A nomogram to predict overall survival of patients with early stage non-small cell lung cancer

Discovery and validation of Hsa-microRNA-3665 promoter methylation as a potential biomarker for the prognosis of esophageal squaous cell carcinoma

BACKGROUND

Methylation of microRNA (miRNA) promoters associated with diseases is a common epigenetic mechanism in the development of various human cancers. However, its relationship with prognosis in esophageal squamous cell carcinoma (ESCC) remains unclear. This study aims to explore the association between the methylation level of has-miR-3665 promoter and prognosis in ESCC.

METHODS

Human miRNA data were downloaded from miRbase, and we identified CpG islands of these human miRNAs by genomics browser analysis. MiRNA methylation levels were detected by methylation-specific high-resolution melting. Gene ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were used to explore the molecular mechanism of hsa-miR-3665. Cox regression analysis was used to investigate prognostic factors. The overall survival rate was predicted by a nomogram.

RESULTS

We found that 88 human miRNAs had promoter methylatio, of which 15 miRNAs were found to be epigenetically regulated in ESCC cells compared with their normal counterparts, including hsa-miR-3665. Meanwhile, hsa-miR-3665 expression was significantly lower in ESCC tumour tissue than in adjacent tissue (P = 0.03). GO and KEGG analyses demonstrated that the target genes are involved in protein transport, transcription regulator activity, MAPK and RAS signaling pathway. High hsa-miR-3665 promoter methylation levels were associated with a poor prognosis (HR = 3.89, 95% CI 1.11 ~ 13.55). Moreover, a nomogram incorporating the hsa-miR-3665 methylation level and clinical factors presented a good performance for predicting survival in the training and validation tests, with C-indices of 0.748 and 0.751, respectively.

CONCLUSIONS

High hsa-miR-3665 promoter methylation levels may be a potential biomarker for the progression of ESCC.

Prediction of knee pain improvement over two years for knee osteoarthritis using a dynamic nomogram based on MRI-derived radiomics: a proof-of-concept study

OBJECTIVES

To develop and validate a nomogram to detect improved knee pain in osteoarthritis (OA) by integrating magnetic resonance imaging (MRI) radiomics signature of subchondral bone and clinical characteristics.

METHODS

Participants were selected from the Vitamin D Effects on Osteoarthritis (VIDEO) study. The primary outcome was 20% improvement of knee pain score over 2 years in participants administrated either vitamin D or placebo. Radiomics features of subchondral bone and clinical characteristics from 216 participants were extracted and analyzed. The participants were randomly split into the training and validation cohorts at a ratio of 8:2. Least absolute shrinkage and selection operator (LASSO) regression was used to select features and generate radiomics signatures. The optimal radiomics signature and clinical indicators were fitted into a nomogram using multivariable logistic regression model.

RESULTS

The nomogram showed favorable discrimination performance [AUCtraining, 0.79 (95% CI: 0.72-0.79), AUCvalidation, 0.83 (95% CI: 0.70-0.96)] as well as a good calibration. Additional contributing value of fusion radiomics signature to the nomogram was statistically significant (NRI, 0.23; IDI, 0.14, P < 0.001 in training cohort and NRI, 0.29; IDI, 0.18, P < 0.05 in validating cohort). Decision curve analysis confirmed the clinical usefulness of nomogram.

CONCLUSION

The radiomics-based nomogram comprising the MR radiomics signature and clinical variables achieves a favorable predictive efficacy and accuracy in differentiating improvement in knee pain among OA patients. This proof-of-concept study provides a promising way to predict clinically meaningful outcomes.

Type of lymphadenectomy does not influence survival in pIa NSCLC patients who underwent VATS lobectomy: Results from the national VATS group database

INTRODUCTION

Stage Ia presents an optimal survival rate after surgical resection, but the type of lymphadenectomy to use in these patients is still debated. The aim of this study is evaluate if one type of lymphadenectomy adopted influences survival in patients who underwent VATS lobectomy for stage Ia NSCLC.

