Machine learning methods predict recurrence of pN3b gastric cancer after radical resection.

Background: The incidence of stage pN3b gastric cancer (GC) is low, and the clinical prognosis is poor, with a high rate of postoperative recurrence. Machine learning (ML) methods can predict the recurrence of GC after surgery. However, the prognostic significance for pN3b remains unclear. Therefore, we aimed to predict the recurrence of pN3b through ML models. Methods: This retrospective study included 336 patients with pN3b GC who underwent radical surgery. A 3-fold cross-validation was used to partition the participants into training and test cohorts. Linear combinations of new variable features were constructed using principal component analysis (PCA). Various ML algorithms, including random forest, support vector machine (SVM), logistic regression, multilayer perceptron (MLP), extreme gradient boosting (XGBoost), and Gaussian naive Bayes (GNB), were utilized to establish a recurrence prediction model. Model performance was evaluated using the receiver operating characteristic (ROC) curve and the area under the curve (AUC). Python was used for the analysis of ML algorithms. Results: Nine principal components with a cumulative variance interpretation rate of 90.71% were identified. The output results of the test set showed that random forests had the highest AUC (0.927) for predicting overall recurrence with an accuracy rate of 80.5%. Random forests had the highest AUC (0.940) for predicting regional recurrence with an accuracy of 89.7%. For predicting distant recurrence, random forests had the highest AUC (0.896) with an accuracy of 84.3%. For peritoneal recurrence, random forests had the highest AUC (0.923) with an accuracy of 83.3%. Conclusions: ML can personalize the prediction of postoperative recurrence in patients with GC with stage pN3b.

Development and validation of the novel subclassification of pN3 for patients with esophageal cancer.

Background: Patients with stage pN3 esophageal cancer (EC) have a large number of metastatic lymph nodes (mLNs) and have poor prognosis. This study was to elucidate whether subclassification of pN3 according to the number of mLNs could improve the discrimination ability of EC patients. Methods: This study retrospectively analyzed patients with pN3 EC from the Surveillance, Epidemiology, and End Results (SEER) database as a training cohort and SEER validation cohort. Patients with pN3 esophageal cancer from the Affiliated Cancer Hospital of Harbin Medical University were used as the validation cohort. The optimal cutoff value of mLNs was identified using the X-tile software, and group pN3 into pN3-I and pN3-II based on mLNs. Kaplan-Meier method and log-rank test were used to analyze the disease-specific survival (DSS). The Cox proportional hazards regression analysis was used to identify the independent prognostic factors. Results: For the training cohort, patients with 7 to 9 mLNs were categorized as pN3-I, while those with more than 9 mLNs were categorized as pN3-II. There were 183 (53.8%) pN3-I and 157 (46.2%) pN3-II. The 5-year DSS rates of pN3-I and pN3-II in the training cohort were 11.7% and 5.2% (P=0.033), and the pN3 subclassification was an independent risk factor associated with patient prognosis. More RLNs may not improve patient prognosis, but the use of mLNs/RLNs is effective in predicting patient prognosis. Furthermore, the pN3 subclassification was well validated in the validation cohort. Conclusion: Subclassification of pN3 can better distinguish survival differences in EC patients.

Nomogram Based on Preoperative Fibrinogen and Systemic Immune-Inflammation Index Predicting Recurrence and Prognosis of Patients with Borrmann Type III Advanced Gastric Cancer.

Background and Objectives: The prognosis is known to differ significantly among advanced gastric cancer (AGC) with Borrmann type III. This study aimed to evaluate the prognosis of these patients more individually. Methods: We selected 542 AGC patients with Borrmann type III. We used the receiver operating characteristic curve to analyze the cutoff values of inflammation indexes, and used Kaplan-Meier and Log rank tests to analyze recurrence-free survival (RFS) and overall survival (OS). The independent risk factors for recurrence and prognosis were analyzed by Cox proportional hazards regression model. The nomogram models were constructed by R studio. Results: Patients with high preoperative fibrinogen (F) and systemic immune-inflammation index (SII) levels had worse RFS and OS and higher risk of postoperative locoregional recurrence, hematogenous metastasis and lymph node metastasis. F and SII can combine with different clinicopathological features (all P<0.05) to construct nomograms to predict 5-year recurrence and prognosis, which both were superior to pTNM stage alone. Conclusion: The nomogram models based on F and SII can evaluate AGC with Borrmann type III postoperative recurrence and prognosis.

Improvement of ACK1-targeted therapy efficacy in lung adenocarcinoma using chloroquine or bafilomycin A1.

BACKGROUND: Activated Cdc42-associated kinase 1 (ACK1) is a promising druggable target for cancer, but its inhibitors only showed moderate effects in clinical trials. The study aimed to investigate the underlying mechanisms and improve the antitumor efficacy of ACK1 inhibitors. METHODS: RNA-seq was performed to determine the downstream pathways of ACK. Using Lasso Cox regression analysis, we built a risk signature with ACK1-related autophagy genes in the lung adenocarcinoma (LUAD) patients from The Cancer Genome Atlas (TCGA) project. The performance of the signature in predicting the tumor immune environment and response to immunotherapy and chemotherapy were assessed in LUAD. CCK8, mRFP-GFP-LC3 assay, western blot, colony formation, wound healing, and transwell migration assays were conducted to evaluate the effects of the ACK1 inhibitor on lung cancer cells. A subcutaneous NSCLC xenograft model was used for in vivo study. RESULTS: RNA-seq revealed the regulatory role of ACK1 in autophagy. Furthermore, the risk signature separated LUAD patients into low- and high-risk groups with significantly different prognoses. The two groups displayed different tumor immune environments regarding 28 immune cell subsets. The low-risk groups showed high immune scores, high CTLA4 expression levels, high immunophenoscore, and low DNA mismatch repair capacity, suggesting a better response to immunotherapy. This signature also predicted sensitivity to commonly used chemotherapy and targeted drugs. In vitro, the ACK1 inhibitors (AIM-100 and Dasatinib) appeared to trigger adaptive autophagy-like response to protect lung cancer cells from apoptosis and activated the AMPK/mTOR signaling pathway, partially explaining its moderate antitumor efficacy. However, blocking lysosomal degradation with chloroquine/Bafilamycine A1 or inhibiting AMPK signaling with compound C/shPRKAA1 enhanced the ACK1 inhibitor's cytotoxic effects on lung cancer cells. The efficacy of the combined therapy was also verified using a mouse xenograft model. CONCLUSIONS: The resulting signature from ACK1-related autophagy genes robustly predicted survival and drug sensitivity in LUAD. The lysosomal degradation inhibition improved the therapeutic effects of the ACK1 inhibitor, suggesting a potential role for autophagy in therapy evasion.

Prognostic Value of Combination of Controlling Nutritional Status and Tumor Marker in Patients with Radical Non-Small-Cell Lung Cancer.

Background: Controlling nutritional status (CONUT) and tumor markers are associated with prognosis in patients with non-small-cell lung cancer (NSCLC). This study is aimed at exploring the potential usefulness of T-CONUT, constructed by combining CONUT and tumor markers, for NSCLC patients undergoing radical surgery. Methods: A total of 483 patients with NSCLC underwent radical surgical resection. The receiver characteristic operating curve (ROC) was used to select the tumor marker with the highest predictive performance, and CONUT was combined with this marker to construct the T-CONUT. The Kaplan-Meier method and log-rank test were used to analyze the overall survival (OS), and chi-square analysis was used to analyze the association between T-CONUT and clinicopathological characteristics. The independent risk factors were analyzed by Cox regression. A nomogram was constructed by R studio. Calibration plots, the c-index, and decision curves were evaluated for the performance of the nomogram. Results: ROC analysis showed that the predictive performance of CYFRA21-1 was better than that of CEA, NSE, and SCC. CYFRA21-1 was selected for combining with CONUT to construct T-CONUT. Elevated T-CONUT indicates poor prognosis of patients. Histological type, pTNM, and T-CONUT are independent risk factors associated with patient prognosis. The areas under the curve of the nomogram for predicting 3- and 5-year OS were 0.760 and 0.761, respectively. Conclusion: T-CONUT comprising CYFRA21-1 and CONUT can effectively predict the prognosis of NSCLC patients.

Prediction of prognosis and immunotherapy response with a robust immune-related lncRNA pair signature in lung adenocarcinoma.

The tumor immune microenvironment plays essential roles in regulating inflammation, angiogenesis, immune modulation, and sensitivity to therapies. Here, we developed a powerful prognostic signature with immune-related lncRNAs (irlncRNAs) in lung adenocarcinoma (LUAD). We obtained differentially expressed irlncRNAs by intersecting the transcriptome dataset for The Cancer Genome Atlas (TCGA)-LUAD cohort and the ImmLnc database. A rank-based algorithm was applied to select top-ranking altered irlncRNA pairs for the model construction. We built a prognostic signature of 33 irlncRNA pairs comprising 40 unique irlncRNAs in the TCGA-LUAD cohort (training set). The immune signature significantly dichotomized LUAD patients into high- and low-risk groups regarding overall survival, which is likewise independently predictive of prognosis (hazard ratio = 3.580, 95% confidence interval = 2.451-5.229, P < 0.001). A nomogram with a C-index of 0.79 demonstrates the superior prognostic accuracy of the signature. The prognostic accuracy of the signature of 33 irlncRNA pairs was validated using the GSE31210 dataset (validation set) from the Gene Expression Omnibus database. Immune cell infiltration was calculated using ESTIMATE, CIBERSORT, and MCP-count methodologies. The low-risk group exhibited high immune cell infiltration, high mutation burden, high expression of CTLA4 and human leukocyte antigen genes, and low expression of mismatch repair genes, which predicted response to immunotherapy. Interestingly, pRRophetic analysis demonstrated that the high-risk group possessed reverse characteristics was sensitive to chemotherapy. The established immune signature shows marked clinical and translational potential for predicting prognosis, tumor immunogenicity, and therapeutic response in LUAD.

Development of immune gene pair-based signature predictive of prognosis and immunotherapy in esophageal cancer.

BACKGROUND: Esophageal cancer (EC) is one of the deadliest solid malignancies, mainly consisting of esophageal squamous cell carcinoma (ESCC) and adenocarcinoma (EAC). Robust biomarkers that can improve patient risk stratification are needed to optimize cancer management. We sought to establish potent prognostic signatures with immune-related gene (IRG) pairs for ESCC and EAC. METHODS: We obtained differentially expressed IRGs by intersecting the Immunology Database and Analysis Portal (ImmPort) with the transcriptome data set of The Cancer Genome Atlas (TCGA)-ESCC and EAC cohorts. A novel rank-based pairwise comparison algorithm was applied to select effective IRG pairs (IRGPs), followed by constructing a prognostic IRGP signature via the least absolute shrinkage and selection operator (LASSO) regression model. We assessed the predictive power of the IRGP signatures on prognosis, tumor-infiltrating immune cells, and immune checkpoint inhibitor (ICI) efficacy in EC. Kaplan-Meier survival analysis and receiver operating characteristic curves (ROC) were used to evaluate the clinical significance of IRGPs. Univariate and multivariate Cox regression analyses were performed to investigate the association of overall survival (OS) with IRGPs and clinical characteristics. RESULTS: We built a 19-IRGP signature for ESCC (n=75) and a 17-IRGP signature for EAC (n=78), with an area under the ROC curve (AUC) of 0.931 and 0.803, respectively. IRGP signature-derived risk scores stratified patients into low- and high-risk groups with significantly different OS in ESCC and EAC (P<0.001). Nomogram and decision curve analysis were used to evaluate the clinical relevance of the prognostic signatures, achieving a C-index of 0.973 in ESCC and 0.880 in EAC. The risk scores were associated with immune and ESTIMATE (Estimation of STromal and Immune cells in MAlignant Tumor tissues using Expression data) scores and the composition of immune cells in the tumor microenvironment. The association between risk score and human leukocyte antigens (HLAs), mismatch repair (MMR) genes, and immune checkpoint molecules demonstrated its predictive value for ICI response. Differential immune characteristics and predictive value of the risk score were observed in EAC. CONCLUSIONS: The established immune signatures showed great promise in predicting prognosis, tumor immunogenicity, and immunotherapy response in ESCC and EAC.

Integrated analysis of immune infiltration in esophageal carcinoma as prognostic biomarkers.

BACKGROUND: Esophageal cancer (EC) is one of the most aggressive and lethal malignancies in the world. The quantity and distribution of immune cells are very important factors in determining cancer. Tumor-infiltrating mast cells (TIM) are a class of immune cells with an important immune regulation function for tumor progression. However, tumor-infiltrating immune cells (TIICs) and their role in EC have not yet been investigated. METHODS: The RNA-seq data of an EC cohort were downloaded from The Cancer Genome Atlas (TCGA) website. In this study, we used the Cell-type Identification by Estimating Relative Subsets of RNA Transcripts (CIBERSORT) algorithm to compare different soakage of inflammatory cells in esophageal squamous cell carcinoma (ESCC) and normal tissue. Kaplan-Meier survival analysis was performed on different immune cell subpopulations and overall survival (OS) in 22 human immune cell phenotypes. Immunohistochemistry (IHC) was also carried out using our clinical tissue samples. RESULTS: The proportion of tumor-infiltrating mast cells (TIM) significantly increased at the late of EC and a high percentage of mast cells indicated a poor OS of EC patients in TCGA database. The IHC staining of tryptase revealed that high level of TIM expression was an independent prognostic factor of survival time in the ESCC patients in our database. In addition, TIM accumulation and infiltration of CD8+T cells were shown to be negatively correlated. CONCLUSIONS: This work revealed that TIM are related to prognosis in patients with EC and TIM may be an independent prognostic factor for EC.