Neuron-specific enolase, histopathological types, and age as risk factors for bone metastases in lung cancer

Construction of a predictive model for bone metastasis from first primary lung adenocarcinoma within 3 cm based on machine learning algorithm: a retrospective study

Background

Adenocarcinoma, the most prevalent histological subtype of non-small cell lung cancer, is associated with a significantly higher likelihood of bone metastasis compared to other subtypes. The presence of bone metastasis has a profound adverse impact on patient prognosis. However, to date, there is a lack of accurate bone metastasis prediction models. As a result, this study aims to employ machine learning algorithms for predicting the risk of bone metastasis in patients.

Method

We collected a dataset comprising 19,454 cases of solitary, primary lung adenocarcinoma with pulmonary nodules measuring less than 3 cm. These cases were diagnosed between 2010 and 2015 and were sourced from the Surveillance, Epidemiology, and End Results (SEER) database. Utilizing clinical feature indicators, we developed predictive models using seven machine learning algorithms, namely extreme gradient boosting (XGBoost), logistic regression (LR), light gradient boosting machine (LightGBM), Adaptive Boosting (AdaBoost), Gaussian Naive Bayes (GNB), multilayer perceptron (MLP) and support vector machine (SVM).

Results

The results demonstrated that XGBoost exhibited superior performance among the four algorithms (training set: AUC: 0.913; test set: AUC: 0.853). Furthermore, for convenient application, we created an online scoring system accessible at the following URL: https://www.xsmartanalysis.com/model/predict/?mid=731symbol=7Fr16wX56AR9Mk233917, which is based on the highest performing model.

Conclusion

XGBoost proves to be an effective algorithm for predicting the occurrence of bone metastasis in patients with solitary, primary lung adenocarcinoma featuring pulmonary nodules below 3 cm in size. Moreover, its robust clinical applicability enhances its potential utility.

Expression changes and clinical significance of serum neuron-specific enolase and squamous cell carcinoma antigen in lung cancer patients after radiotherapy

OBJECTIVE

To explore the changes and clinical significance of serum Neuron-Specific Enolase (NSE) and Squamous Cell Carcinoma antigen (SCC) in patients with lung cancer before and after radiotherapy.

METHODS

82 patients with lung cancer were treated with radiotherapy, and effective clinical intervention was given during the radiotherapy process. The patients were followed up for 1 year after radiotherapy and were divided into a recurrence and metastasis group (n = 28) and a non-recurrence and metastasis group (n = 54) according to their prognosis. Another 54 healthy volunteers examined in the present study's hospital during the same period were selected as the control group. To compare the changes of NSE and SCC levels in serum in patients with lung cancer at admission and after radiotherapy, and to explore their clinical significance.

RESULTS

After intervention, NSE and SCC levels in the serum of the two groups of patients were significantly lower than those before intervention, and the levels of CD4⁺ and CD4⁺/CD8⁺ were significantly higher than those before intervention (p < 0.05); the level of CD8⁺ was not significantly different from that before intervention (p > 0.05). And NSE and SCC levels in the intervention group were significantly lower than those in the routine group, the levels of CD4⁺, CD4⁺/CD8⁺ were significantly higher than those in the routine group (p < 0.05).

CONCLUSION

NSE and SCC in serum can preliminarily evaluate the effect of radiotherapy in patients with lung cancer and have a certain predictive effect on prognosis.

Prognostic nomogram to predict the distant metastasis after intensity-modulated radiation therapy for patients with nasopharyngeal carcinoma

ABSTRACT

Distant metastasis-free survival (DMFS) significantly differs among individuals with nasopharyngeal carcinoma (NPC). This analysis was carried out to find prognostic risk factors of DMFS and create a nomogram to predict DMFS for NPC patients who received Intensity-Modulated Radiation Therapy (IMRT).During March 2008 to January 2010, 437 patients with confirmed NPC from First Affiliated Hospital of Guangxi Medical University were recruited into this study. We developed a nomogram for predicting DMFS according to Cox regression analysis. Nomogram performance was assessed by concordance index (C-index), bootstrap validation method, and operating characteristics curves (ROC), respectively.Four independent prognostic factors for distant metastasis were identified, including age, chemotherapy, N-stage and residual tumor. C-index of the nomogram for prediction of DMFS was 0.807 (95% confidence interval, 0.726 to 0.738), which was confirmed using bootstrap validation, indicating satisfactory predictive accuracy. The calibration curves also showed adequate agreement in predicting the 3 and 5-year DMFS. The 3 and 5-year area under the curve (AUC) of ROC for nomogram and TMN stage were 0.828 and 0.612, 0.809, and 0.571, respectively. Classifying risk subgroups based on optimal cut-off value contributes to the effective discrimination of distant metastasis.The nomogram developed for this study is useful for oncologists to accurately predict DMFS and facilitates individualized treatment for patients with NPC.

