Search

Abstract Background Obstructive sleep apnea hypopnea syndrome (OSAHS) is a common disease that can cause multiple organ damage in the whole body. Our aim was to use machine learning (ML) to build an independent polysomnography (PSG) model to analyze risk factors and predict OSAHS. Materials and methods Clinical data of 2064 snoring patients who underwent physical examination in the Health Management Center of the First Affiliated Hospital of Shanxi Medical University from July 2018 to July 2023 were retrospectively collected, involving 24 characteristic variables. Then they were randomly divided into training group and verification group according to the ratio of 7:3. By analyzing the importance of these features, it was concluded that LDL-C, Cr, common carotid artery plaque, A1c and BMI made major contributions to OSAHS. Moreover, five kinds of machine learning algorithm models such as logistic regression, support vector machine, Boosting, Random Forest and MLP were further established, and cross validation was used to adjust the model hyperparameters to determine the final prediction model. We compared the accuracy, Precision, Recall rate, F1-score and AUC indexes of the model, and finally obtained that MLP was the optimal model with an accuracy of 85.80%, Precision of 0.89, Recall of 0.75, F1-score of 0.82, and AUC of 0.938. Conclusion We established the risk prediction model of OSAHS using ML method, and proved that the MLP model performed best among the five ML models. This predictive model helps to identify patients with OSAHS and provide early, personalized diagnosis and treatment options.

Abstract Head neck squamous cell carcinoma (HNSCC) is one of the most common malignant tumors which ranks the sixth incidence in the world. Although treatments for HNSCC have improved significantly in recent years, its recurrence rate and mortality rate remain high. Myosin genes have been studied in a variety of tumors, however its role in HNSCC has not been elucidated. GSE58911 and GSE30784 gene expression profile analysis were performed to detect significantly dys-regulated myosin genes in HNSCC. The Cancer Genome Atlas (TCGA) HNSCC database was used to verify the dys-regulated myosin genes and study the relationship between these genes and prognosis in HNSCC. The results showed that MYL1, MYL2, MYL3, MYH2, and MYH7 were down-regulated, while MYH10 was up-regulated in patients with HNSCC. Interestingly, MYL1, MYL2, MYH1, MYH2, and MYH7 were shown to be unfavorable prognostic markers in HNSCC. It is also worth noting that MYL1 was a specific unfavorable prognostic biomarker in HNSCC. MYL1, MYL2, MYL3, MYH2, MYH7, and MYH10 promoted CD4 + T cells activation in HNSCC. MYL1 was proved to be down-regulated in HNSCC tissues compared to normal tissues at protein levels. MYL1 overexpression had no effect on proliferation, but significantly promoted migration of Fadu cells. MYL1 increased EGF and EGFR protein expression levels. Moreover, there is a positive correlation between MYL1 expression and Tcm CD8 cells, Tcm CD4 + cells, NK cells, Mast cells, NKT cells, Tfh cells and Treg cells in HNSCC. Overall, MYL1 facilitates tumor metastasis and correlates with tumor immune infiltration in HNSCC and these effects may be associated with the EGF/EGFR pathway.

BackgroundHypopharyngeal squamous cell cancer (HSCC) is one of the most malignant tumors of the head and neck. It is not easy to detect in the early stage due to its hidden location; thus, lymph node metastasis is highly likely at diagnosis, leading to a poor prognosis. It is believed that epigenetic modification is related to cancer invasion and metastasis. However, the role of m6A-related lncRNA in the tumor microenvironment (TME) of HSCC remains unclear.MethodsThe whole transcriptome and methylation sequencing of 5 pairs of HSCC tissues and adjacent tissues were performed to identify the methylation and transcriptome profiles of lncRNAs. The biological significance of lncRNAs differentially expressing the m6A peak was analyzed by Gene Ontology and Kyoto Encyclopedia of Genes and Genomes. By constructing an m6A lncRNA-microRNA network, the mechanism of m6A lncRNAs in HSCC was analyzed. The relative expression levels of selected lncRNAs were examined by quantitative polymerase chain reaction. The CIBERSORT algorithm was used to evaluate the relative proportion of immune cell infiltration in HSCC and paracancerous tissues.ResultsBased on an in-depth analysis of the sequencing results, 14413 differentially expressed lncRNAs were revealed, including 7329 up-regulated and 7084 down-regulated lncRNAs. Additionally, 4542 up-methylated and 2253 down-methylated lncRNAs were detected. We demonstrated methylation patterns and gene expression profiles of lncRNAs of HSCC transcriptome. In the intersection analysis of lncRNAs and methylated lncRNAs, 51 lncRNAs with up-regulated transcriptome and methylation and 40 lncRNAs with down-regulated transcriptome and methylation were screened, and significantly differentiated lncRNAs were further studied. In the immune cell infiltration analysis, B cell memory was significantly elevated in cancer tissue, while γδT cell amount was significantly decreased.Conclusionm6A modification of lncRNAs might be involved in HSCC pathogenesis. Infiltration of immune cells in HSCC might provide a new direction for its treatment. This study provides new insights for exploring the possible HSCC pathogenesis and searching for new potential therapeutic targets.

