Which Is a More Accurate Predictor in Colorectal Survival Analysis? Nine Data Mining Algorithms vs. the TNM Staging System

Objective

Over the past decades, many studies have used data mining technology to predict the 5-year survival rate of colorectal cancer, but there have been few reports that compared multiple data mining algorithms to the TNM classification of malignant tumors (TNM) staging system using a dataset in which the training and testing data were from different sources. Here we compared nine data mining algorithms to the TNM staging system for colorectal survival analysis.

Methods

Two different datasets were used: 1) the National Cancer Institute''s Surveillance, Epidemiology, and End Results dataset; and 2) the dataset from a single Chinese institution. An optimization and prediction system based on nine data mining algorithms as well as two variable selection methods was implemented. The TNM staging system was based on the 7^th edition of the American Joint Committee on Cancer TNM staging system.

Results

When the training and testing data were from the same sources, all algorithms had slight advantages over the TNM staging system in predictive accuracy. When the data were from different sources, only four algorithms (logistic regression, general regression neural network, Bayesian networks, and Naïve Bayes) had slight advantages over the TNM staging system. Also, there was no significant differences among all the algorithms (p>0.05).

Conclusions

The TNM staging system is simple and practical at present, and data mining methods are not accurate enough to replace the TNM staging system for colorectal cancer survival prediction. Furthermore, there were no significant differences in the predictive accuracy of all the algorithms when the data were from different sources. Building a larger dataset that includes more variables may be important for furthering predictive accuracy.     

A Lymph Node Staging System for Gastric Cancer: A Hybrid Type Based on Topographic and Numeric Systems

Although changing a lymph node staging system from an anatomically based system to a numerically based system in gastric cancer offers better prognostic performance, several problems can arise: it does not offer information on the anatomical extent of disease and cannot represent the extent of lymph node dissection. The purpose of this study was to discover an alternative lymph node staging system for gastric cancer. Data from 6025 patients who underwent gastrectomy for primary gastric cancer between January 2000 and December 2010 were reviewed. The lymph node groups were reclassified into lesser-curvature, greater-curvature, and extra-perigastric groups. Presence of any metastatic lymph node in one group was considered positive. Lymph node groups were further stratified into four (new N0–new N3) according to the number of positive lymph node groups. Survival outcomes with this new N staging were compared with those of the current TNM system. For validation, two centers in Japan (large center, n = 3443; medium center, n = 560) were invited. Even among the same pN stages, the more advanced new N stage showed worse prognosis, indicating that the anatomical extent of metastatic lymph nodes is important. The prognostic performance of the new staging system was as good as that of the current TNM system for overall advanced gastric cancer as well as lymph node—positive gastric cancer (Harrell C-index was 0.799, 0.726, and 0.703 in current TNM and 0.799, 0.727, and 0.703 in new TNM stage). Validation sets supported these outcomes. The new N staging system demonstrated prognostic performance equal to that of the current TNM system and could thus be used as an alternative.     

Identification of Plasma Lipid Biomarkers for Prostate Cancer by Lipidomics and Bioinformatics

Background

Lipids have critical functions in cellular energy storage, structure and signaling. Many individual lipid molecules have been associated with the evolution of prostate cancer; however, none of them has been approved to be used as a biomarker. The aim of this study is to identify lipid molecules from hundreds plasma apparent lipid species as biomarkers for diagnosis of prostate cancer.

Methodology/Principal Findings

Using lipidomics, lipid profiling of 390 individual apparent lipid species was performed on 141 plasma samples from 105 patients with prostate cancer and 36 male controls. High throughput data generated from lipidomics were analyzed using bioinformatic and statistical methods. From 390 apparent lipid species, 35 species were demonstrated to have potential in differentiation of prostate cancer. Within the 35 species, 12 were identified as individual plasma lipid biomarkers for diagnosis of prostate cancer with a sensitivity above 80%, specificity above 50% and accuracy above 80%. Using top 15 of 35 potential biomarkers together increased predictive power dramatically in diagnosis of prostate cancer with a sensitivity of 93.6%, specificity of 90.1% and accuracy of 97.3%. Principal component analysis (PCA) and hierarchical clustering analysis (HCA) demonstrated that patient and control populations were visually separated by identified lipid biomarkers. RandomForest and 10-fold cross validation analyses demonstrated that the identified lipid biomarkers were able to predict unknown populations accurately, and this was not influenced by patient''s age and race. Three out of 13 lipid classes, phosphatidylethanolamine (PE), ether-linked phosphatidylethanolamine (ePE) and ether-linked phosphatidylcholine (ePC) could be considered as biomarkers in diagnosis of prostate cancer.