METHODS

Clinical and pathological data from pIa patients in the prospective VATS Italian nationwide registry were reviewed and analysed. Patients and tumour characteristics,type of lymphadenectomy (sampling or radical nodal dissection,MRLD), were collected and correlated to Overall Survival(OS) and Disease free Survival(DFS). The Kaplan-Meier product-limit method was used to estimate OS and DFS and the log-rank test was adopted to evaluate the differences between groups. A propensity match was performed to reduce bias due to the retrospective study design.

RESULTS

The final analysis was conducted on 2039 patients, 179 died during follow-up,recurrence rate was 13%. MRLD was performed in 1287(63.1%)patients. The univariable analysis identified as favourable prognostic factors for OS the female sex(p = 0.023), low ECOG-score(0.008),low SUVmax(p < 0.001), GGO appearance(p < 0.001), pT < 2 cm(p = 0.002) and low tumour grading(p = 0.002). The multivariable analysis confirmed as independent prognostic factors low ECOG-score(p = 0.012), low SUVmax(p < 0.001) and low tumour grading(p < 0.001). Analysing survival in patients with solid/sub-solid nodules and after propensity score matching for pTdimension and number of N2 resected lymphnodes, no OS differences were present comparing sampling vs MRLD.

CONCLUSION

Survival in pIa patients seems to be determined by patient and tumour characteristics such as performance status,grading and SUVmax. Type of lymphadnectomy did not seem to be correlated with OS in these patients.

Development and validation of a prognostic nomogram for early stage non-small cell lung cancer: a study based on the SEER database and a Chinese cohort

Objective

This study aimed to construct a nomogram to effectively predict the overall survival (OS) of patients with early-stage non-small-cell lung cancer (NSCLC).

Methods

For the training and internal validation cohorts, a total of 26,941 patients with stage I and II NSCLC were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. A nomogram was constructed based on the risk factors affecting prognosis using a Cox proportional hazards regression model. And 505 patients were recruited from Jiaxing First Hospital for external validation. The discrimination and calibration of the nomogram were evaluated by C-index and calibration curves.

Results

A Nomogram was created after identifying independent prognostic factors using univariate and multifactorial factor analysis. The C-index of this nomogram was 0.726 (95% CI, 0.718–0.735) and 0.721 (95% CI, 0.709–0.734) in the training cohort and the internal validation cohort, respectively, and 0.758 (95% CI, 0.691–0.825) in the external validation cohort, which indicates that the model has good discrimination. Calibration curves for 1-, 3-, and 5-year OS probabilities showed good agreement between predicted and actual survival. In addition, DCA analysis showed that the net benefit of the new model was significantly higher than that of the TNM staging system.

Conclusion

We developed and validated a survival prediction model for patients with non-small cell lung cancer in the early stages. This new nomogram is superior to the traditional TNM staging system and can guide clinicians to make the best clinical decisions.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-022-10067-8.

Establishment and Validation of a Predictive Nomogram for Postoperative Survival of Stage I Non-Small Cell Lung Cancer

Background

Surgical procedure is the preferred option for people with early-stage non-small cell lung cancer (NSCLC), while nearly 30% of patients experienced metastatic or recurrent tumor after operation. The primary intention of this context is to summarize high-risk prognostic factors and set up a novel nomogram to predict the overall survival of individuals with stage I NSCLC after resection.

Methods

Research objects, 10,218 patients with stage I NSCLC after operation from 2010 to 2015, were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Independent prognostic factors, confirmed by Cox regression analyses, were integrated into a nomogram, to predict the 3-and 5-year overall survival of these individuals. The model experienced internal validation of testing cohorts above and external validation crewed by 160 patients from China. Finally, the nomogram was evaluated through several verification methods such as concordance index (C-index), calibration plots and receiver operating characteristic curve (ROC).

