Bayesian Networks in Pediatric Cardiac Surgery

Use of Deep Neural Networks and Bayesian Analysis to Identify Risk Factors for Poor Outcome After Pediatric Cardiac Surgery

Pediatric cardiac surgery with cardiopulmonary bypass is associated with significant morbidity and mortality. Also score systems for risk factors, such as Risk Adjustment for Congenital Heart surgery (RACHS 1) score or the ARISTOTLE score, have been developed, outcome prediction remains difficult. New mathematical methods using deep neural networks associated with Bayesian statistical methods have been developed to give a better understanding of the complex interaction between different risk factors, to identify risk factors and group them in related families. This method has been successfully used to predict mortality in dialysis patient as well as to better describe complex psychiatric syndromes.

The primary hypothesis of this study is that the use of these tools will give a better understanding on the factors affecting outcome after pediatric cardiac surgery.

A network analysis using Gaussian Graphical Models, Mixed Graphical models and Bayesian networks will be used to identify single or groups of risk factors for morbidity and mortality after pediatric cardiac surgery under cardiopulmonary bypass.

Study Overview

• Status: Completed
• Conditions: Cardiopulmonary Bypass; Pediatrics; Cardiac Surgical Procedures
• Intervention / Treatment: Procedure: Pediatric cardiac surgery under cardiopulmonary bypass

• Study Type: Observational
• Enrollment (Actual): 1364

Contacts and Locations

Study Locations

• Belgium
  • Brussels, Belgium, 1020
    • Hopital Universitaire des Enfants Reine Fabiola

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: No older than 16 years (Child)
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

All patients with pediatric cardiac surgery under cardiopulmonary bypass between 2008 and 2018 at our institution

Description

Inclusion Criteria:

• 0 to 16 years
• cardiac surgery under cardiopulmonary bypass

Exclusion Criteria:

• ASA (American Society of Anesthesiologists) status 5
• Jehovah's Witness

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Retrospective

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Pediatric cardiac surgery; All patients with pediatric cardiac surgery under cardiopulmonary bypass between 2008 and 2018 will be included	Procedure: Pediatric cardiac surgery under cardiopulmonary bypass; All patients with pediatric cardiac surgery under cardiopulmonary bypass between 2008 and 2018 operated at our institution

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Outcome predictors	All preoperative, peroperative and postoperative variables will be entered into a deep neural network with Bayesian statistics to identify groups or individual risk factors for postoperative morbidity and mortality	28 days

Collaborators and Investigators

• Sponsor: Brugmann University Hospital
• Collaborators: Université Libre de Bruxelles

Publications and helpful links

General Publications

• Jenkins KJ, Gauvreau K, Newburger JW, Spray TL, Moller JH, Iezzoni LI. Consensus-based method for risk adjustment for surgery for congenital heart disease. J Thorac Cardiovasc Surg. 2002 Jan;123(1):110-8. doi: 10.1067/mtc.2002.119064.
• Lacour-Gayet F, Clarke D, Jacobs J, Comas J, Daebritz S, Daenen W, Gaynor W, Hamilton L, Jacobs M, Maruszsewski B, Pozzi M, Spray T, Stellin G, Tchervenkov C, Mavroudis And C; Aristotle Committee. The Aristotle score: a complexity-adjusted method to evaluate surgical results. Eur J Cardiothorac Surg. 2004 Jun;25(6):911-24. doi: 10.1016/j.ejcts.2004.03.027.
• Siga MM, Ducher M, Florens N, Roth H, Mahloul N, Fouque D, Fauvel JP. Prediction of all-cause mortality in haemodialysis patients using a Bayesian network. Nephrol Dial Transplant. 2020 Aug 1;35(8):1420-1425. doi: 10.1093/ndt/gfz295.
• Briganti G, Linkowski P. Item and domain network structures of the Resilience Scale for Adults in 675 university students. Epidemiol Psychiatr Sci. 2019 Apr 22;29:e33. doi: 10.1017/S2045796019000222.
• Till AC, Florquin R, Delhaye M, Kornreich C, Williams DR, Briganti G. A network perspective on abnormal child behavior in primary school students. Psychol Rep. 2023 Aug;126(4):1933-1953. doi: 10.1177/00332941221077907. Epub 2022 Mar 24.

Study record dates

Study Major Dates

• Study Start (Actual): September 17, 2022
• Primary Completion (Actual): March 31, 2023
• Study Completion (Actual): April 30, 2023

Study Registration Dates

• First Submitted: September 8, 2022
• First Submitted That Met QC Criteria: September 8, 2022
• First Posted (Actual): September 13, 2022

Study Record Updates

• Last Update Posted (Actual): July 27, 2023
• Last Update Submitted That Met QC Criteria: July 26, 2023
• Last Verified: July 1, 2023

More Information

Terms related to this study

• Other Study ID Numbers: PED_CARDIAC_surg_Bayesian

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No