Anastomotic Leak is Increased With Clostridium difficile Infection After Colectomy: Machine Learning-Augmented...

Area of Science:

• Surgical outcomes research
• Infectious disease epidemiology
• Health informatics

Background:

• Clostridium difficile infection (CDI) is a leading cause of healthcare-associated infections, with rising incidence and severity.
• CDI contributes to anastomotic leak (AL) due to bacterial collagenase production.
• Asymptomatic colonization with C. difficile is increasing, particularly in high-risk patients.

Purpose of the Study:

• To investigate the association between CDI and AL in colectomy patients.
• To quantify the impact of CDI on AL, mortality, and length of stay.
• To explore the dose-dependent relationship between CDI, AL, and patient comorbidities (ASA class).

Main Methods:

• Nationally representative case-control study using the ACS-NSQIP database.
• Machine learning-augmented multivariable regression (backward propagation neural network).
• Propensity score (PS)-modified analysis (doubly robust augmented inverse probability weighted).

Main Results:

• CDI significantly increases the odds of anastomotic leak (OR 2.39, P < .001).
• CDI independently increases AL likelihood by 3.8%–6.8%.
• The risk of AL in CDI patients increases with higher ASA class (dose-dependent effect).

Conclusions:

• This is the first national study linking CDI and AL in colectomy patients.
• Advanced statistical methods confirm CDI as a significant risk factor for AL.
• CDI exacerbates AL risk in a manner that is dependent on patient's ASA class.