Predicting surgical intervention in pediatric intussusception using machine learning model

##plugins.themes.academic_pro.article.sidebar##

Published Jun 1, 2025
https://doi.org/10.62438/tunismed.v103i6.5542
Download
pdf
Vol. 103 No. 6 (2025): Tunis Med June 2025

##plugins.themes.academic_pro.article.main##

Saloua Ammar
Department of pediatric surgery, Hédi Chaker Hospital, Sfax, Faculty of medicine of Sfax, University of Sfax, Tunisia
Imen Sellami
Faculty of medicine of Sfax, University of Sfax, Tunisia
Emna Krichen
Department of pediatric surgery, Hédi Chaker Hospital, Sfax, Tunisia
Wiem Rhaiem
Department of pediatric surgery, Hédi Chaker Hospital, Sfax, Tunisia
Sahla Sellami
Faculty of medicine of Sfax, University of Sfax, Tunisia
Manar Hbaieb
Department of pediatric surgery, Hédi Chaker Hospital, Sfax, Faculty of medicine of Sfax, University of Sfax, Tunisia
Manel Kammoun
Department of anesthesiology, Hedi Chaker Hospital, Sfax, Faculty of medicine of Sfax, University of Sfax, Tunisia
Anouar Jarraya
Department of anesthesiology, Hedi Chaker Hospital, Sfax, Faculty of medicine of Sfax, University of Sfax, Tunisia
Hayet Zitouni
Department of pediatric surgery, Hédi Chaker Hospital, Sfax, Faculty of medicine of Sfax, University of Sfax, Tunisia
Riadh Mhiri
Department of pediatric surgery, Hédi Chaker Hospital, Sfax, Faculty of medicine of Sfax, University of Sfax, Tunisia

Abstract

Aim: To develop and validate a model predicting surgical treatment of intussusception in children.


Methods: Design: Retrospective study of charts and development of a model for predicting surgical treatment using logistic regression and machine learning using’’Knime’’ platform. Setting: Data collection occurred in the Department of Pediatric Surgery between January 2013 and December 2022. Patients: Children aged less than 3 years old with the diagnosis of ileocolic intussusception.


Results: One hundred and nine children were assigned to the training set, and 47 were assigned to the validation set. There were no significant differences between the two sets in clinical characteristics and surgical reduction. Surgical reduction was performed in 64 patients in the training set and 23 patients in the validation set (p=0.259). The univariate analysis showed that the duration of symptoms, mental state, palpable abdominal mass, bloody stools, elevated white blood cells, intraperitoneal effusion on ultrasound, and mass length were significantly associated with surgical treatment. After Logistic regression, bloody stools (p=0.033; OR=2.61), the duration of symptoms (p=0.028; OR=1.02), and the length of the intussusception (p=0.014; OR=1.265) were identified as independent risk factors for surgical treatment. The clinic-pathologic risk factors incorporated in the machine learning model were bloody stools, the duration of symptoms, and the length of the intussusception. This model was highly predictive, with a sensitivity and specificity of 95% for the SVM-derived model.


Conclusions: This model may be applied to facilitate pre-surgery decisions for children with intussusception. Larger prospective multicenter studies are needed to validate the model.

Keywords:

