Verstovsek Srdan, Krečak Ivan, Heidel Florian H, De Stefano Valerio, Bryan Kenneth, Zuurman Mike W, Zaiac Michael, Morelli Mara, Smyth Aoife, Redondo Santiago, Bigan Erwan, Ruhl Michael, Meier Christoph, Beffy Magali, Kiladjian Jean-Jacques
Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA.
Department of Internal Medicine, General Hospital of Sibenik-Knin County, 22000 Sibenik, Croatia.
Biomedicines. 2023 Jul 7;11(7):1925. doi: 10.3390/biomedicines11071925.
Patients with polycythemia vera (PV) are at significant risk of thromboembolic events (TE). The PV-AIM study used the Optum de-identified Electronic Health Record dataset and machine learning to identify markers of TE in a real-world population. Data for 82,960 patients with PV were extracted: 3852 patients were treated with hydroxyurea (HU) only, while 130 patients were treated with HU and then changed to ruxolitinib (HU-ruxolitinib). For HU-alone patients, the annualized incidence rates (IR; per 100 patients) decreased from 8.7 (before HU) to 5.6 (during HU) but increased markedly to 10.5 (continuing HU). Whereas for HU-ruxolitinib patients, the IR decreased from 10.8 (before HU) to 8.4 (during HU) and was maintained at 8.3 (after switching to ruxolitinib). To better understand markers associated with TE risk, we built a machine-learning model for HU-alone patients and validated it using an independent dataset. The model identified lymphocyte percentage (LYP), neutrophil percentage (NEP), and red cell distribution width (RDW) as key markers of TE risk, and optimal thresholds for these markers were established, from which a decision tree was derived. Using these widely used laboratory markers, the decision tree could be used to identify patients at high risk for TE, facilitate treatment decisions, and optimize patient management.
真性红细胞增多症（PV）患者发生血栓栓塞事件（TE）的风险很高。PV-AIM研究使用了Optum去识别化电子健康记录数据集和机器学习技术，在真实世界人群中识别TE的标志物。提取了82960例PV患者的数据：3852例患者仅接受羟基脲（HU）治疗，而130例患者先接受HU治疗，然后改用芦可替尼（HU-芦可替尼）。对于仅接受HU治疗的患者，年化发病率（IR；每100例患者）从HU治疗前的8.7降至治疗期间的5.6，但在持续HU治疗时显著升至10.5。而对于HU-芦可替尼治疗的患者，IR从HU治疗前的10.8降至治疗期间的8.4，并在改用芦可替尼后维持在8.3。为了更好地了解与TE风险相关的标志物，我们为仅接受HU治疗的患者建立了一个机器学习模型，并使用独立数据集对其进行了验证。该模型确定淋巴细胞百分比（LYP）、中性粒细胞百分比（NEP）和红细胞分布宽度（RDW）为TE风险的关键标志物，并确定了这些标志物的最佳阈值，由此得出一个决策树。使用这些广泛使用的实验室标志物，该决策树可用于识别TE高危患者，促进治疗决策，并优化患者管理。
