A Combination of Multilayer Perceptron, Radial Basis Function Artificial Neural Networks, and Machine Learning Image Segmentation for the Dimension Reduction and the Prognosis Assessment of Diffuse Large B-Cell Lymphoma

• Main Authors: Joaquim Carreras, Yara Yukie Kikuti, Masashi Miyaoka, Shinichiro Hiraiwa, Sakura Tomita, Haruka Ikoma, Yusuke Kondo, Atsushi Ito, Naoya Nakamura, Rifat Hamoudi
• Format: Article
• Language: English
• Published: MDPI AG 2021-03-01
• Series: AI
• Subjects: overall survival; diffuse large B-cell lymphoma; artificial intelligence; Multilayer Perceptron; Radial Basis Function; PD-L1 (CD274)
• Online Access: https://www.mdpi.com/2673-2688/2/1/8
• ISSN: 2673-2688

The prognosis of diffuse large B-cell lymphoma (DLBCL) is heterogeneous. Therefore, we aimed to highlight predictive biomarkers. First, artificial intelligence was applied into a discovery series of gene expression of 414 patients (GSE10846). A dimension reduction algorithm aimed to correlate with the overall survival and other clinicopathological variables; and included a combination of Multilayer Perceptron (MLP) and Radial Basis Function (RBF) artificial neural networks, gene-set enrichment analysis (GSEA), Cox regression and other machine learning and predictive analytics modeling [C5.0 algorithm, logistic regression, Bayesian Network, discriminant analysis, random trees, tree-AS, Chi-squared Automatic Interaction Detection CHAID tree, Quest, classification and regression (C&R) tree and neural net)]. From an initial 54,613 gene-probes, a set of 488 genes and a final set of 16 genes were defined. Secondly, two identified markers of the immune checkpoint, PD-L1 (<i>CD274</i>) and IKAROS (<i>IKZF4</i>), were validated in an independent series from Tokai University, and the immunohistochemical expression was quantified, using a machine-learning-based Weka segmentation. High PD-L1 associated with poor overall and progression-free survival, non-GCB phenotype, Epstein–Barr virus infection (EBER+), high RGS1 expression and several clinicopathological variables, such as high IPI and absence of clinical response. Conversely, high expression of IKAROS was associated with a good overall and progression-free survival, GCB phenotype and a positive clinical response to treatment. Finally, the set of 16 genes (<i>PAF1, USP28, SORT1, MAP7D3, FITM2, CENPO, PRCC, ALDH6A1, CSNK2A1, TOR1AIP1, NUP98, UBE2H, UBXN7, SLC44A2, NR2C2AP</i> and <i>LETM1</i>), in combination with <i>PD-L1</i>, <i>IKAROS</i>, <i>BCL2</i>, <i>MYC</i>, <i>CD163</i> and <i>TNFAIP8</i>, predicted the survival outcome of DLBCL with an overall accuracy of 82.1%. In conclusion, building predictive models of DLBCL is a feasible analytical strategy.