Lipids & metabolic liver disease
Interpretable machine learning analysis of immunoinflammatory biomarkers for predicting Coronary Heart Disease (CHD) among Non-Alcoholic Fatty Liver Disease (NAFLD) patients
Authors' conclusion
Six immunoinflammatory markers demonstrated significant associations with CHD risk in NAFLD populations, among which the NHR index exhibited particularly promising predictive potential.
Study context
- Population
- NAFLD patients undergoing coronary angiography282 after propensity score matching (PSM)
- Participants
- 407 patients
- Exposure
- NAFLD + CHD vs NAFLD without CHD
- NAFLD + CHDn = 250
- NAFLDn = 157reference
- Outcome
- Risk factors for CHD in NAFLD (multivariate logistic regression, adjusted for age, sex, hypertension, smoking history)
Methodological detailspropensity-score matched, Lasso regression, interpretable machine learning (RF, SVM, GLM; SHAP)
- Propensity-score matched
- Lasso regression
- Interpretable machine learning (RF, SVM, GLM; SHAP)
Main finding
As reported in the abstract
NHR index, most significant risk factor for CHD: OR
1.375
95% CI 1.021–1.852P < 0.001
Observational data: associations, not effects.
Further findings
Other independent risk/protective factors for CHD
- NLR, SII, SIRI and NMR were also identified as risk factors
- PNR was a protective factor for CHD events in NAFLD
Restricted cubic splines (RCS) analysis: shape of relationship with CHD occurrence
- SII non-linear J-shaped relationship with CHD risk, non-linear P
- 0.025
- Linear relationships of NHR, NLR and PNR with CHD occurrence
Correlation of NHR with Gensini score (CHD severity)
- NHR had the highest correlation with CHD severity, R
- 0.256
- P
- P < 0.001
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Composed by AI from the published abstract and checked against it. How Briefs are made →