Analysis of risk factors and gene mutation characteristics of different metastatic sites of lung cancer

Risk factors vary in terms of the pattern of lung cancer metastasis and specific metastatic organs. In this study, we retrospectively analyzed the clinical risk factors of tumor metastasis in lung cancer patients and used second‐generation gene sequencing to characterize relevant gene mutations. The risk factors of different metastatic sites of real‐world lung cancer were explored to find the differentially expressed genes and risk factors in different metastatic organs, which laid a foundation for further study on the metastasis patterns and mechanisms of lung cancer. The clinical risk factors of tumor metastasis in 137 lung cancer patients who attended our department from May 2017 to March 2019 were retrospectively analyzed and grouped based on bone metastasis, brain metastasis, other distant metastasis, and no metastasis. Single‐ or multi‐factor logistic regression analysis was performed to analyze the effect of neutrophil/lymphocyte ratio/platelet/lymphocyte ratio/lymphocyte to monocyte ratio on platelets (PLTs) and bone metastasis by combining PLT values, age, pathology type, gender, and smoking history. Based on the presence or absence of bone metastasis, distal metastasis, and PLT values of lung cancer, 39 tissue specimens of primary lung cancer were taken for 773 gene grouping and gene mutation characterization. The tumor mutation load, gene copy number instability, microsatellite instability, and tumor heterogeneity among different groups were analyzed. Age and PLT level were independent risk factors for bone metastasis and distal metastasis, but not for brain metastasis. The RB1 gene was mutated during bone metastasis, and tumor heterogeneity was less in the elevated PLT group. PLT values were an independent risk factor for distant metastases from lung cancer other than the brain. Age has a significant effect on bone metastasis formation. RB1 gene mutation was significantly associated with bone metastasis.

Synchronous bone metastasis in lung cancer: retrospective study of a single center of 15,716 patients from Tianjin, China

Background

This study aimed to describe the incidence, clinical characteristics, and prognosis of lung cancer patients with synchronous bone metastasis (SBM) and to analyze the prognostic factors of the lung cancer patients with SBM.

Methods

A total of 15,716 lung cancer patients who were diagnosed between 2009 to 2018 in the Tianjin Medical University Cancer Institute and Hospital were retrospectively reviewed. Among them, patients with SBM were checked. Both the demographic and clinical characteristics were included as follows: age, gender, marital status, history of smoking, alcohol consumption, family history of tumor, Karnofsky score, lymph node metastasis, histological type. Besides, laboratory data such as alkaline phosphatase, lactate dehydrogenase, carcinoembryonic antigen, squamous cell carcinoma antigen, cytokeratin-19 fragment, and neuron specific enolase were also included. The log-rank test and multivariate Cox regression analysis were employed to reveal the potential prognostic predictors. A further analysis using the Kaplan–Meier was employed to demonstrate the difference on the prognosis of LC patients between adenocarcinoma and non-adenocarcinoma.

Results

Among the included patients, 2738 patients (17.42%) were diagnosed with SBM. A total of 938 patients (34.3%) with SBM were successfully followed and the median survival was 11.53 months (95%CI: 10.57–12.49 months), and the 1-, 2-, and 5-year overall survival rate was 51, 17, and 8%, respectively. Multivariable Cox regression results showed history of smoking and high level of NSE were associated with the poor prognosis, while adenocarcinoma histological type was associated with better survival.

Conclusion

The prevalence of SBM in lung cancer is relatively high with poor survival. The lung cancer patients with SBM showed diverse prognosis. Among all the pathological types, the division of adenocarcinoma suggested different prognosis of the lung cancer patients with SBM. The present study emphasized the importance of pathological diagnosis on prognostic determinants in lung cancer patients with SBM.

Multifunctional neuron-specific enolase: its role in lung diseases

Neuron-specific enolase (NSE), also known as gamma (γ) enolase or enolase-2 (Eno2), is a form of glycolytic enolase isozyme and is considered a multifunctional protein. NSE is mainly expressed in the cytoplasm of neurons and neuroendocrine cells, especially in those of the amine precursor uptake and decarboxylation (APUD) lineage such as pituitary, thyroid, pancreas, intestine and lung. In addition to its well-established glycolysis function in the cytoplasm, changes in cell localization and differential expression of NSE are also associated with several pathologies such as infection, inflammation, autoimmune diseases and cancer. This article mainly discusses the role and diagnostic potential of NSE in some lung diseases.

