To explore the diagnostic value of cardiac magnetic resonance feature tracking (CMR-FT) divided left atrial (LA) strain in differentiating constrictive pericarditis (CP) and restrictive cardiomyopathy (RCM). Patients with CP (n = 40) and RCM (n = 40), and another 40 normal control group were retrospectively enrolled over a period of 8 years at a tertiary cardiac centre. Left ventricular (LV) and biatrial strain and strain rate (SR) were measured. Atrial strain was used to differentiate between patients with CP and RCM. Then, patients were grouped according to their left ventricular ejection fraction (LVEF), either ≥50% or < 50%. A deeper analysis was done to evaluate the diagnostic value of atrial strain in these subgroups. Receiver operating characteristic curves (ROC) were used to assess the accuracy of myocardial strain based on CMR FT for the differential diagnosis of CP and RCM. LV and LA strain and SR were significantly lower in patients with CP and RCM than those in the normal controls (P < 0.05). LA strain and SR were significantly lower in the RCM group than in the CP group (P < 0.05). In patients with either LVEF≥50% or＜50%, LA strain were lower in the RCM group than in the CP group (P < 0.05). ROC analysis showed that LA stored strain (LA-εs) had a good differential diagnostic value for CP and RCM, with an area under the curve (AUC) of 0.811 and an optimal cutoff value of 6.98%, above this value it tends to develop CP. Further, an excellent differential diagnostic value was found in patients with LVEF＜50%, with an AUC of 0.955. LA strain analysis obtained by CMR-FT provides good differential diagnostic value for distinguishing CP from RCM, especially in patients with LVEF＜50%.

利用机器学习的方法评估基于冠状动脉CT血管成像（coronary CT angiography, CCTA）的力学组学对左冠状动脉前降支心肌桥近端斑块形成的预测价值。 回顾性搜集2007年1月–2021年4月在我院行至少2次CCTA检查示左冠状动脉前降支心肌桥且基线左冠状动脉前降支无粥样硬化斑块的患者，两次CCTA检查间隔3个月以上。心肌桥近端粥样硬化斑块的形成为主要终点事件。记录患者的人口学特征和临床危险因素并将不同组别患者按照年龄性别进行 1∶1 匹配。基于CCTA进行计算流体动力学分析。在CCTA图像上测量心肌桥的位置、长度、深度和收缩期狭窄指数，以及提取左冠状动脉前降支近段的力学组学参数。利用多因素Cox回归筛选有意义特征，采用随机森林算法挑选力学组学特征并进行后续建模，为每个患者的力学组学特征进行赋值评分。采用对数秩检验方法和Kaplan-Meier图探讨力学组学模型对未来斑块形成的预测价值。采用受试者工作特征曲线评估不同心肌桥组对斑块形成的预测价值。 该研究共纳入104例左冠状动脉前降支心肌桥患者，其中52例患者心肌桥近端斑块形成，中位随访时间为3.0年。总人群的平均年龄为（54.56±10.56）岁，75.00%（78/104）为男性。除吸烟史外（21.15% vs. 5.77%, P=0.04），其余的临床及解剖学特征在有无斑块形成组间差异无统计学意义（所有P>0.05）。入组患者按照7∶3分为训练集（n=74）和验证集（n=30），随机森林算法构建的力学组学模型按照赋分≥0.46和<0.46为赋分较高组和赋分较低组，力学组学模型在验证组的敏感性、准确性分别为0.87（0.58～0.98）和0.63（0.44～0.79）。多因素Cox回归模型中，力学组学（危险比=10.58；95%置信区间：3.23～34.64，P≤0.001）与斑块形成呈正相关。通过对数秩检验力学组学赋分较高组相对于赋分较低组在心肌桥近端更容易形成斑块（P<0.001）。全部人群、训练集、验证集、表浅心肌桥组、长心肌桥组和短心肌桥组力学组学预测斑块形成曲线下面积分别为0.88（0.82～0.95）、0.89（0.82～0.96）、0.86（0.74～0.99）、0.92（0.86～0.97）、0.86（0.74～0.98）和0.91（0.83～0.98）。 力学组学对左冠状动脉前降支心肌桥近端动脉粥样硬化斑块形成有一定预测价值。