Conclusions/Significance

Using lipidomics and bioinformatic and statistical methods, we have identified a few out of hundreds plasma apparent lipid molecular species as biomarkers for diagnosis of prostate cancer with a high sensitivity, specificity and accuracy.     

局限性前列腺癌病理分期比较的临床研究进展

目的：探讨指诊分期和动态增强核磁（DCE—MRI）分期预测局限性前列腺癌病理结果的临床价值。方法：对42例局限性前列腺癌患者术前行经直肠指诊分期及MRI、DCE—MRI分期,并与根治术后的病理结果进行比较,评价临床分期及DCE—MRI分期的临床意义。结果：DCE—MRI分期与病理分期相比总体检测结果相同（0．25〈P〈0．5）,能很好的预测前列腺内肿瘤的病理分期;直肠指诊诊断局限性前列腺癌有较高的敏感性（89．5％）,DCE—MRI则有较高的特异性（79．17％）及准确性（83．33％）。结论：直肠指诊是筛查前列腺癌的重要手段,DCE—MRI则能更好的了解肿瘤的范围及浸润情况,更准确的预测肿瘤的病理分期。     

A stroma-related lncRNA panel for predicting recurrence and adjuvant chemotherapy benefit in patients with early-stage colon cancer

The heterogeneity in prognoses and chemotherapeutic responses of colon cancer patients with similar clinical features emphasized the necessity for new biomarkers that help to improve the survival prediction and tailor therapies more rationally and precisely. In the present study, we established a s troma-related l ncRNA s ignature (SLS) based on 52 lncRNAs to comprehensively predict clinical outcome. The SLS model could not only distinguish patients with different recurrence and mortality risks through univariate analysis, but also served as an independent factor for relapse-free and overall survival. Compared with the conventionally used TNM stage system, the SLS model clearly possessed higher predictive accuracy. Moreover, the SLS model also effectively screened chemotherapy-responsive patients, as only patients in the low-SLS group could benefit from adjuvant chemotherapy. The following cell infiltration and competing endogenous RNA (ceRNA) network functional analyses further confirmed the association between the SLS model and stromal activation-related biological processes. Additionally, this study also identified three phenotypically distinct colon cancer subtypes that varied in clinical outcome and chemotherapy benefits. In conclusion, our SLS model may be a significant determinant of survival and chemotherapeutic decision-making in colon cancer and may have a strong clinical transformation value.     

Genomic signatures associated with the development, progression, and outcome of prostate cancer

Prostate cancer remains a common cause of cancer death in men. Applications of new genomic technologies to the recent development of high-quality prostate cancer models in multiple contexts have added great molecular insight into the development of and progression to metastasis. Genomic analysis of DNA, RNA, and protein alterations allows for the global assessment of this disease and provides the molecular framework to improve risk classification, outcome prediction, and development of targeted therapies. The creation of expression profiles and signatures will allow the evaluation of cancer phenotypes and give insight into determining those with increased risk of cancer, identification of critical pathways involved in the development of cancer, prediction of disease outcome, and assessment of the response of cancer to established and novel therapies.This review focuses on highlighting recent work in genomics and on its role in evaluating potential genetic modifiers of prostate cancer and novel biomarkers that may help with prostate cancer diagnosis, its potential to provide a better understanding of prostate cancer behavior and transition to metastatic disease, and its role in current and new therapies in prostate cancer. This framework has the exciting potential to be predictive and provide personalized and individual treatment to the large number of men diagnosed with prostate cancer each year.     