Results

Multivariate analysis identified that age, gender, histologic type, differentiation class, type of operation, T stage and treatment were significant predictive factors for the survival of stage I NSCLC. Based on these factors, a nomogram was constructed to predict the 3- and 5-year overall survival of these individuals. Meanwhile, in the training set, this nomogram displayed excellent superiority over the TNM staging system with abroad application, especially in C-index (0.669 vs 0.580) and the AUC (the Area Under ROC Curve) for the 3- and 5-year survival (0.678 vs 0.582; 0.650 vs 0.576). In the calibration curve, the curve representing predicted survival tended to align with the line representing actual survival as well.

Conclusion

A nomogram was successfully created and verified to achieve the goal that made a rounded accurate prediction on the survival of postoperative I NSCLC patients in terms of the SEER database.

Comparison of nomogram and machine-learning methods for predicting the survival of non-small cell lung cancer patients

BACKGROUND

Most patients with advanced non-small cell lung cancer (NSCLC) have a poor prognosis. Predicting overall survival using clinical data would benefit cancer patients by allowing providers to design an optimum treatment plan. We compared the performance of nomograms with machine-learning models at predicting the overall survival of NSCLC patients. This comparison benefits the development and selection of models during the clinical decision-making process for NSCLC patients.

METHODS

Multiple machine-learning models were used in a retrospective cohort of 6586 patients. First, we modeled and validated a nomogram to predict the overall survival of NSCLC patients. Subsequently, five machine-learning models (logistic regression, random forest, XGBoost, decision tree, and light gradient boosting machine) were used to predict survival status. Next, we evaluated the performance of the models. Finally, the machine-learning model with the highest accuracy was chosen for comparison with the nomogram at predicting survival status by observing a novel performance measure: time-dependent prediction accuracy.

RESULTS

Among the five machine-learning models, the accuracy of random forest model outperformed the others. Compared with the nomogram for time-dependent prediction accuracy with a follow-up time ranging from 12 to 60 months, the prediction accuracies of both the nomogram and machine-learning models changed as time varied. The nomogram reached a maximum prediction accuracy of 0.85 in the 60th month, and the random forest algorithm reached a maximum prediction accuracy of 0.74 in the 13th month.

CONCLUSIONS

Overall, the nomogram provided more reliable prognostic assessments of NSCLC patients than machine-learning models over our observation period. Although machine-learning methods have been widely adopted for predicting clinical prognoses in recent studies, the conventional nomogram was competitive. In real clinical applications, a comprehensive model that combines these two methods may demonstrate superior capabilities.

Lung cancer survival prediction and biomarker identification with an ensemble machine learning analysis of tumor core biopsy metabolomic data

INTRODUCTION

While prediction of short versus long term survival from lung cancer is clinically relevant in the context of patient management and therapy selection, it has proven difficult to identify reliable biomarkers of survival. Metabolomic markers from tumor core biopsies have been shown to reflect cancer metabolic dysregulation and hold prognostic value.

OBJECTIVES

Implement and validate a novel ensemble machine learning approach to evaluate survival based on metabolomic biomarkers from tumor core biopsies.

METHODS

Data were obtained from tumor core biopsies evaluated with high-resolution 2DLC-MS/MS. Unlike biofluid samples, analysis of tumor tissue is expected to accurately reflect the cancer metabolism and its impact on patient survival. A comprehensive suite of machine learning algorithms were trained as base learners and then combined into a stacked-ensemble meta-learner for predicting "short" versus "long" survival on an external validation cohort. An ensemble method of feature selection was employed to find a reliable set of biomarkers with potential clinical utility.

RESULTS

Overall survival (OS) is predicted in external validation cohort with AUROC_TEST of 0.881 with support vector machine meta learner model, while progression-free survival (PFS) is predicted with AUROC_TEST of 0.833 with boosted logistic regression meta learner model, outperforming a nomogram using covariate data (staging, age, sex, treatment vs. non-treatment) as predictors. Increased relative abundance of guanine, choline, and creatine corresponded with shorter OS, while increased leucine and tryptophan corresponded with shorter PFS. In patients that expired, N6,N6,N6-Trimethyl-L-lysine, L-pyrogluatmic acid, and benzoic acid were increased while cystine, methionine sulfoxide and histamine were decreased. In patients with progression, itaconic acid, pyruvate, and malonic acid were increased.