Single nucleotide polymorphisms within the Wnt pathway predict the risk of bone metastasis in patients with non-small cell lung cancer

The Wingless-type (Wnt) signaling pathway plays an important role in the development and progression of cancer. This study aimed to evaluate the relationship between single nucleotide polymorphisms (SNPs) in the Wnt pathway and the risk of bone metastasis in patients with non-small cell lung cancer (NSCLC). We collected 500 blood samples from patients with NSCLC and genotyped eight SNPs from four core genes (WNT2, AXIN1, CTNNB1 and APC) present within the WNT pathway. Moreover, we assessed the potential relationship of these genes with bone metastasis development. Our results showed that the AC/AA genotype of CTNNB1: rs1880481 was associated with a decreased risk of bone metastasis. Polymorphisms with an HR of < 1 had a cumulative protective impact on the risk of bone metastasis. Furthermore, patients with the AC/AA genotype of CTNNB1: rs1880481 was associated with Karnofsky performance status score, squamous cell carcinoma antigen and Ki-67 proliferation index. Lastly, patients with the AC/AA genotype of CTNNB1: rs1880481 had significantly longer median progression free survival time than those with the CC genotype. In conclusion, SNPs within the Wnt signaling pathway are associated with a decreased risk of bone metastasis, and may be valuable biomarkers for bone metastasis in patients with NSCLC.

Different distant metastasis patterns based on tumor size could be found in extensive-stage small cell lung cancer patients: a large, population-based SEER study

BACKGROUND

Small-cell lung cancer (SCLC) is a malignant cancer with the ability to metastasize quickly. The relationship between tumor size and the distant metastasis patterns of Extensive-Stage Small Cell Lung Cancer (ES-SCLC) has not been reported.

OBJECTIVES

The aim of this study was to determine the different distant metastasis patterns as they related to tumor size in ES-SCLC.

PATIENTS AND METHODS

We used Surveillance, Epidemiology, and End Results (SEER) population-based data collected from 2010 through 2013 to identify 11058 ES-SCLC patients with definite evidence of distant metastases. Multivariate logistic regression analysis was used to demonstrate the association between tumor size and distant metastasis patterns including bone, liver, brain, and lung metastases. Age, race, sex, and N stage were also selected in the logistic regression model.

RESULTS

Subtle differences in metastasis patterns were found among patients based on different tumor sizes. Patients with tumors 3-7 cm have a higher risk of bone metastasis compared with those that have tumors ≤3 cm (OR 1.165, 95% CI [1.055-1.287], P = 0.003) and patients with tumors ≥7 cm have a higher risk of lung metastasis (OR 1.183, 95% CI [1.039-1.347], P = 0.011). In addition, patients with tumors ≥7 cm had a lower risk of brain metastasis and liver metastasis than patients with tumors ≤3 cm (OR 0.799, 95% CI [0.709-0.901], P < 0.001; OR 0.747, 95% CI [0.672-0.830], P < 0.001). Interestingly, there was no correlation between a larger tumor and a higher risk of metastasis. However, the tumor metastasis pattern did have some correlation with age, gender, race and N-status.

CONCLUSION

The pattern of distant metastasis of ES-SCLC is related to the tumor size and the tumor size is indicative of the metastatic site. Larger tumor sizes did not correlate with a higher risk of distant metastasis, but the size is related to the pattern of distant metastasis. The study of different distant metastasis patterns based on tumor size and other clinical features (e.g., age, race, sex, and N stage) in ES-SCLC is clinically valuable.

A novel logistic regression model combining semi-supervised learning and active learning for disease classification

Traditional supervised learning classifier needs a lot of labeled samples to achieve good performance, however in many biological datasets there is only a small size of labeled samples and the remaining samples are unlabeled. Labeling these unlabeled samples manually is difficult or expensive. Technologies such as active learning and semi-supervised learning have been proposed to utilize the unlabeled samples for improving the model performance. However in active learning the model suffers from being short-sighted or biased and some manual workload is still needed. The semi-supervised learning methods are easy to be affected by the noisy samples. In this paper we propose a novel logistic regression model based on complementarity of active learning and semi-supervised learning, for utilizing the unlabeled samples with least cost to improve the disease classification accuracy. In addition to that, an update pseudo-labeled samples mechanism is designed to reduce the false pseudo-labeled samples. The experiment results show that this new model can achieve better performances compared the widely used semi-supervised learning and active learning methods in disease classification and gene selection.

Screening and Biosensor-Based Approaches for Lung Cancer Detection

Early diagnosis of lung cancer helps to reduce the cancer death rate significantly. Over the years, investigators worldwide have extensively investigated many screening modalities for lung cancer detection, including computerized tomography, chest X-ray, positron emission tomography, sputum cytology, magnetic resonance imaging and biopsy. However, these techniques are not suitable for patients with other pathologies. Developing a rapid and sensitive technique for early diagnosis of lung cancer is urgently needed. Biosensor-based techniques have been recently recommended as a rapid and cost-effective tool for early diagnosis of lung tumor markers. This paper reviews the recent development in screening and biosensor-based techniques for early lung cancer detection.