Adjusting confounders in ranking biomarkers: a model-based ROC approach

High-throughput studies have been extensively conducted in the research of complex human diseases. As a representative example, consider gene-expression studies where thousands of genes are profiled at the same time. An important objective of such studies is to rank the diagnostic accuracy of biomarkers (e.g. gene expressions) for predicting outcome variables while properly adjusting for confounding effects from low-dimensional clinical risk factors and environmental exposures. Existing approaches are often fully based on parametric or semi-parametric models and target evaluating estimation significance as opposed to diagnostic accuracy. Receiver operating characteristic (ROC) approaches can be employed to tackle this problem. However, existing ROC ranking methods focus on biomarkers only and ignore effects of confounders. In this article, we propose a model-based approach which ranks the diagnostic accuracy of biomarkers using ROC measures with a proper adjustment of confounding effects. To this end, three different methods for constructing the underlying regression models are investigated. Simulation study shows that the proposed methods can accurately identify biomarkers with additional diagnostic power beyond confounders. Analysis of two cancer gene-expression studies demonstrates that adjusting for confounders can lead to substantially different rankings of genes.     

Performance of an adipokine pathway-based multilocus genetic risk score for prostate cancer risk prediction

Few biomarkers are available to predict prostate cancer risk. Single nucleotide polymorphisms (SNPs) tend to have weak individual effects but, in combination, they have stronger predictive value. Adipokine pathways have been implicated in the pathogenesis. We used a candidate pathway approach to investigate 29 functional SNPs in key genes from relevant adipokine pathways in a sample of 1006 men eligible for prostate biopsy. We used stepwise multivariate logistic regression and bootstrapping to develop a multilocus genetic risk score by weighting each risk SNP empirically based on its association with disease. Seven common functional polymorphisms were associated with overall and high-grade prostate cancer (Gleason≥7), whereas three variants were associated with high metastatic-risk prostate cancer (PSA≥20 ng/mL and/or Gleason≥8). The addition of genetic variants to age and PSA improved the predictive accuracy for overall and high-grade prostate cancer, using either the area under the receiver-operating characteristics curves (P<0.02), the net reclassification improvement (P<0.001) and integrated discrimination improvement (P<0.001) measures. These results suggest that functional polymorphisms in adipokine pathways may act individually and cumulatively to affect risk and severity of prostate cancer, supporting the influence of adipokine pathways in the pathogenesis of prostate cancer. Use of such adipokine multilocus genetic risk score can enhance the predictive value of PSA and age in estimating absolute risk, which supports further evaluation of its clinical significance.     

Beyond prostate-specific antigen: new serologic biomarkers for improved diagnosis and management of prostate cancer

The use of total prostate-specific antigen (tPSA) measurement has dramatically improved the ability to detect prostate cancer at earlier stages. However, as the number of men presenting with advanced disease (and high tPSA levels) has decreased, and given the fact that tPSA is highly reflective of benign prostatic hyperplasia, the need has emerged for novel biomarkers specifically associated with prostate cancer in order to improve predictive models. Several new biomarkers have shown promise, and studies continue to investigate the role of these markers in the detection, staging, and prognosis of prostate cancer. As new useful biomarkers continue to emerge, guidelines for their employment, as well as coordination of further research studies, are needed; a systematic, phased, nomogram-based model is a rational way to manage these efforts.     

Partial AUC estimation and regression

Accurate diagnosis of disease is a critical part of health care. New diagnostic and screening tests must be evaluated based on their abilities to discriminate diseased from nondiseased states. The partial area under the receiver operating characteristic (ROC) curve is a measure of diagnostic test accuracy. We present an interpretation of the partial area under the curve (AUC), which gives rise to a nonparametric estimator. This estimator is more robust than existing estimators, which make parametric assumptions. We show that the robustness is gained with only a moderate loss in efficiency. We describe a regression modeling framework for making inference about covariate effects on the partial AUC. Such models can refine knowledge about test accuracy. Model parameters can be estimated using binary regression methods. We use the regression framework to compare two prostate-specific antigen biomarkers and to evaluate the dependence of biomarker accuracy on the time prior to clinical diagnosis of prostate cancer.     

Semiparametric Models of Time-Dependent Predictive Values of Prognostic Biomarkers

Summary .  Rigorous statistical evaluation of the predictive values of novel biomarkers is critical prior to applying novel biomarkers into routine standard care. It is important to identify factors that influence the performance of a biomarker in order to determine the optimal conditions for test performance. We propose a covariate-specific time-dependent positive predictive values curve to quantify the predictive accuracy of a prognostic marker measured on a continuous scale and with censored failure time outcome. The covariate effect is accommodated with a semiparametric regression model framework. In particular, we adopt a smoothed survival time regression technique ( Dabrowska, 1997 ,  The Annals of Statistics   25, 1510–1540) to account for the situation where risk for the disease occurrence and progression is likely to change over time. In addition, we provide asymptotic distribution theory and resampling-based procedures for making statistical inference on the covariate-specific positive predictive values. We illustrate our approach with numerical studies and a dataset from a prostate cancer study.     