CONCLUSION

This study demonstrates the feasibility of an ensemble machine learning approach to accurately predict patient survival from tumor core biopsy metabolomic data.

Effect of Adjuvant Chemotherapy on Survival of Patients With 8th Edition Stage IB Non-Small Cell Lung Cancer

BACKGROUND

The efficacy of adjuvant chemotherapy in patients with 8th edition stage IB (tumor size ≤4 cm) non-small cell lung cancer (NSCLC) remains unclear.

METHODS

We identified 9757 eligible patients (non-chemotherapy group: n=8303; chemotherapy group: n=1454) between 2004 and 2016 from the Surveillance, Epidemiology and End Results (SEER) database. Log-rank test was used to compare overall survival (OS) between the chemotherapy and non-chemotherapy groups. Cox regression model was applied to investigate the independent prognosis factors of all surgically treated stage IB patients, and then the nomogram was constructed. Propensity score matching (PSM) was performed to reduce the confounding bias, and subgroup analyses of the matched cohort were also performed. Finally, we reviewed 184 patients with stage IB NSCLC from July 2008 to December 2016 in Jinling Hospital as a validation cohort, and compared disease-free survival (DFS) and OS between the two groups.

RESULTS

In the SEER database cohort, adjuvant chemotherapy was associated with improved OS in both unmatched and matched (1417 pairs) cohorts (all P <0.05). The survival benefit (both OS and DFS) was confirmed in the validation cohort (P <0.05). Multivariate analysis showed age, race, sex, marital status, histology, tumor location, tumor size, differentiation, surgical method, lymph nodes (LNs) examined, radiotherapy and chemotherapy were prognostic factors for resected stage IB NSCLC (all P <0.05). The concordance index and calibration curves demonstrated good prediction effect. Subgroup analyses showed patients with the following characteristics benefited from chemotherapy: old age, poor differentiation to undifferentiation, 0-15 LNs examined, visceral pleural invasion (VPI), lobectomy and no radiotherapy (all P <0.05).

CONCLUSIONS

Adjuvant chemotherapy is associated with improved survival in 8th edition stage IB NSCLC patients, especially in those with old age, poorly differentiated to undifferentiated tumors, 0-15 LNs examined, VPI, lobotomy and no radiotherapy. Further prospective trials are needed to confirm these conclusions. Besides, the nomogram provides relatively accurate prediction for the prognosis of resected stage IB NSCLC patients.

Early assessment of circulating tumor DNA after curative-intent resection predicts tumor recurrence in early-stage and locally advanced non-small-cell lung cancer

Circulating tumor DNA (ctDNA) has demonstrated great potential as a noninvasive biomarker to assess minimal residual disease (MRD) and profile tumor genotypes in patients with non‐small‐cell lung cancer (NSCLC). However, little is known about its dynamics during and after tumor resection, or its potential for predicting clinical outcomes. Here, we applied a targeted‐capture high‐throughput sequencing approach to profile ctDNA at various disease milestones and assessed its predictive value in patients with early‐stage and locally advanced NSCLC. We prospectively enrolled 33 consecutive patients with stage IA to IIIB NSCLC undergoing curative‐intent tumor resection (median follow‐up: 26.2 months). From 21 patients, we serially collected 96 plasma samples before surgery, during surgery, 1–2 weeks postsurgery, and during follow‐up. Deep next‐generation sequencing using unique molecular identifiers was performed to identify and quantify tumor‐specific mutations in ctDNA. Twelve patients (57%) had detectable mutations in ctDNA before tumor resection. Both ctDNA detection rates and ctDNA concentrations were significantly higher in plasma obtained during surgery compared with presurgical specimens (57% versus 19% ctDNA detection rate, and 12.47 versus 6.64 ng·mL⁻¹, respectively). Four patients (19%) remained ctDNA‐positive at 1–2 weeks after surgery, with all of them (100%) experiencing disease progression at later time points. In contrast, only 4 out of 12 ctDNA‐negative patients (33%) after surgery experienced relapse during follow‐up. Positive ctDNA in early postoperative plasma samples was associated with shorter progression‐free survival (P = 0.013) and overall survival (P = 0.004). Our findings suggest that, in early‐stage and locally advanced NSCLC, intraoperative plasma sampling results in high ctDNA detection rates and that ctDNA positivity early after resection identifies patients at risk for relapse.

