Related Experiment Video
Updated: Aug 27, 2025
Surgical Swine Model of Chronic Cardiac Ischemia Treated by Off-Pump Coronary Artery Bypass Graft Surgery
Published on: March 27, 2018
Causal determinants of postoperative length of stay in cardiac surgery using causal graphical learning
Jaron J R Lee1, Ranjani Srinivasan2, Chin Siang Ong3
1Department of Computer Science, Johns Hopkins University, Baltimore, Md; Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, Md.
Insights
Causal graphical modeling identified key factors influencing cardiac surgery patient length of stay. Understanding these determinants can improve clinical protocols and patient management strategies.
Area of Science:
- Cardiovascular Surgery
- Medical Informatics
- Causal Inference
Background:
- Postoperative length of stay (LOS) is a critical metric in cardiac surgery.
- Identifying true causal determinants of LOS is essential for effective clinical interventions.
- Existing statistical methods may not fully capture complex causal relationships.
Purpose of the Study:
- To determine the causal factors affecting postoperative length of stay in patients undergoing coronary artery bypass grafting or aortic valve replacement.
- To differentiate between direct and indirect causes of prolonged postoperative LOS.
- To compare causal effects with traditional statistical associations.
Main Methods:
- Utilized causal graphical modeling (Fast Causal Inference algorithm) on electronic health record data from 2011-2016.
- Employed the latent variable intervention-calculus when the directed acyclic graph is absent (LV-IDA) algorithm to quantify causal effects.
- Integrated background clinical knowledge to construct a Partial Ancestral Graph (PAG).
- Contrasted causal findings with results from standard linear regression analysis.
Main Results:
- The study analyzed 2610 cardiac surgery patients, with a mean LOS of 219 hours (vs. national mean of 168 hours).
- Identified direct causes (e.g., age, diabetes, complications) and indirect causes (e.g., gender, race, surgeon) of LOS.
- Strongest causal effects included preoperative dialysis (209 hrs), neuro/infection complications (315/131 hrs), and total operating time (48 hrs).
- Linear regression analysis showed divergent results compared to causal effect estimates.
Conclusions:
- Causal graphical modeling effectively identified direct and indirect determinants of postoperative length of stay in cardiac surgery.
- Findings provide valuable insights for optimizing clinical protocols and patient management strategies.
- Distinguishing causal effects from mere associations is crucial for targeted healthcare improvements.
Objective:
We aimed to learn the causal determinants of postoperative length of stay in cardiac surgery patients undergoing isolated coronary artery bypass grafting or aortic valve replacement surgery.
Methods:
For patients undergoing isolated coronary artery bypass grafting or isolated aortic valve replacement surgeries between 2011 and 2016, we used causal graphical modeling on electronic health record data. The Fast Causal Inference (FCI) algorithm from the Tetrad software was used on data to estimate a Partial Ancestral Graph (PAG) depicting direct and indirect causes of postoperative length of stay, given background clinical knowledge. Then, we used the latent variable intervention-calculus when the directed acyclic graph is absent (LV-IDA) algorithm to estimate strengths of causal effects of interest. Finally, we ran a linear regression for postoperative length of stay to contrast statistical associations with what was learned by our causal analysis.
Results:
In our cohort of 2610 patients, the mean postoperative length of stay was 219 hours compared with the Society of Thoracic Surgeons 2016 national mean postoperative length of stay of approximately 168 hours. Most variables that clinicians believe to be predictors of postoperative length of stay were found to be causes, but some were direct (eg, age, diabetes, hematocrit, total operating time, and postoperative complications), and others were indirect (including gender, race, and operating surgeon). The strongest average causal effects on postoperative length of stay were exhibited by preoperative dialysis (209 hours); neuro-, pulmonary-, and infection-related postoperative complications (315 hours, 89 hours, and 131 hours, respectively); reintubation (61 hours); extubation in operating room (-47 hours); and total operating room duration (48 hours). Linear regression coefficients diverged from causal effects in magnitude (eg, dialysis) and direction (eg, crossclamp time).
Conclusions:
By using retrospective electronic health record data and background clinical knowledge, causal graphical modeling retrieved direct and indirect causes of postoperative length of stay and their relative strengths. These insights will be useful in designing clinical protocols and targeting improvements in patient management.
Related Concept Videos
01:28Cardiomyopathy VII: Pre and Post Operative Nursing Management
01:15Assumptions of Survival Analysis
01:21Causality in Epidemiology
01:23Peripheral Artery Disease V: Postoperative Nursing Management
01:21Cancer Survival Analysis
01:18Introduction To Survival Analysis
The primary goal of survival analysis is to estimate survival time—the time...