Identification of clinical heterogeneity and construction of a novel subtype predictive model in patients with ankylosing spondylitis: An unsupervised machine learning study

• Published in: International immunopharmacology Vol. 117; p. 109879
• Main Authors: Sun, Xuhua, Zhou, Chenxing, Zhu, Jichong, Wu, Shaofeng, Liang, Tuo, Jiang, Jie, Chen, Jiarui, Chen, Tianyou, Huang, Sheng Sheng, Chen, Liyi, Ye, Zhen, Guo, Hao, Zhan, Xinli, Liu, Chong
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.04.2023
• Subjects: Alpha-Ketoglutarate-Dependent Dioxygenase FTO; Ankylosing spondylitis; C-Reactive Protein; Cluster Analysis; Databases, Factual; Humans; Immune cell infiltration; Immunohistochemistry; Machine learning; Predictive model; Spondylitis, Ankylosing - genetics; Unsupervised Machine Learning; Immunohistochemistry; FTO; CRP; BASO; Predictive model; MONO; AUC; SC; MNR; ALKBH5; RBC; MLR; NLR; PNR; LASSO; PLR; WBC; PLT; Ankylosing spondylitis; ML; BMI; LYM; YTHDF1; BASDAI; HGB; YTHDF2; YTHDF3; SpA; ESR; NASML1; METTL3; NASML2; ROC; EOS; GEO; Immune cell infiltration; AS; SML; RF; PMR; UML; Machine learning; BASFI; m6A; BASRI-hip score; CBLL1; NEU

•We used UML to classify AS patients based on similar clinical characteristics. We then used the clinical data to construct a novel subtype predictive model based on the two UML clusters.•To determine the AS pathogenesis process, we analyzed the difference in the immune microenvironment between AS p...