Clinical performance validation and four diagnostic strategy assessments of high-sensitivity troponin I assays

Abstract

Acute coronary syndrome (ACS) includes conditions such as unstable angina (UA), non-ST elevation myocardial infarction (NSTEMI), and ST elevation myocardial infarction (STEMI). High-sensitivity cardiac troponin I (hs-cTnI) assays have been recommended as primary biomarkers for NSTEMI diagnosis due to their high sensitivity and specificity. However, there is no consensus on the optimal diagnostic strategy for early NSTEMI detection. This study aims to evaluate the diagnostic performance of four hs-cTnI-based strategies for suspected NSTEMI: Limit of Detection (LoB), Single Cut-off, hs-cTnI 0/1 h Algorithm, and hs-cTnI 0/2 h Algorithm, in a Chinese cohort and compare the performance of assays from different manufacturers. Performance verification was conducted, including LoB, LoD, LoQ, and precision analysis. Clinical samples from 267 ACS patients were analyzed using Hybiome hs-cTnI assays. Diagnostic accuracy was assessed based on sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score. The LoB strategy demonstrated 100% sensitivity but low PPV (14.0%). Both the hs-cTnI 0/1 h Algorithm and hs-cTnI 0/2 h Algorithm showed high diagnostic performance, with the 0/2 h algorithm providing the best overall. 89.0% accuracy, 93.3% sensitivity, and 73.68% F1-score. The hs-cTnI 0/2 h Algorithm offers the most reliable diagnostic performance for early NSTEMI diagnosis.

Keywords: Diagnostic strategy; NSTEMI; hs-cTnI.

Fig. 1

Determination of LoQ of hybiome hs-cTnI assay using EP17-A2 protocol.

Fig. 2

Comparison of hybiome hs-cTnI and beckman hs-cTnI assays: Passing-bablok regression and bland-altman analysis. The passing-bablok regression analysis shows a strong linear relationship between the hybiome hs-cTnI and beckman hs-cTnI assays (y = 1.275x + 1.4, r = 0.981), with a mean difference of 35.6%(26.5–44.6%) and limits of 1.96SD ranging from − 48.3% to + 119.4%, confirming the accuracy of the regression model with a 95% CI.

Fig. 3

Diagnostic performance of various algorithms for suspected NSTEMI: comparison of limit of detection (LoB), single cut-off, hs-cTnI 0/1 h algorithm, and hs-cTnI 0/2 h algorithm. It summarizes accuracy, sensitivity, specificity, and F1-score for each method across different NSTEMI patient cohorts.