Lipids & metabolic liver disease
Relationship between atherogenic index of plasma and length of stay in critically ill patients with atherosclerotic cardiovascular disease: a retrospective cohort study and predictive modeling based on machine learning
Authors' conclusion
AIP is a significant predictor of ICU and hospital LOS in patients with critically ill ASCVD. AIP could serve as an early prognostic tool for guiding clinical decision-making and managing patient outcomes.
Study context
- Population
- Critically ill patients with atherosclerotic cardiovascular disease (ASCVD), MIMIC-IV; 54.91% male
- Participants
- 2,423 patients
- Exposure
- Higher vs lower atherogenic index of plasma (AIP)
- Outcome
- ICU LOS and total hospital LOS (prolonged stay)
Methodological detailsMIMIC-IV database, machine learning predictive modelling
- MIMIC-IV database
- Machine learning predictive modelling
Main finding
As reported in the abstract
Prolonged ICU and hospital LOS per unit increase in AIP
Prolonged ICU length of stay (LOS), per unit AIP increase: adjusted OR
1.42
95% CI 1.11–1.81P = 0.006
Prolonged hospital LOS, per unit AIP increase: adjusted OR
1.73
95% CI 1.34–2.24P < 0.001
Observational data: associations, not effects.
Further findings
Shape of association (restricted cubic spline (RCS) regression)
- Linear relationship between increasing AIP and both ICU LOS and hospital LOS
Machine learning (ML) prediction of LOS endpoints
- LGB ROC
- 0.740
- Logistic regression (LR) ROC
- 0.832
- AIP identified as a vital component of hospitalization duration
Original publication
Relationship between atherogenic index of plasma and length of stay in critically ill patients with atherosclerotic cardiovascular disease: a retrospective cohort study and predictive modeling based on machine learning. Cardiovasc Diabetol. Published 28 February 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →