A Gene-Related Nomogram for Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer

Metastasis-Related Signature for Clinically Predicting Prognosis and Tumor Immune Microenvironment of Osteosarcoma Patients

Osteosarcoma is the most prevalent clinical malignant bone tumor in adolescents. The prognosis of metastatic osteosarcoma is still very poor. The aim of our study was to investigate the clinical diagnosis and prognostic significance of metastasis related genes (MRGs) in patients with osteosarcoma. Clinical information and RNA sequencing data with osteosarcoma patients were obtained and set as the training set from UCSC databases. GSE21257 were downloaded and chosen as the verification cohort. An eight gene metastasis related risk signature including MYC, TAC4, ABCA4, GADD45GIP1, TNFRSF21, HERC5, MAGEA11, and PDE1B was built to predict the overall survival of osteosarcoma patients. Based on risk assessments, patients were classified into high- and low-risk groups. The high-risk patients had higher risk score and shorter survival time. ROC curves revealed that this risk signature can accurately predict survival times of osteosarcoma patients at the 1-, 2-, 3-, 4- and 5- year. GSEA revealed that MYC targets, E2F targets, mTORC1 signaling, Wnt /β-catenin signaling and cell cycle were upregulated, and cell adhesion molecules, and primary immunodeficiency were decreased in high-risk group. MRGs were highly linked with the tumor immune microenvironment and ICB response. These results identified that MRGs as a novel prognostic and diagnostic biomarker in osteosarcoma.

Probabilistic ratiocination of hepatocellular carcinoma after resection: evaluation of expected to be promising approaches

Background

Precise prediction of survival after treatment is of great importance for patients with diseases with high mortality. RNA sequencing data and deep learning (DL) methods are expected to become promising approaches in the development of prediction models in the future. We aimed to evaluate the optimal covariates and methodology for patients with hepatocellular carcinoma (HCC) undergoing surgical resection.

Methods

The Cox proportional hazards regression model and the DL approach were used to develop prediction models incorporating clinical, genetic, and combined clinical and genetic variables for survival prediction in patients with HCC after resection. A total of 1,114 patients and 184 patients were enrolled in the present study from 2,163 and 601 patients from Eastern Hepatobiliary Surgery Hospital and Renji Hospital, respectively. The models were internally validated through random sampling and externally validated in clinical cohorts. Between-model comparisons were carried out in terms of the integrated discrimination improvement and net reclassification index.

Results

The Cox and DL clinical models were developed by adopting 7 independent prognostic factors (total bilirubin, prothrombin time, tumor size, tumor number, lymph node metastasis, and vascular invasion) and 22 clinical factors, respectively. Both the Cox clinical model and the DL clinical model showed excellent performances in the derivation [area under the curve (AUC): 0.75 vs. 0.77] and validation (AUC: 0.83 vs. 0.80) sets. The derived Cox genetic model with 6 significant prognostic genes was not as effective as the DL approach involving 686 genes. A combined clinical and genetic approach modified the performances of both the Cox and DL models. The integrated discrimination improvement and net reclassification index of the DL clinical model were generally better than those of the Cox clinical model.

Conclusions

Our Cox clinical model sufficiently provided precise survival prediction in patients with HCC after resection. It may serve as an accurate and cost-effective tool for predicting survival in such patients.

Development and validation of a collagen signature-based nomogram for preoperatively predicting lymph node metastasis and prognosis in colorectal cancer

Background

Current preoperative evaluation approaches cannot provide adequate information for the prediction of lymph node (LN) metastasis in colorectal cancer (CRC). Collagen alterations in the tumor microenvironment affect the progression of tumor cells. To more accurately assess the LN status of CRC preoperatively, we developed and validated a collagen signature-based nomogram for predicting LN metastasis in CRC.

Methods

In total, 342 consecutive CRC patients were assigned to the training and validation cohorts. A total of 148 fully quantitative collagen features were extracted based on preoperative biopsies using multiphoton imaging, and the least absolute shrinkage and selection operator method was utilized to construct the collagen signature. A collagen signature-based nomogram was developed by multivariable logistic regression in the training cohort. Nomogram performance was evaluated for its discrimination, calibration, and clinical usefulness and then validated in the validation cohort. The prognostic values of the nomogram were also evaluated.

