Department of Rheumatology, Qilu Hospital of Shandong University, Jinan, Shandong, China.
Department of Neurology, Qilu Hospital of Shandong University, Jinan, Shandong, China.
CNS Neurosci Ther. 2024 Aug;30(8):e14882. doi: 10.1111/cns.14882.
To explore the clinico-sero-pathological characteristics and risk prediction model of idiopathic inflammatory myopathy (IIM) patients with different muscular perifascicular (PF) changes.
IIM patients in our center were enrolled and the clinico-sero-pathological data were retrospectively analyzed. A decision tree model was established through machine learning.
There were 231 IIM patients enrolled, including 53 with perifascicular atrophy (PFA), 39 with perifascicular necrosis (PFN), and 26 with isolated perifascicular enhancement of MHC-I/MHC-II (PF-MHCn). Clinically, PFA patients exhibited skin rashes and dermatomyositis-specific antibodies (DM-MSAs, 74.5%) except for anti-Mi2. PFN patients showed the most severe muscle weakness, highest creatine kinase (CK), anti-Mi2 (56.8%), and anti-Jo-1 (24.3%) antibodies. PF-MHCn patients demonstrated negative MSAs (48.0%) and elevated CK. Histopathologically, MAC predominantly deposited on PF capillaries in PFA but on non-necrotic myofiber in PFN (43.4% and 36.8%, p < 0.001). MxA expression was least in PF-MHCn (36.0% vs. 83.0% vs. 63.2%, p < 0.001). The decision tree model could effectively predict different subgroups, especially PFA and PFN.
Three types of PF change of IIMs representing distinct clinico-serological characteristics and pathomechanism. Undiscovered MSAs should be explored especially in PF-MHCn patients. The three pathological features could be accurately predicted through the decision tree model.
探讨不同肌束膜旁（PF）改变的特发性炎性肌病（IIM）患者的临床、血清学和病理特征及风险预测模型。
回顾性分析我院收治的 IIM 患者的临床、血清学和病理资料，采用机器学习建立决策树模型。
共纳入 231 例 IIM 患者，其中肌束膜旁萎缩 53 例（PFA），肌束膜旁坏死 39 例（PFN），肌束膜旁 MHC-I/MHC-II 单独增强 26 例（PF-MHCn）。PFA 患者除抗 Mi2 外，均有皮疹和皮肌炎特异性抗体（DM-MSAs，74.5%），PFN 患者肌无力最严重，肌酸激酶（CK）、抗 Mi2（56.8%）和抗 Jo-1（24.3%）抗体水平最高，PF-MHCn 患者则表现为阴性 MSAs（48.0%）和 CK 升高。病理上，PFA 以 MAC 主要沉积于 PF 毛细血管，PFN 以非坏死肌纤维为主（43.4%和 36.8%，p<0.001），PF-MHCn 中 MxA 表达最少（36.0% vs. 83.0% vs. 63.2%，p<0.001）。决策树模型能有效预测不同亚组，特别是 PFA 和 PFN。
三种 IIM 肌束膜旁改变代表不同的临床、血清学和发病机制。尤其是在 PF-MHCn 患者中，应进一步探索未发现的 MSAs。该决策树模型可准确预测三种病理特征。
