Sabatine, Marc S.

Importance Although the Martin-Hopkins equation is widely validated and used to estimate low-density lipoprotein cholesterol (LDL-C) for clinical care, a simplified equation could streamline implementation and enable broader adoption. Objective To develop a simplified machine learning–based alternative to the Martin-Hopkins equation using multivariate adaptive regression splines (LDL-C–MH-MARS) and compare its performance with the Friedewald (LDL-C–F), Sampson–National Institutes of Health (LDL-C–S), Modified Sampson (LDL-C–MS), and Martin-Hopkins (LDL-C–MH) equations. Design, Setting, and Participants The Very Large Database of Lipids is a cross-sectional database of clinical lipid measurements from a population-representative convenience sample of adult and pediatric patients. Lipid measurements were performed by Vertical Auto Profile ultracentrifugation between October 1, 2015, and June 30, 2019. The study included patients with complete lipid panel data who were randomly assigned to a training set and a test set. External validation against preparative ultracentrifugation-based LDL-C measurements was performed in reference laboratory datasets from the Mayo Clinic (broad LDL-C concentrations) and the Further Cardiovascular Outcomes Research With Proprotein Convertase Subtilisin/Kexin Type 9 (PCSK9) Inhibition in Subjects with Elevated Risk (FOURIER) trial (observations from patients with low LDL-C concentrations while taking evolocumab). Study data were analyzed from January to October 2025. Exposures LDL-C–F, LDL-C–S, LDL-C–MS, LDL-C–MH, and LDL-C–MH-MARS equations. Main Outcomes and Measures Accuracy of estimated vs ultracentrifugation-measured LDL-C concentration based on bias, root mean square error (RMSE), and concordance by guideline-based categories. Results The study included 4 939 528 patients (mean [SD] age, 56 [16] years; 2 635 486 female [53%]) with complete lipid panel data who were randomly assigned to a training set (n = 3 292 889) and a test set (n = 1 646 639). LDL-C–MH-MARS equation demonstrated a very low median (IQR) bias of −0.1 (−2.1 to 1.8) mg/dL (to convert to millimoles per liter, multiply by 0.0259), comparable with LDL-C–MH. The median (IQR) difference between the MARS and original Martin-Hopkins equations (ie, LDL-C–MH-MARS – LDL-C–MH) was −0.5 (−1.2 to 0) mg/dL, further suggesting comparability between the 2 methods. The RMSE was smallest for LDL-C–MH-MARS (4.7 mg/dL) and LDL-C–MH (4.9 mg/dL), followed by LDL-C–S (5.8 mg/dL), LDL-C-MS (6.0 mg/dL), and LDL-C–F (7.2 mg/dL). The proportion of patients correctly classified according to clinical categories was nearly identical for LDL-C–MH-MARS (89.7%) and LDL-C–MH (89.6%) but lower for LDL-C–S (86.3%), LDL-C–MS (84.7%), and LDL-C–F (83.1%). The LDL-C–MH-MARS, LDL-C–MH, LDL-C–MS, LDL-C–S, and LDL-C–F equations underestimated LDL-C concentration in 16%, 17%, 28%, 39%, and 60%, respectively, when classifying LDL-C less than 70 mg/dL in patients with triglyceride concentrations of 200 to 399 mg/dL (to convert to millimoles per liter, multiply by 0.0113). The patterns of results were similar in external validation datasets, with the LDL-C–MH-MARS and LDL-C–MH equations demonstrating the highest accuracy. Conclusions and Relevance Study results suggest that the new machine learning–based LDL-C equation provided results comparable with those of the original Martin-Hopkins method while simplifying implementation to a single equation.

Abstract Background Cardiovascular guidelines have long recommended low-density lipoprotein-cholesterol (LDL-C) as the primary target for lipid-lowering therapy. Recent guidelines have emphasized the importance of achieving low LDL-C levels; hence, the accurate measurement of low LDL-C is increasingly clinically relevant. Methods Using lipid panel test results from the Mayo Clinic (n = 24 590) and the FOURIER clinical trial of evolocumab (n = 9605), the following modified Sampson equation was developed by least-squares regression to match LDL-C (mg/dL) by the β-quantification reference method, by combining terms into non High Density Lipoprotein Cholesterol (nonHDLC = Total Cholesterol – High Density Lipoprotein Cholesterol) and forcing the coefficient to be one: Results The modified Sampson equation demonstrated significant improvement in its concordance to the reference method compared to other equations (the Lin Concordance Correlation Coefficient 0.992, P < 0.001). By overall kappa analysis, it showed the best agreement to the reference method at the 55 mg/dL cutpoint (1.4 mmol/L, 0.98 [P < 0.001], Sampson–NIH: 0.96, Martin–Hopkins: 0.96, Friedewald: 0.94) and the 70 mg/dL cutpoint (1.8 mmol/L, 0.97 [P < 0.001], Sampson–NIH: 0.94, Martin–Hopkins: 0.95, Friedewald: 0.92). The false classification rate of the modified Sampson equation was also significantly lower compared to the other equations at 55 mg/dL (15%, [P < 0.001], Sampson–NIH: 29%, Martin–Hopkins: 28%, Friedewald: 37%) and 70 mg/dL (18%, [P < 0.001]; Sampson–NIH: 30%, Martin–Hopkins: 28.%, Friedewald: 34%). The new equation increases the percentage of correctly classified patients with low LDL-C by approximately 10% to 20% over the other equations based on its net reclassification index. Conclusions The modified Sampson equation shows improved accuracy compared to other equations for low LDL-C. It more accurately identifies high-risk patients, who are not at their LDL-C goals and could benefit from more intensive lipid-lowering therapy.

Background— Data supporting the prognostic significance of high-sensitivity C-reactive protein (hs-CRP) are derived largely from individuals with no overt coronary artery disease or from patients with acute coronary syndromes. In contrast, the ability of hs-CRP to predict outcomes in patients with stable coronary artery disease and the prognostic significance of the Centers for Disease Control/American Heart Association hs-CRP cut points in such a population remain relatively unexplored. Methods and Results— We measured hs-CRP in 3771 patients with stable coronary artery disease from the Prevention of Events With Angiotensin-Converting Enzyme Inhibition (PEACE) trial, a randomized placebo-controlled trial of the angiotensin-converting enzyme inhibitor trandolapril. Patients were followed up for a median of 4.8 years for cardiovascular death, myocardial infarction, or stroke, as well as new heart failure and diabetes. After adjustment for baseline characteristics and treatments, higher hs-CRP levels, even >1 mg/L, were associated with a significantly greater risk of cardiovascular death, myocardial infarction, or stroke (hs-CRP 1 to 3 mg/L: adjusted hazard ratio, 1.39; 95% CI, 1.06 to 1.81; P =0.016; hs-CRP >3 mg/L: adjusted hazard ratio, 1.52; 95% CI, 1.15 to 2.02; P =0.003). Similarly, elevated hs-CRP levels were an independent predictor of new heart failure (adjusted P <0.001 for trend) and new diabetes (adjusted P <0.001 for trend). There were no significant interactions between hs-CRP levels and the effects of trandolapril on any of the above outcomes. Conclusions— In stable coronary artery disease, an elevated hs-CRP level, even >1 mg/L, is a significant predictor of adverse cardiovascular events independently of baseline characteristics and treatments. An elevated hs-CRP does not appear to identify patients with stable coronary artery disease and preserved ejection fraction who derive particular benefit from angiotensin-converting enzyme inhibition.