1.Performance of multi-modality and multi-classifier fusion models for predicting radiation-induced oral mucositis in patients with nasopharyngeal carcinoma.
Yue HU ; Yu ZENG ; Linjing WANG ; Zhiwei LIAO ; Jianming TAN ; Yanhao KUANG ; Pan GONG ; Bin QI ; Xin ZHEN
Journal of Southern Medical University 2024;44(12):2434-2442
OBJECTIVES:
To evaluate the performance of different multi-modality fusion models for predicting radiation-induced oral mucositis (RIOM) following radiotherapy in patients with nasopharyngeal carcinoma (NPC).
METHODS:
We retrospectively collected the data from 198 patients with locally advanced NPC who experienced RIOM following radiotherapy at the Affiliated Tumor Hospital of Guangzhou Medical University from September, 2022 to February, 2023. Based on oral radiation dose-volume parameters and clinical features of NPC, basic classification models were developed using different combinations of feature selection algorithms and classifiers and integrated using a multi-criterion decision-making (MCDM)-based classifier fusion (MCF) strategy and its variant, the H-MCF model. The basic classification models, MCF model, the H-MCF model with a single modality or multiple modalities and other ensemble classifiers were compared for performances for predicting RIOM by assessing the area under the ROC curve (AUC), accuracy, sensitivity, and specificity.
RESULTS:
The H-MCF model, which integrated multi-modality features, achieved the highest accuracy for predicting severe RIOM with an AUC of 0.883, accuracy of 0.850, sensitivity of 0.933, and specificity of 0.800.
CONCLUSIONS
Compared with each of the individual classifiers, the multimodal multi-classifier fusion algorithm combining clinical and dosimetric modalities demonstrates superior performance in predicting the incidence of severe RIOM in NPC patients following radiotherapy.
Humans
;
Nasopharyngeal Carcinoma/radiotherapy*
;
Nasopharyngeal Neoplasms/radiotherapy*
;
Retrospective Studies
;
Stomatitis/diagnosis*
;
Algorithms
;
Radiation Injuries/diagnosis*
;
Female
;
Male
;
ROC Curve
2.Biejiajian Wan Regulates Polarization of Macrophages via HIF-1α/NF-κB Signaling Pathway
Yang LIU ; Chunyu HE ; Tong LI ; Weiguang CHEN ; Yanhao MA ; Ying KUANG ; Songqi HE ; Haitao SUN
Chinese Journal of Experimental Traditional Medical Formulae 2022;28(19):9-16
ObjectiveTo investigate the effect and mechanism of Biejiajian Wan on liver fibrosis by regulating the polarization of macrophages. MethodRaw264.7 cells were cultured in vitro by serum pharmacological method, and the hypoxia model of RAW264.7 cells was established by stimulating RAW264.7 cells with cobalt chloride (CoCl2). The cells were randomly divided into blank group, CoCl2 hypoxia model group (200 mmol·L-1), Biejiajian Wan low-dose group (200 mmol·L-1+0.55 g·kg-1 Fuzheng Quyu capsules), medium-dose group (200 mmol·L-1+1.1 g·kg-1 Biejiajian Wan), and high-dose group (200 mmol·L-1+2.2 g·kg-1 Biejiajian Wan) and Fuzheng Quyu capsule group (200 mmol·L-1+0.56 g·kg-1 Biejiajian Wan). Cell proliferation was detected by cell counting kit-8 (CCK-8), and the gene expression of hypoxia inducible factor-1α (HIF-1α), interleukin-1β (IL-1β) and interleukin-6 (IL-6) in macrophages was detected by real time fluorescence quantitative polymerase chain reaction (Real-time PCR). The expression of macrophage polarization-related protein and HIF-1α/nuclear factor-kappa B (NF-κB) signaling pathway-related protein was tested by Western blot, and the distribution and expression of NF-κB signaling pathway-related protein and HIF-1α were determined by cell immunofluorescence. ResultCompared with the conditions in the blank group, the proliferation of RAW264.7 cells was inhibited after CoCl2 stimulation for 24 hours (P<0.05), the mRNA expression of HIF-1α, IL-1β and IL-6 in the model group were increased (P<0.05), the protein expression of HIF-1α and M1 macrophage phenotypic proteins IL-6 and tumor necrosis factor-α (TNF-α) was boosted while that of M2 macrophage phenotypic protein interleukin-10 (IL-10) was reduced (P<0.05), the protein expression of NF-κB p65, phosphorylation (p)-NF-κB p65, phosphorylated NF-κB inhibits protein kinase α/β (p-IKKα/β) and phosphorylated NF-κB inhibits protein α (p-IκBα) was elevated (P<0.05), the nuclear expression of HIF-1α and NF-κB p65 was promoted. Compared with the conditions in the model group, after 24 hours of treatment with corresponding drug-containing serum, each treatment group promoted the proliferation of RAW264.7 cells (P<0.05), the mRNA expression levels of HIF-1α, IL-1β and IL-6 in macrophages were reduced (P<0.05), the protein expression of HIF-1α, IL-6 and TNF-α was decreased, while that of CD163 and IL-10 was increased (P<0.05), the protein expression of NF-κB p65, p-NF-κB p65, p-IKKα/β and p-IκBα was lowered (P<0.05), the nuclear expression of HIF-1α and NF-κB p65 was inhibited. ConclusionBiejiajian Wan could modulate the polarization of macrophages, attenuate the injury of macrophage-associated inflammatory response under hypoxia, and thus delay the progression of liver fibrosis, which might be related to its regulation of HIF-1α/NF-κB signaling pathway.

Result Analysis
Print
Save
E-mail