intussusception, prediction, surgery, machine learning model

##plugins.themes.academic_pro.article.details##

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

References

  1. - Tiwari C, Shah H, Sandlas G, Bothra J. Paediatric Intussusception: A Clinical Scoring System to Predict the Risk of Operative Intervention. J Mother Child 2020;24(1):19-23.
  2. - Zhuang Y, Wang X, Fan X, Li F, He G, Luo M et al . Developing a nomogram for predicting surgical intervention in pediatric intussusception after hydrostatic reduction. Front Pediatr 2023;11:1092548.
  3. - Khorana J, singhavejsakul J, Ukarapol N, laohapensang M, Jakraphan Siriwongmongkol J,1 and Patumanond J. Pronostic indicators for failed nonsurgical reduction of of intussusception. Therapeutics and Clinical Risk Management 2016;12
  4. - Carroll AG, Kavanagh RG, Ni Caoilfhionn, Cullinan NM, Lavelle LP and Malone DP . Comparative Effectiveness of Imaging Modalities for the Diagnosis and Treatment of Intussusception: A Critically Appraised Topic. Acad Radiol 2017; 24(5):521-529
  5. - Kelley-Quon LI, Arthur LG, Williams RF, Goldin AB, St Peter SD, Beres AL et al. Management of Intussusception in Children: A Systematic Review. J Ped Surg 2021; 56(3):586-596
  6. - Khorana J, Singhavejsakul J, Ukarapol N, Laohapensang M, Wakhanrittee J and Patumanond J. Enema reduction of intussusception: the success rate of hydrostatic and pneumatic reduction. Ther Clin Risk Manag. 2015;11:1837–42.
  7. - Bekdash B, Marven SS and Sprigg A. Reduction of intussusception: defining a better index of successful non-operative treatment. Pediatr Radiol 2013;43(6):649–956.
  8. - Guo, Jy., Qian, Yf. Predicting recurrent cases of intussusception in children after air enema reduction with machine learning models. Pediatr Surg Int 2023;39, 9
  9. - Khorana J, Singhavejsakul J, Ukarapol N, Laohapensang M, Siriwongmongkol J and Patumanond J. Prognostic indicators for failed nonsurgical reduction of intussusception. Ther Clin Risk Manag 2016; 12:1231–7.
  10. - Wu TH, Huang GS, Wu CT, Lai JY, Chen CC and Hu MH . Clinical characteristics of pediatric intussusception and predictors of bowel resection in affected patients. Front Surg 2022; 9:926089.
  11. - He N, Zhang S, Ye X, Zhu X, Zhao Z and Sui X. Risk factors associated with failed sonographically guided saline hydrostatic intussusception reduction in children. J Ultrasound Med 2014; 33(9):1669–75.
  12. - Bianco A, Al-Azzawi ZAM, Guadagno E, Osmanlliu E, Gravel J and Poenaru D. Use of machine learning in pediatric surgical clinical prediction tools: A systematic review. J Ped Surg 2023; 58: 908e916
  13. - Atema J, Van Rossem C, Leeuwenburgh M, Stoker J and Boermeester MA. Scoring system to distinguish uncomplicated from complicated acute appendicitis. B J Surg 2015; 102(8):979–990
  14. - Hu Y, Gong X, Shu L, Duan H, Luo Q, Zhang B et al. Understanding risk factors for postoperative mortality in neonates based on explainable machine learning technology. J Ped Surg 2021; 2165-2171
  15. - Zeng X, Hu Y, Shu L, Li J, Duan H, Shu Q et al. Explainable machine-learning predictions for complications after pediatric congenital heart surgery.Scientific Reports 2021; 11.
  16. - Ting X, Xufei D, Jiangbin L, Weijue Xu, Zhibao Lv and Guogang Ye. Development and Validation of a Nomogram for Predicting Pathological Intussusceptions in Children Prior to Surgical Intervention. Front in Pediatr 2022;10:877358.
  17. - Rejenin JA, Festen C, Van Roosmalen RP. Intussception. Factors related to treatment. Arch Dis Child1990.65(8):871-3.
  18. - Khorana J, Patmanond J, Ukarapol, Laohapensang M, Visrutaratna P, Singhavejsakul J. Clinical prediction rules for failed non operative reduction of intusception. Therapeutics and clinical risk management 2016 :12 1411-1416
  19. - He N, Zhang S, Ye X et al. Risk factors associated with failed sonographically guided saline hydrostatic intussusception reduction in children. J Ultrasound Med 2014;33(9):1669–75.
  20. - Zhang Y, Dong Q, Li SX, Zhu X, Zhao Z and Sui X. Clinical and ultrasonographic features of secondary intussusception in children. Eur Radiol 2016; 26:4329–38.
  21. - Chen B, Cao J, Yan C, Zheng C, Chen J and Guo C. A promising new predictive factor for detecting bowel resection in childhood intussusception: the lymphocyte- C-reactive protein ratio. BMC Pediatr 2021;21(1):577.
  22. - Young DG. O’Neil JA, Jr, Rowe MI, Grosfeld JL, Grosfeld JL, Fonkalsrud EW and Coran AG. Intussusception. Pediatric surgery 1998: 1185–1198.pp. 1981 ISBN: 978-0815165187
  23. - Khorana J, Singhavejsakul J, Ukarapol N, Laohapensang M, Siriwongmongkol J and Patumanond J. Prognostic indicators for failed nonsurgical reduction of intussusception. Ther Clin Risk Manag 2016; 12:1231–7.
  24. - Khorana J, Patumanond J, Ukarapol N, Laohapensang M, Visrutaratna P and Singhavejsakul J. Clinical prediction rules for failed nonoperative reduction of intussusception. Ther Clin Risk Manag 2016; 12:1