Imatinib adherence prediction using machine learning approach in patients with gastrointestinal stromal tumor.

BACKGROUND: Nonadherence to imatinib is common in patients with gastrointestinal stromal tumor (GIST), which is associated with poor prognosis and financial burden. The primary aim of this study was to investigate the adherence rate in patients with GIST and subsequently develop a model based on machine learning (ML) and deep learning (DL) techniques to identify the associated factors and predict the risk of imatinib nonadherence. METHODS: All eligible patients completed four sections of questionnaires. After the data set was preprocessed, statistically significance variables were identified and further processed to modeling. Six ML and four DL algorithms were applied for modeling, including eXtreme gradient boosting, light gradient boosting machine (LGBM), categorical boosting, random forest, support vector machine, artificial neural network, multilayer perceptron, NaiveBayes, TabNet, and Wide&Deep. The optimal ML model was used to identify potential factors for predicting adherence. RESULTS: A total of 397 GIST patients were recruited. Nonadherence was observed in 185 patients (53.4%). LGBM exhibited superior performance, achieving a mean f1_score of 0.65 and standard deviation of 0.12. The predominant indicators for nonadherent prediction of imatinib were cognitive functioning, whether to perform therapeutic drug monitoring (if_TDM), global health status score, social support, and gender. CONCLUSIONS: This study represents the first real-world investigation using ML techniques to predict risk factors associated with imatinib nonadherence in patients with GIST. By highlighting the potential factors and identifying high-risk patients, the multidisciplinary medical team can devise targeted strategies to effectively address the daily challenges of treatment adherence.

The synergy of the XPO1 inhibitors combined with the BET inhibitor INCB057643 in high-grade B-cell lymphoma via downregulation of MYC expression.

High grade B-cell lymphoma with MYC and BCL2 rearrangements (HGBCL-DH) represents an uncommon B-cell lymphoma (BCL) with aggressive clinical courses and poor prognosis. Despite revolutionary therapeutic advances in BCL, there has been limited treatment progress in HGBCL-DH, thus necessitating additional therapeutic strategies for HGBCL-DH. This study demonstrated that the BET antagonist INCB057643 synergized with the XPO1 inhibitors (selinexor and eltanexor) to decrease cell viability and increase cell apoptosis in HGBCL-DH cells with or without TP53 mutations. As anticipated, the combined treatment of INCB057643 with selinexor slowed tumor growth and reduced the tumor burden in TP53-mutated HGBCL-DH xenografts. Mechanistically, MYC functional inhibition was a potential molecular mechanism underlying the synergy of the combined INCB057643 and selinexor treatment in HGBCL-DH cells independent of TP53 mutation status. In TP53 mutated HGBCL-DH cells, inducing DNA damage and impairing the DNA damage response (DDR) were involved in the therapeutic interaction of the combined regimen. In TP53 wild-type cells, the molecular mechanism was linked with upregulation of p53 levels and activation of its targeted pathways, rather than dysregulation of the DDR. Collectively, we might provide a potential promising combination therapy regimen for the management of HGBCL-DH. Clinical evaluations are warranted to confirm this conclusion.

CD4 T cells in chronic myeloid leukemia present MHC class II-dependent and IFN-γ-dependent cytotoxic capacity.

At present, many therapeutic schemes have been used to improve the prognosis of patients with chronic myeloid leukemia (CML), but response remains poor in a small group of patients. CD4 T cell-mediated cytotoxicity has been found in various autoimmune diseases. This study analyzed the characteristics of CD4 T cell mediated cytotoxicity in CML patients and healthy people. The cytotoxicity of CD4 T cells was tested in using two CML cell lines, including the MHC class II-deficient K562 cells and the MHC class II-expressing KU812 cells. CD4 T cell-mediated lysis was minimal in K562 cells but was much higher in KU812 cells. In CML patients, the level of CD4 T cell-mediated lysis was limited to a certain level. Interestingly, pre-treating KU812 cells with IFN-γ could significantly elevate the expression of MHC class II and elevate the level of CD4 T cell-mediated lysis. Overall, these data indicated CD4 T cells could become a potential candidate for cytotoxic elimination of CML cells.

Immunomodulatory mechanism of a purified polysaccharide isolated from Isaria cicadae Miquel on RAW264.7 cells via activating TLR4-MAPK-NF-κB signaling pathway.

The immunomodulatory effect of a novel purified polysaccharide (JCH-1) isolated from Isaria cicadae Miquel had been confirmed to promote secretion of nitric oxide (NO), tumor necrosis factor-alpha (TNF-α) and interleukin 6 (IL-6) in our previous study. However, the immunomodulatory mechanism was still unclear. The purpose of this study was to investigate the immunomodulatory mechanism of JCH-1. Experimental data showed that JCH-1 could increase protein expression of toll-like receptor 4 (TLR4), promote the phosphorylation of mitogen-activated protein kinase (MAPK), as well as nuclear factor-kappa B (NF-κB) p65. Importantly, TLR4 inhibitor inhibited JCH-1-induced activation of MAPK-NF-κB signaling pathway, thus suppressed JCH-1-induced secretion of NO, TNF-α and IL-6. Collectively, these results indicated that JCH-1 actives RAW264.7 cells through TLR4-MAPK-NF-κB signaling pathway.