Current Clinical Applications of the In-capromab Pendetide Scan (ProstaScint(R) Scan, Cyt-356)

Prostate-specific antigen (PSA) has been extremely helpful in the detection of new or recurrent prostate cancer. However, localization of the recurrent tumor has been challenging with currently available radiographic modalities. The (111)In-capromab pendetide scan was developed to diagnose accurately and, more importantly, localize and stage a new or recurrent prostate cancer. Studies suggest that the (111)In-capromab pendetide scan can provide more accurate staging of clinically localized prostate cancer prior to staging lymphadenectomy or definitive therapy. It can also provide valuable information when local adjuvant radiation therapy is considered in men with biochemical cancer recurrence following radical prostatectomy.     

Translational proteomics: what can you do for true patients?

Matching the right medical strategy to the right patient is the key for modern clinical oncology. To this aim, we have many delicate drugs designed to target in elegant ways critical proteins identified in cancer cells. However, clinical oncologists and multidisciplinary groups devoted to treating patients in an integrative fashion have histology and an TNM staging system as the most relevant biomarkers to decide therapeutic approaches for our patients. In addition, the most used drugs are classical chemotherapeutic compounds such as cisplatin, epirrubicin, irinotecan, oxaliplatin, and so on. Thus, new targeted therapies, surgery, radiotherapy, and chemotherapy will live together causing a duality for the immediate future. We will try to delineate unmet needs for clinical oncologists that would add value for cancer proteomics in terms of true patients.     

Identification of a novel glycolysis-related gene signature that can predict the survival of patients with lung adenocarcinoma

Lung cancer is one of the most malignant cancers worldwide, and lung adenocarcinoma (LUAD) is the most common histologic subtype. Thousands of biomarkers related to the survival and prognosis of patients with this cancer type have been investigated through database mining; however, the prediction effect of a single gene biomarker is not satisfactorily specific or sensitive. Thus, the present study aimed to develop a novel gene signature of prognostic values for patients with LUAD. Using a data-mining method, we performed expression profiling of 1145 mRNAs in large cohorts with LUAD (n = 511) from The Cancer Genome Atlas database. Using the Gene Set Enrichment Analysis, we selected 198 genes related to GLYCOLYSIS, which is the most important enrichment gene set. Moreover, these genes were identified using Cox proportional regression modeling. We established a risk score staging system to predict the outcome of patients with LUAD and subsequently identified four genes (AGRN, AKR1A1, DDIT4, and HMMR) that were closely related to the prognosis of patients with LUAD. The identified genes allowed us to classify patients into the high-risk group (with poor outcome) and low-risk group (with better outcome). Compared with other clinical factors, the risk score has a better performance in predicting the outcome of patients with LUAD, particularly in the early stage of LUAD. In conclusion, we developed a four-gene signature related to glycolysis by utilizing the Cox regression model and a risk staging model for LUAD, which might prove valuable for the clinical management of patients with LUAD.     

Expression of CaT-like, a novel calcium-selective channel, correlates with the malignancy of prostate cancer

The regulation of intracellular Ca(2+) plays a key role in the development and growth of cells. Here we report the cloning and functional expression of a highly calcium-selective channel localized on the human chromosome 7. The sequence of the new channel is structurally related to the gene product of the CaT1 protein cloned from rat duodenum and is therefore called CaT-like (CaT-L). CaT-L is expressed in locally advanced prostate cancer, metastatic and androgen-insensitive prostatic lesions but is undetectable in healthy prostate tissue and benign prostatic hyperplasia. Additionally, CaT-L is expressed in normal placenta, exocrine pancreas, and salivary glands. New markers with well defined biological function that correlate with aberrant cell growth are needed for the molecular staging of cancer and to predict the clinical outcome. The human CaT-L channel represents a marker for prostate cancer progression and may serve as a target for therapeutic strategies.     