Overall Survival Analyses following Adjuvant Chemotherapy or Nonadjuvant Chemotherapy in Patients with Stage IB Non-Small-Cell Lung Cancer

Background

Adjuvant chemotherapy (ACT) can improve prognosis for stages II-IIIA patients with non-small-cell lung cancer (NSCLC), but its implication in stage I patients is still an intractable puzzle. This study aims to seek ACT candidates for stage IB NSCLC and establish a nomogram to predict overall survival (OS) of specific patient for clinician's decision.

Method

We performed a retrospective study on 16,765 patients (ACT group: n = 2,187; non-ACT group: n = 14,578) from the Surveillance, Epidemiology, and End Results (SEER) database. Overall survival was assessed in two groups. We performed propensity-score matching for risk adjustment. The risk factors were identified and used to create nomogram. Concordance index (C-index), Hosmer–Lemeshow test, and calibration were applied to evaluate model performance. To further evaluate the influence of tumor size on the selection of potential ACT candidates for patients with stage IB NSCLC, subgroup analyses were executed.

Result

Survival analysis for the entire study cohort showed that ACT had better OS than non-ACT (HR = 0.800, CI: (0.751–0.851), P < 0.0001). In matched cohort, ACT also presented better OS than non-ACT (HR = 0.775, CI: (0.704–0.853), P < 0.0001). Univariate and multivariate Cox regression analysis revealed that eight prognostic factors, including gender, age, grade, pathological subtype, tumor size, visceral pleural invasion, surgical procedure, and the number of removed lymph nodes, were significantly correlated with OS. The nomogram was further constructed based on these prognostic factors. The C-index of nomogram was 0.639 (95%CI: 0.632–0.646). The Hosmer–Lemeshow test, and calibration presented good congruence between the predictions and actual observations. Subgroup analyses of tumor size group showed that ACT shared similar OS to non-ACT in NSCLC patients with tumor size ≤20 mm (P > 0.05). However, for NSCLC patients with 20 mm < size ≤30 mm (HR = 0.845, 95%CI (0.724–0.986), P=0.032) and 30 mm < size ≤40 mm (HR = 0.912, 95%CI (0.833–1.000), P=0.049), ACT associated with better OS.

Conclusion

In this study, we found that ACT had better OS than non-ACT in patients with stage IB NSCLC. The nomogram provided an individual prediction of OS for patients after surgical resection. Patients with tumor size >20 mm and ≤40 mm may be potential candidates for ACT.

A nomogram for predicting overall survival in patients with resected non-small cell lung cancer treated with chemotherapy

Background

Chemotherapy is a common treatment for patients with resected non-small cell lung cancer (NSCLC). However, there are few models for predicting the survival outcomes of these patients. Here, we developed a clinical nomogram for predicting overall survival (OS) in this cohort.

Methods

A total of 16,661 patients with resected NSCLC treated with chemotherapy were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. We identified prognostic factors and integrated them into a nomogram. The model was subjected to bootstrap internal validation using the SEER database and external validation using a database in China and the National Cancer Database (NCDB). The model’s predictive accuracy and discriminative ability were tested by calibration and concordance index (C-index).

