles. Qualitative observations indicated that linear models underestimated HR at lower BT ranges and overestimated it at higher ones, particularly in younger children. These findings challenge the direct linear association assumed in prior studies.
CONCLUSION: This study provides new insights into the non-linear dynamics between HR, BT, and age in critically ill children, emphasizing further research to quantify and understand these relationships.
SIGNIFICANCE: By refining predictive models and re-evaluating traditional assumptions, this work provides valuable insights for improving clinical decision-making in PICU settings.
Disciplines :
Computer science
Author, co-author :
Lu, Emilie ; École de Technologie Supérieure, Electrical Engineering Department, Montréal, Canada ; Saint-Justine Mother and Child University Hospital Center, Montréal, Canada
LE, Thanh-Dung ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom ; University of Québec, Biomedical Information Processing Lab, École de Technologie Supérieure, Canada
Jouvet, Philippe ; University of Montreal, CHU Sainte-Justine Research Center, CHU Sainte-Justine Hospital, Canada
Noumeir, Rita ; University of Québec, Biomedical Information Processing Lab, École de Technologie Supérieure, Canada
External co-authors :
yes
Language :
English
Title :
Heart Rate and Body Temperature Relationship in Children Admitted to PICU: A Machine Learning Approach.
Natural Sciences and Engineering Research Council Fonds de la recherche en sante du Quebec
Funding text :
This work was supported in part by the Natural Sciences and Engineering Research Council (NSERC), in part by the Fonds de la recherche en sante du Quebec (FRQS), in part by the Institut de Valorisation des donn\u00E9es de l\u2019Universit\u00E9 de Montr\u00E9al (IVADO), and in part by the Fonds de la recherche en sante du Quebec (FRQS). Data and reproducible codes are available upon request from Prof. Philippe Jouvet, M.D., PhD.
T. M. Slusher et al., “Pediatric critical care in resource-limited settings—Overview and lessons learned,” Front. Pediatrics, vol. 6, 2018, Art. no. 49.
J. A. Heneghan et al., “Characteristics and outcomes of critical illness in children with feeding and respiratory technology dependence,” Pediatr. Crit. Care Med.: J. Soc. Crit. Care Med. World Federation Pediatr. Intensive Crit. Care Societies, vol. 20, no. 5, pp. 417–425, 2019.
“CDSS grouping in AI acute care for the child,” Accessed: Apr. 16, 2024. [Online]. Available: https://chusj-sip-ia.ca/home
I. J. Brekke et al., “The value of vital sign trends in predicting and monitoring clinical deterioration: A systematic review,” PLoS One, vol. 14, no. 1, 2019, Art. no. e0210875.
M. M. Jensen and M. Brabrand, “The relationship between body temperature, heart rate and respiratory rate in acute patients at admission to a medical care unit,” Scand. J. Trauma, Resuscitation Emerg. Med., vol. 23, no. 1, 2015, Art. no. A12.
P. Davies and I. Maconochie, “The relationship between body temperature, heart rate and respiratory rate in children,” Emerg. Med. J.: EMJ, vol. 26, no. 9, pp. 641–643, 2009.
S. Liu, J. Yao, and M. Motani, “Early prediction of vital signs using generative boosting via LSTM networks,” in Proc. IEEE Int. Conf. Bioinf. Biomed., 2019, pp. 437–444.
B. W. Nelson et al., “Guidelines for wrist-worn consumer wearable assessment of heart rate in biobehavioral research,” NPJ Digit. Med., vol. 3, no. 1, 2020, Art. no. 90.
S. Fleming et al., “Normal ranges of heart rate and respiratory rate in children from birth to 18 years of age: A systematic review of observational studies,” Lancet, vol. 377, no. 9770, pp. 1011–1018, 2011.
C. Daymont, C. P. Bonafide, and P. W. Brady, “Heart rates in hospitalized children by age and body temperature,” Pediatrics, vol. 135, no. 5, pp. e1173–e1181, 2015.
S. Sidhu and J. E. Marine, “Evaluating and managing bradycardia,” Trends Cardiovasc. Med., vol. 30, no. 5, pp. 265–272, 2020.
C. Heal et al., “The association between temperature, heart rate, and respiratory rate in children aged under 16 years attending urgent and emergency care settings,” Eur. J. Emerg. Med., vol. 29, no. 6, pp. 413–416, 2022.
H. K. Walker, W. D. Hall, and J. W. Hurst, “Clinical methods: The history, physical, and laboratory examinations,” Butterworths, 1990.
M. Thompson et al., “Deriving temperature and age appropriate heart rate centiles for children with acute infections,” Arch. Dis. Childhood, vol. 94, no. 5, pp. 361–365, 2009.
G. W. Kirschen et al., “Relationship between body temperature and heart rate in adults and children: A local and national study,” Amer. J. Emerg. Med., vol. 38, no. 5, pp. 929–933, 2020.
M. E. Broman et al., “The relationship between heart rate and body temperature in critically ill patients,” Crit. Care Med., vol. 49, no. 3, pp. e327–e331, 2021.
D. Brossier et al., “Creating a high-frequency electronic database in the PICU: The perpetual patient,” Pediatr. Crit. care Med., vol. 19, no. 4, pp. e189–e198, 2018.
D. Kinaneva et al., “Machine learning algorithms for regression analysis and predictions of numerical data,” in Proc. 3rd Int. Congr. Hum.-Comput. Interact., Optim. Robot. Appl., 2021, pp. 1–6.