Results

A seven-feature-based collagen signature was built. We found that the collagen signature showed a significant association with LN metastasis in CRC. Additionally, a nomogram incorporating preoperative tumor differentiation, computed tomography-reported T stage and LN status, carcinoembryonic antigen level, carbohydrate antigen 19-9 level and collagen signature was developed. This nomogram had good discrimination and calibration, with AUROCs of 0.826 and 0.846 in the training and validation cohorts, respectively, and had a sensitivity of 86.5%, a specificity of 68.2%, an accuracy of 76.9%, a negative predictive value of 84.9%, and a positive predictive value of 71.2% for all patients. Compared to the clinicopathological model, which consisted of the clinicopathological risk factors for LN metastasis, the collagen signature-based nomogram demonstrated a significantly improved ability to discriminate LN status. Moreover, a nomogram-predicted high-risk subgroup had remarkably reduced survival compared with that of the low-risk subgroup.

Conclusions

The collagen signature in the tumor microenvironment of preoperative biopsies is an independent predictor for LN metastasis in CRC, and the collagen signature-based nomogram is helpful for tailored treatment and prognostic predictions in CRC preoperatively.

A deep learning nomogram kit for predicting metastatic lymph nodes in rectal cancer

Background

Preoperative diagnoses of metastatic lymph nodes (LNs) by the most advanced deep learning technology of Faster Region‐based Convolutional Neural Network (Faster R‐CNN) have not yet been reported.

Materials and Methods

In total, 545 patients with pathologically confirmed rectal cancer between January 2016 and March 2019 were included and were randomly allocated with a split ratio of 2:1 to the training and validation sets, respectively. The MRI images for metastatic LNs were evaluated by Faster R‐CNN. Multivariate regression analyses were used to develop the predictive models. Faster R‐CNN nomograms were constructed based on the multivariate analyses in the training sets and were validated in the validation sets.

Results

The Faster R‐CNN nomogram for predicting metastatic LN status contained predictors of age, metastatic LNs by Faster R‐CNN and differentiation degrees of tumors, with areas under the curves (AUCs) of 0.862 (95% CI: 0.816‐0.909) and 0.920 (95% CI: 0.876‐0.964) in the training and validation sets, respectively. The Faster R‐CNN nomogram for predicting LN metastasis degree contained predictors of metastatic LNs by Faster R‐CNN and differentiation degrees of tumors, with AUCs of 0.859 (95% CI: 0.804‐0.913) and 0.886 (95% CI: 0.822‐0.950) in the training and validation sets, respectively. Calibration plots and decision curve analyses demonstrated good calibrations and clinical utilities. The two nomograms were used jointly as a kit for predicting metastatic LNs.

Conclusion

The Faster R‐CNN nomogram kit exhibits excellent performance in discrimination, calibration, and clinical utility and is convenient and reliable for predicting metastatic LNs preoperatively.

Clinical trial registration: ChiCTR‐DDD‐17013842.

A prognostic nomogram for neuroblastoma in children

Introduction

Neuroblastoma is one of the most common extracranial solid tumors in children, which accounts for about 7-10% in children's tumors. The prognosis group of patients with neuroblastoma could not only improve the efficacy of high-risk patients, but also reduce the effects of drug complications for surviving patients.

Material and Methods

Patients diagnosed with neuroblastoma between 1986 and 2012 were selected form the TARGET database. The nomogram was built with potential risk factors based on COX regression analysis. The precision of the 3-year and 5-year survival of the nomograms was evaluated by the area under receiver operating characteristic (ROC) curve (AUC).

Results

A total of 757 child neuroblastoma patients were selected from the TARGET database. Univariate analysis showed that age of diagnosis (>520 day), race of American Indian or Alaska Native, stage 4 in International Neuroblastoma Staging System (INSS), MYCN status, DNA ploidy, and high mitosis-karyorrhexis index were associated with overall survival (OS). Multivariate analysis showed age of diagnosis (>520 day), stage 4 in INSS and DNA ploidy were independent risk factors of OS. The concordance index (C-index) of the nomogram was 0.704 (95% CI [0.686-0.722]) in the training cohort while the C-index in the validation cohort was 0.672 (95% CI [0.644-0.700]). AUC values of ROC curves for 3-year OS and 5-year OS in the training cohort were 0.732 and 0.772, respectively. The nomogram performed better compared with INSS staging system, tumor histology and children's oncology group (COG) risk group with C-indexes of 0.662 (95% CI [0.648-0.676]), 0.637 (95% CI [0.622-0.652]) and 0.651 (95% CI [0.637-0.665]), respectively.

Conclusions

The nomogram showed stronger predictive power than the INSS staging system, tumor histology and COG risk group. Precise estimates of the prognosis of childhood neuroblastoma might help doctors make better treatment decisions.