IGF2BPs belongs to a family of conserved RNA-bound oncoembryonic proteins that play a crucial part in various aspects of cell function, such as cell migration, morphology, metabolism, proliferation and differentiation. Recent studies have shown that IGF2BPs play a role as a member of m6A reader. m6A is the most abundant modification in RNA epigenetics, which is closely related to a family of RNA-binding proteins. These proteins are fell into three categories—writers, readers and erasers. In the present study, IGF2BPs play an important role in tumor metabolism, especially in head and neck squamous cell carcinoma (HNSCC) metabolism. In this paper, the basic structure of IGF2BPs, its role in the development of HNSCC, molecular mechanism, research progress and research prospect of IGF2BPs in HNSCC are reviewed, which will providing new ideas for further study of IGF2BPs.

Background: Thyroid hormones have been shown to regulate breast cancer cells growth, the absence or reduction of thyroid hormones in cells could provoke a proliferation arrest in G0-G1 or weak mitochondrial activity, which makes cells insensitive to therapies for cancers through transforming into low metabolism status. This biological phenomenon may help explain why treatment efficacy and prognosis vary among breast cancer patients having hypothyroid, hyperthyroid and normal function. Nevertheless, the abnormal thyroid function in breast cancer patients has been considered being mainly caused by thyroid diseases, few studied influence of chemotherapy on thyroid function and whether its alteration during chemotherapy can influence the respose to chemotherapy is still unclear. So, we aimed to find the alterations of thyroid function and non-thyroidal illness syndrome (NTIS) prevalence druing chemotherapy in breast cancer patients, and investigate the influence of thyroid hormones on chemotherapeutic efficacy.Methods: Thyroid hormones and NTIS prevalence at initial diagnosis and during chemotherapy were analyzed in 685 breast diseases patients (369 breast cancer, 316 breast benign lesions). The influence of thyroid hormones on chemotherapeutic efficacy was evaluated by chemosensitization test, to compare chemotherapeutic efficacy between breast cancer cells with chemotherapeutics plus triiodothyronine (T3) and chemotherapeutics only.Results: In breast cancer, NTIS prevalence at the initial diagnosis was higher and increased during chemotherapy, but declined before the next chemotherapeutic course. Thyroid hormones decreased signigicantly during chemotherapy. T3 can enhance the chemosensitivity of MCF-7 to 5-Fu and taxol, with progression from G0-G1 phase to S phase. The similar chemosensitization role of T3 were found in MDA-MB-231. We compared chemotherapeutic efficacy among groups with different usage modes of T3, finding pretreatment with lower dose of T3, using higher dose of T3 together with 5-Fu or during chemotherapy with 5-Fu were all available to achieve chemosensitization, but pretreatment with lower dose of T3 until the end of chemotherapy may be a safer and more efficient therapy.Conclusions: Taken together, thyroid hormones decreasing during chemotherapy was found in lots of breast cancer patients. On the other hand, thyroid hormones can enhance the chemotherapeutic efficacy through gatherring tumor cells in actively proliferating stage, which may provide a new adjuvant therapy for breast cancer in furture, especially for those have hypothyroidism during chemotherapy. [ABSTRACT FROM AUTHOR]