L. D. Cloedt et al., “The impact of implementing a “pain, agitation, and delirium bundle” in a pediatric intensive care unit: Improved delirium diagnosis,” J. Pediatr. Intensive Care, vol. 11, no. 03, pp. 233–239, 2021.
A. Amigoni et al., “Recommendations for analgesia and sedation in critically ill children admitted to intensive care unit,” J. Anesthesia, Analg. Crit. Care, vol. 2, no. 1, 2022, Art. no. 9.
P. Dolibog et al., “Comparative analysis of human body temperatures measured with noncontact and contact thermometers,” Healthcare, vol. 10, no. 2, 2022, Art. no. 331.
M. Meyer, M. Rambod, and M. LeWinter, “Pharmacological heart rate lowering in patients with a preserved ejection fraction—Review of a failing concept,” Heart Failure Rev., vol. 23, pp. 499–506, 2018.
G. S. King et al., “Antiarrhythmic medications,” StatPearls Publishing, 2024.
“Pediatric medical devices,” Accessed: Apr. 16, 2024. [Online]. Available: https://www.fda.gov/medical-devices/products-and-medicalprocedures/pediatric-medical-devices
V. K. Patidar et al., “Quantile regression comprehensive in machine learning: A review,” in Proc. IEEE Int. Students’ Conf. Elect., Electron. Comput. Sci., 2023, pp. 1–6.
G. D. Hutcheson and L. A. M. Moutinho, “The SAGE dictionary of quantitative management research,” in SAGE Dictionary Quantitative Manage. Res., pp. 1–344, 2011.
S. Fafalios, P. Charonyktakis, and I. Tsamardinos, “Gradient boosting trees,” Gnosis Data Anal. PC, vol. 1, pp. 1–3, 2020.
N. Aziz et al., “A study on gradient boosting algorithms for development of AI monitoring and prediction systems,” in Proc. Int. Conf. Comput. Intell., 2020, pp. 11–16.
B. Boehmke and B. M. Greenwell, Hands-on Machine Learning With R. Boca Raton, FL, USA: CRC Press, 2019.
A. Cutler, D. R. Cutler, and J. R. Stevens, “Random forests,” in Ensemble Machine Learning: Methods and Applications. Berlin, Germany: Springer, 2012, pp. 157–175.
S. Sivamohan, S. Sridhar, and S. Krishnaveni, “An effective recurrent neural network (RNN) based intrusion detection via bi-directional long short-term memory,” in Proc. Int. Conf. Intell. Technol., 2021, pp. 1–5.
B. N. Saha and A. Senapati, “Long short term memory (LSTM) based deep learning for sentiment analysis of English and Spanish data,” in Proc. Int. Conf. Comput. Perform. Eval., 2020, pp. 442–446.
D. Molina Estren, A. K. De la Hoz Manotas, and F. M. Palechor, “Classification and features selection method for obesity level prediction,” J. Theor. Appl. Inf. Technol., vol. 99, no. 11, pp. 2525–2536, 2021.
G. Varoquaux and O. Colliot, “Evaluating machine learning models and their diagnostic value,” in Machine Learning For Brain Disorders. Berlin, Germany: Springer, 2023, pp. 601–630.
D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., vol. 7, 2021, Art. no. e623.
D. M. Keer, H. Lohiya, and S. Chouhan, “Goodness of fit for linear regression using R-squared and adjusted rsquared,” Int. J. Res. Pub. Rev., vol. 4, no. 3, pp. 2431–2439, 2023.
K. Tyagi et al., “Regression analysis,” in Proc. Artif. Intell. Mach. Learn. EDGE Comput., 2022, pp. 53–63.
C. Rane et al., “Optimal input gain: All you need to supercharge a feed-forward neural network,” 2023, arXiv:2303.17732.
I. Steinwart and A. Christmann, “Estimating conditional quantiles with the help of the pinball loss,” Bernoulli, vol. 17, pp. 211–225, 2011.
J. A. Machado and J. Silva, “Quantile regression and heteroskedasticity,” Dept. of Econ., Univ. of Essex, Colchester, England, U.K., 2013. [Online]. Available: https://jmcss.som.surrey.ac.uk/JM_JSS.pdf
T. Narayan et al., “Expected pinball loss for quantile regression and inverse CDF estimation,” Trans. Mach. Learn. Res., vol. 2024, Accessed: Feb. 18, 2024. [Online]. Available: https://openreview.net/forum?id= Eg8Rnb0Hdd
A. Alutaibi and S. Ganti, “Network traffic prediction using quantile regression with linear, tree, and deep learning models,” in Proc. IEEE 45th Conf. Local Comput. Netw., 2020, pp. 421–424.
F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.
O. M. Momo and Y. Morikawa, “Measuring the association between temperature and heart rate in children: Be aware of the uncertainties,” Eur. J. Emerg. Med., vol. 30, no. 2, pp. 147–148, 2023.
C. Heal et al., “Response to ‘measuring the association between temperature and heart rate in children: Be aware of the uncertainties’,” Eur. J. Emerg. Med., vol. 30, no. 2, pp. 148–148, 2023.
J. H. Friedman, “Greedy function approximation: A gradient boosting machine,” Ann. Statist., vol. 29, pp. 1189–1232, 2001.
N. Yakob et al., “Data representation structure to support clinical decision-making in the pediatric intensive care unit: Interview study and preliminary decision support interface design,” JMIR Formative Res., vol. 8, 2024, Art. no. e49497.
