Coppinger Justine, West Tim, Kirmess Kris M, Fogelman Ilana, Ray Sutapa, Verghese Philip B, Braunstein Joel B, Yarasheski Kevin E
C2N Diagnostics, LLC, St. Louis, MO USA.
NPJ Dement. 2025;1(1):23. doi: 10.1038/s44400-025-00026-y. Epub 2025 Sep 4.
The diagnostic performance of the Amyloid Probability Score 2 (APS2; the algorithmic result of the PrecivityAD2™ blood test) was originally trained and validated in two cohorts of cognitively impaired (CI) individuals and is in clinical use. Here, we further test the repeatability and reliability of the prespecified APS2 algorithm and cut point in an independent cohort. APS2 diagnostic performance was determined using amyloid positron emission tomography (PET) as the reference standard. Concordance with amyloid PET was high (AUC-ROC 0.95 (95% CI): 0.93-0.98); 54% of participants had a positive APS2. The previously validated APS2 cut point yielded an overall accuracy of 91% (95% CI: 86-94%), sensitivity 90% (95% CI: 83-94%) and specificity 92% (95% CI: 84-96%). Our findings demonstrate that the prespecified APS2 algorithm and cut point are repeatable, reliable, robust, accurate, and generalizable for identifying brain beta-amyloid pathology in patients with cognitive impairment and being evaluated in a clinical care setting.
淀粉样蛋白概率评分2（APS2；PrecivityAD2™血液检测的算法结果）的诊断性能最初在两组认知障碍（CI）个体中进行了训练和验证，目前已投入临床使用。在此，我们在一个独立队列中进一步测试了预先设定的APS2算法和切点的可重复性和可靠性。以淀粉样蛋白正电子发射断层扫描（PET）作为参考标准来确定APS2的诊断性能。与淀粉样蛋白PET的一致性很高（AUC-ROC为0.95（95%CI）：0.93-0.98）；54%的参与者APS2呈阳性。先前验证的APS2切点的总体准确率为91%（95%CI：86-94%），敏感性为90%（95%CI：83-94%），特异性为92%（95%CI：84-96%）。我们的研究结果表明，预先设定的APS2算法和切点对于识别认知障碍患者的脑β淀粉样蛋白病理状况具有可重复性、可靠性、稳健性、准确性和可推广性，并且可在临床护理环境中进行评估。