Mass spectrometry-based expression profiling of clinical prostate cancer

The maturation of MS technologies has provided a rich opportunity to interrogate protein expression patterns in normal and disease states by applying expression protein profiling methods. Major goals of this research strategy include the identification of protein biomarkers that demarcate normal and disease populations, and the identification of therapeutic biomarkers for the treatment of diseases such as cancer (Celis, J. E., and Gromov, P. (2003) Proteomics in translational cancer research: Toward an integrated approach. Cancer Cell 3, 9-151). Prostate cancer is one disease that would greatly benefit from implementing MS-based expression profiling methods because of the need to stratify the disease based on molecular markers. In this review, we will summarize the current MS-based methods to identify and validate biomarkers in human prostate cancer. Lastly, we propose a reverse proteomic approach implementing a quantitative MS research strategy to identify and quantify biomarkers implicated in prostate cancer development. With this approach, the absolute levels of prostate cancer biomarkers will be identified and quantified in normal and diseased samples by measuring the levels of native peptide biomarkers in relation to a chemically identical but isotopically labeled reference peptide. Ultimately, a centralized prostate cancer peptide biomarker expression database could function as a repository for the identification, quantification, and validation of protein biomarker(s) during prostate cancer progression in men.     

肿瘤标志物CEA、CA199对结直肠癌TNM分期的预判价值

目的:探讨肿瘤标志物CEA、CA199浓度变化在结直肠癌TNM分期中的预判价值。方法:回顾我院2010年1月~2013年10月收治的经手术治疗的结、直肠癌患者(共96例)的有关资料,分析其术前CEA、CA199浓度水平与术后病理确定TNM分期结果的相互关系,进行相应的统计学检测。结果:结直肠癌Ⅰ~Ⅳ期CEA浓度依次为4.28±1.78、6.92±2.01、23.99±6.49和362.64±158.80 ng/mL,CA199浓度依次为12.58±2.98、13.37±2.62、36.84±10.33和238.71±103.69 U/mL,肿瘤标志物CEA、CA199的浓度随TNM分期升级而增高,通过Kruskal-Wallis秩检验分析及Spearman秩相关分析,表明CEA、CA199的血清浓度与TNM分期明显相关(P0.01)。结论:CEA、CA199血清浓度与TNM分期呈正相关,而年龄与CEA、CA199在各期中的浓度无明显相关性。因此,应用CEA、CA199的血清学测定在一定程度上具有预判结直肠癌TNM分期的价值。     

淋巴结转移率对胃癌预后价值的评价

目的:评价淋巴结转移率(MLR)对胃癌术后患者预后的预测价值。方法:回顾性分析2004年至2006年间在我院就诊,临床资料完整的363例胃癌术后患者。按照第七版UICC/TNM(pN分期)及淋巴结转移率两种方法对淋巴结进行分期,比较两种方法评价胃癌预后的准确性及适用性,确定MLR分期方法的特点及优势。结果:363例胃癌术后患者按单变量生存分析方法将淋巴结转移率(MLR)分为四期:MLR0(0.0%)、MLR1(0-30%)、MLR2(30-70%)、MLR3(≥70%),其5年生存率分别为84.9%、58.3%、28.7%、12.9%,有显著性统计学差异(P<0.001)。pN分期分为pN0、pN1、pN2、pN3a、pN3b,其5年生存率分别为84.9%、60.8%、32.0%、21.9%、6.8%,有显著性统计学差异(P<0.001)。单因素COX生存分析后显示,MLR分期越高,预后越差(HR:MLR1,MLR2,MLR3/MLR0=1.589,4.455,9.900,P<0.001)。按清除淋巴结个数将所有病例分成两组:group1(≤15个)、group2(>15个),在该两组中比较pN及MLR分期的预后,结果显示pN3a在group1组中的5年生存率明显低于group2组(6.2%vs.38.4%,P<0.001),而MLR分期与清除淋巴结个数无统计学生存相关差异(P>0.05)。COX比例风险模型多因素分析表明,pN分期、MLR分期、肿瘤浸润深度、肿瘤分化程度均为影响预后的独立因素,以pN及MLR分期风险比最高。结论:MLR分期是评价胃癌术后患者预后的独立因素,该方法不受淋巴结清扫个数的影响,与pN分期方法相比,实用、准确、简单,可以降低pN分期因淋巴结清扫不足造成的期别转移现象。