Numerous studies have revealed the relationship between lipid expression and increased cardiovascular risk in ST-segment elevation myocardial infarction (STEMI) patients. Nevertheless, few investigations have focused on the risk stratification of STEMI patients using machine learning algorithms. A total of 1355 STEMI patients who underwent percutaneous coronary intervention were enrolled in this study during 2015–2018. Unsupervised machine learning (consensus clustering) was applied to the present cohort to classify patients into different lipid expression phenogroups, without the guidance of clinical outcomes. Kaplan-Meier curves were implemented to show prognosis during a 904-day median follow-up (interquartile range: 587–1316). In the adjusted Cox model, the association of cluster membership with all adverse events including all-cause mortality, all-cause rehospitalization, and cardiac rehospitalization was evaluated. All patients were classified into three phenogroups, 1, 2, and 3. Patients in phenogroup 1 with the highest Lp(a) and the lowest HDL-C and apoA1 were recognized as the statin-modified cardiovascular risk group. Patients in phenogroup 2 had the highest HDL-C and apoA1 and the lowest TG, TC, LDL-C and apoB. Conversely, patients in phenogroup 3 had the highest TG, TC, LDL-C and apoB and the lowest Lp(a). Additionally, phenogroup 1 had the worst prognosis. Furthermore, a multivariate Cox analysis revealed that patients in phenogroup 1 were at significantly higher risk for all adverse outcomes. Machine learning-based cluster analysis indicated that STEMI patients with increased concentrations of Lp(a) and decreased concentrations of HDL-C and apoA1 are likely to have adverse clinical outcomes due to statin-modified cardiovascular risks. ChiCTR1900028516 ( http://www.chictr.org.cn/index.aspx ).

中文翻译：

---

使用基于血脂谱的机器学习对 ST 段抬高型心肌梗死 (STEMI) 患者进行风险分层

大量研究揭示了 ST 段抬高型心肌梗死 (STEMI) 患者的脂质表达与心血管风险增加之间的关系。然而，很少有研究关注使用机器学习算法对 STEMI 患者进行风险分层。本研究共纳入 1355 名 2015-2018 年间接受经皮冠状动脉介入治疗的 STEMI 患者。在没有临床结果指导的情况下，将无监督机器学习（共识聚类）应用于当前队列，将患者分为不同的脂质表达表型组。采用 Kaplan-Meier 曲线来显示 904 天中位随访期间的预后（四分位数范围：587-1316）。在调整后的 Cox 模型中，评估了聚类成员资格与所有不良事件（包括全因死亡率、全因再住院和心脏再住院）的关联。所有患者均分为三个表组：1、2 和 3。表组 1 中 Lp(a) 最高、HDL-C 和 apoA1 最低的患者被认为是他汀类药物改良的心血管风险组。表组 2 患者的 HDL-C 和 apoA1 最高，TG、TC、LDL-C 和 apoB 最低。相反，表型组 3 中的患者具有最高的 TG、TC、LDL-C 和 apoB 以及最低的 Lp(a)。此外，表型组 1 的预后最差。此外，多变量 Cox 分析显示，表型组 1 中的患者发生所有不良后果的风险显着较高。基于机器学习的聚类分析表明，Lp(a) 浓度升高、HDL-C 和 apoA1 浓度降低的 STEMI 患者可能会因他汀类药物改善心血管风险而出现不良临床结果。ChiCTR1900028516（http://www.chictr.org.cn/index.aspx）。