Results

Age, sex, number of dissected lymph nodes, extent of surgery, N stage, T stage, and grade were independent factors for OS and were integrated into the model. The calibration curves for probability of 1-, 3-, and 5-year OS showed excellent agreement between the predicted and actual survivals. The C-index of the nomogram was higher than that of the Tumor-Node-Metastasis staging system for predicting OS (training cohort, 0.62 vs. 0.58; China cohort, 0.68 vs. 0.63; NCDB cohort, 0.59 vs. 0.57).

Conclusions

We developed a nomogram that can present individual prediction of OS for patients with resected NSCLC who are undergoing chemotherapy. This practical prognostic tool may help clinicians in treatment planning.

Construction of a Five-Super-Enhancer-Associated-Genes Prognostic Model for Osteosarcoma Patients

Osteosarcoma is a malignant tumor most commonly arising in children and adolescents and associated with poor prognosis. In recent years, some prognostic models have been constructed to assist clinicians in the treatment of osteosarcoma. However, the prognosis and treatment of patients with osteosarcoma remain unsatisfactory. Notably, super-enhancer (SE)-associated genes strongly promote the progression of osteosarcoma. In the present study, we constructed a novel effective prognostic model using SE-associated genes from osteosarcoma. Five SE-associated genes were initially screened through the least absolute shrinkage and selection operator (Lasso) penalized Cox regression, as well as univariate and multivariate Cox regression analyses. Meanwhile, a risk score model was constructed using the expression of these five genes. The excellent performance of the five-SE-associated-gene-based prognostic model was determined via time-dependent receiver operating characteristic (ROC) curves and Kaplan-Meier curves. Inferior outcome of overall survival (OS) was predicted in the high-risk group. A nomogram based on the polygenic risk score model was further established to validate the performance of the prognostic model. It showed that our prognostic model performed outstandingly in predicting 1-, 3-, and 5-year OS of patients with osteosarcoma. Meanwhile, these five genes also belonged to the hub genes associated with survival and necrosis of osteosarcoma according to the result of weighted gene co-expression network analysis based on the dataset of GSE39058. Therefore, we believe that the five-SE-associated-gene-based prognostic model established in this study can accurately predict the prognosis of patients with osteosarcoma and effectively assist clinicians in treating osteosarcoma in the future.

Development and validation of a prognostic nomogram to predict overall survival and cancer-specific survival for patients with anaplastic thyroid carcinoma

Background

Anaplastic thyroid carcinoma (ATC) is a rare malignant tumor with a poor prognosis. However, there is no useful clinical prognostic predictive tool for ATC so far. Our study identified risk factors for survival of ATC and created a reliable nomogram to predict overall survival (OS) and cancer-specific survival (CSS) of patients with ATC.

Methods

A total of 1,404 cases of ATC diagnosed between 1983 and 2013 were extracted from on the Surveillance, Epidemiology and End Results database based on our inclusion criteria. OS and CSS were compared among patients between each variable by Kaplan-Meier methods. The Cox proportional hazards model was used to evaluate multiple prognostic factors and obtain independent predictors. All independent risk factors were included to build nomograms, whose accuracy and practicability were tested by concordance index (C-index), calibration curves, ROC curves, DCA, net reclassification improvement (NRI) and integrated discrimination improvement (IDI).

Results

Historic stage, tumor size, surgery and radiotherapy were independent risk factors associated with ATC according to multivariate Cox regression analysis of OS. However, gender was also an important prognostic predictor in CSS besides the factors mentioned above. These characteristics were included in the nomograms predicting OS and CSS of patients with ATC. The nomograms predicting OS and CSS performed well with a C-index of 0.765 and 0.773. ROC curves, DCA, NRI and IDI suggested that the nomogram was superior to TNM staging and age.

Conclusion

The proposed nomogram is a reliable tool based on the prediction of OS and CSS for patients with ATC. Such a predictive tool can help to predict the survival of the patients.