Identification of prognostic signatures in remnant gastric cancer through an interpretable risk model based on machine learning: a multicenter cohort study.

OBJECTIVE: The purpose of this study was to develop an individual survival prediction model based on multiple machine learning (ML) algorithms to predict survival probability for remnant gastric cancer (RGC). METHODS: Clinicopathologic data of 286 patients with RGC undergoing operation (radical resection and palliative resection) from a multi-institution database were enrolled and analyzed retrospectively. These individuals were split into training (80%) and test cohort (20%) by using random allocation. Nine commonly used ML methods were employed to construct survival prediction models. Algorithm performance was estimated by analyzing accuracy, precision, recall, F1-score, area under the receiver operating characteristic curve (AUC), confusion matrices, five-fold cross-validation, decision curve analysis (DCA), and calibration curve. The best model was selected through appropriate verification and validation and was suitably explained by the SHapley Additive exPlanations (SHAP) approach. RESULTS: Compared with the traditional methods, the RGC survival prediction models employing ML exhibited good performance. Except for the decision tree model, all other models performed well, with a mean ROC AUC above 0.7. The DCA findings suggest that the developed models have the potential to enhance clinical decision-making processes, thereby improving patient outcomes. The calibration curve reveals that all models except the decision tree model displayed commendable predictive performance. Through CatBoost-based modeling and SHAP analysis, the five-year survival probability is significantly influenced by several factors: the lymph node ratio (LNR), T stage, tumor size, resection margins, perineural invasion, and distant metastasis. CONCLUSIONS: This study established predictive models for survival probability at five years in RGC patients based on ML algorithms which showed high accuracy and applicative value.

[Effect of Human Umbilical Cord-derived Mesenchymal Stem Cells on Proliferation and Differentiation of Leukemia Cells].

OBJECTIVE: To investigate the effect of human umbilical cord-derived mesenchymal stem cells(HUC-MSC) on the proliferation and differentiation of NB4 treated with all-trans retinoid acid (ATRA) and its underlining mechanisms . METHODS: Human umbilical cord mesenchymal stem cells were isolated from umbilical cord of newborns. Co-culture system was established by HUC-MSC and NB4 in vitro. The experiment was divided into 4 groups: NB4 group (NB4 cells alone) , NM group (NB4 cells co-cultured with HUC-MSC) , NA group (NB4 cells treated with ATRA) , NMA group (NB4 cells co-cultured with HUC-MSC and treated with ATRA) . NB4 cells were counted by a microscopy, NB4 proliferation was monitored by CCK-8 assay, NB4 differentiation was assessed by Wright ' s staining and nitroblue tetrazolium reduction test. IL-6 levels in the culture supernatant of different groups were tested by ELISA kit. Quantitative PCR was used to detect the transcription level of CDKN1A, CCND1 and Survivin. RESULTS: NB4 and HUC-MSC in the co-culturing systems were in good condition with a slight repression of NB4 proliferation by HUC-MSC. HUC-MSC could collaborate with ATRA to induce significant NB4 differentiation. Consistent with this finding, IL-6 expression levels of co-cultured groups were remarkably higher than that in any other groups or the group of HUC-MSC alone. The quantitative PCR analysis showed that the levels of CDKN1A and CCND1 mRNA expression were increased or decreased respectively in the co-cultured groups. CONCLUSION: HUC-MSC co-culture can reduce proliferation but promote the differentiation of NB4 cells, suggesting that this effect may be closely related with the secretion of IL-6 which can affect the expression of some factors in vitro.

[Effect of BD Regimen Combined with Cyclophosphamide and Pirarubicin in Treatment of Relapse/Refractory Multiple Myeloma].

OBJECTIVE: To compare the efficacy and safety of BD regimen combined with cyclophosphamide(CTX) and pirarubicin chemotherapy(P-CAD) for patients with relapse/refractory multiple myeloma(MM). METHODS: Twenty-eight cases of relapse/refractory MM were enrolled in a group of P-CAD regimen, 36 cases of relapse/retractory MM treated with BD were used as controls. The therapeutic efficacy and adverse reactions of 2 regimens for patients with relapse/retractory MM were compared and analyzed. RESULTS: The overall response rate (CR+NCR+PR+MR) of the 28 cases treated with P-CAD regimen was 85.7%, and the response rate (CR+PR) was 75.0%. The median progression-free survival time were 16.1 months, and the average survival time were 30.6 months, while the overall response rate of the 36 patients treated with BD regimen was 63.9%, and the response rate was 55.6%. The median progression-free survival time were 13.7 months, and the average survival time were 26.7 months. The adverse reactions of 2 groups included gastrointestinal reactions, peripheral neuropathy, fatigue, skin rashes, leucopenia and thrombocytopenia, and they were all well tolerated. CONCLUSION: BD regimen combined with cyclophosphamide and pirarubicin chemotherapy can improve the response rate of patients with relapse/refractory multiple myeloma, and shows the trend of prolonging PFS and survival times. Patients were well tolerated, and this regimen is a new choice in treatment of relapse/refractory MM.