Classification and regression trees are machine-learning methods for constructing prediction models from data. The models are obtained by recursively partitioning the data space and fitting a simple prediction model within each partition. As a result, the partitioning can be represented graphically as a decision tree. Classification trees are designed for dependent variables that take a finite number of unordered values, with prediction error measured in terms of misclassification cost. Regression trees are for dependent variables that take continuous or ordered discrete values, with prediction error typically measured by the squared difference between the observed and predicted values. This article gives an introduction to the subject by reviewing some widely available algorithms and comparing their capabilities, strengths, and weakness in two examples. © 2011 John Wiley & Sons, Inc. WIREs Data Mining Knowl Discov 2011 1 14-23 DOI: 10.1002/widm.8

This article is categorized under: 

Technologies > Classification
Technologies > Machine Learning
Technologies > Prediction
Technologies > Statistical Fundamentals

/pdf/classification-and-regression-trees-1td8f8b4ru.pdf

Classification and regression trees

EASL-EORTC clinical practice guidelines : management of hepatocellular carcinoma

BackgroundSomatic mutations have the potential to encode “non-self” immunogenic antigens. We hypothesized that tumors with a large number of somatic mutations due to mismatch-repair defects may be susceptible to immune checkpoint blockade. MethodsWe conducted a phase 2 study to evaluate the clinical activity of pembrolizumab, an anti–programmed death 1 immune checkpoint inhibitor, in 41 patients with progressive metastatic carcinoma with or without mismatch-repair deficiency. Pembrolizumab was administered intravenously at a dose of 10 mg per kilogram of body weight every 14 days in patients with mismatch repair–deficient colorectal cancers, patients with mismatch repair–proficient colorectal cancers, and patients with mismatch repair–deficient cancers that were not colorectal. The coprimary end points were the immune-related objective response rate and the 20-week immune-related progression-free survival rate. ResultsThe immune-related objective response rate and immune-related progression-free survival ...

/pdf/pd-1-blockade-in-tumors-with-mismatch-repair-deficiency-1eb0ztv7j7.pdf

PD-1 Blockade in Tumors with Mismatch-Repair Deficiency

Background Intratumor heterogeneity may foster tumor evolution and adaptation and hinder personalized-medicine strategies that depend on results from single tumor-biopsy samples. Methods To examine intratumor heterogeneity, we performed exome sequencing, chromosome aberration analysis, and ploidy profiling on multiple spatially separated samples obtained from primary renal carcinomas and associated metastatic sites. We characterized the consequences of intratumor heterogeneity using immunohistochemical analysis, mutation functional analysis, and profiling of messenger RNA expression. Results Phylogenetic reconstruction revealed branched evolutionary tumor growth, with 63 to 69% of all somatic mutations not detectable across every tumor region. Intratumor heterogeneity was observed for a mutation within an autoinhibitory domain of the mammalian target of rapamycin (mTOR) kinase, correlating with S6 and 4EBP phosphorylation in vivo and constitutive activation of mTOR kinase activity in vitro. Mutational intratumor heterogeneity was seen for multiple tumor-suppressor genes converging on loss of function; SETD2, PTEN, and KDM5C underwent multiple distinct and spatially separated inactivating mutations within a single tumor, suggesting convergent phenotypic evolution. Gene-expression signatures of good and poor prognosis were detected in different regions of the same tumor. Allelic composition and ploidy profiling analysis revealed extensive intratumor heterogeneity, with 26 of 30 tumor samples from four tumors harboring divergent allelic-imbalance profiles and with ploidy heterogeneity in two of four tumors. Conclusions Intratumor heterogeneity can lead to underestimation of the tumor genomics landscape portrayed from single tumor-biopsy samples and may present major challenges to personalized-medicine and biomarker development. Intratumor heterogeneity, associated with heterogeneous protein function, may foster tumor adaptation and therapeutic failure through Darwinian selection. (Funded by the Medical Research Council and others.)

http://www.therenegadecell.com/wiki/images/0/0d/NEJM-2012-366%2810%29-883.pdf

Intratumor heterogeneity and branched evolution revealed by multiregion sequencing.

Over the past decade, comprehensive sequencing efforts have revealed the genomic landscapes of common forms of human cancer. For most cancer types, this landscape consists of a small number of “mountains” (genes altered in a high percentage of tumors) and a much larger number of “hills” (genes altered infrequently). To date, these studies have revealed ~140 genes that, when altered by intragenic mutations, can promote or “drive” tumorigenesis. A typical tumor contains two to eight of these “driver gene” mutations; the remaining mutations are passengers that confer no selective growth advantage. Driver genes can be classified into 12 signaling pathways that regulate three core cellular processes: cell fate, cell survival, and genome maintenance. A better understanding of these pathways is one of the most pressing needs in basic cancer research. Even now, however, our knowledge of cancer genomes is sufficient to guide the development of more effective approaches for reducing cancer morbidity and mortality.

/pdf/cancer-genome-landscapes-qmge4i5y2h.pdf

Cancer Genome Landscapes

// Changhoon Yoo 1 , Jihoon Kang 1 , Deokhoon Kim 2 , Kyu-Pyo Kim 1 , Baek-Yeol Ryoo 1 , Seung-Mo Hong 3 , Jung Jin Hwang 4 , Seong-Yun Jeong 4 , Shin Hwang 5 , Ki-Hun Kim 5 , Young-Joo Lee 5 , Klaus P. Hoeflich 6 , Oleg Schmidt-Kittler 6 , Stephen Miller 6 , Eun Kyung Choi 4, 7 1 Department of Oncology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea 2 Asan Institute for Life Science, University of Ulsan College of Medicine, Seoul, Korea 3 Department of Pathology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea 4 Institute for Innovative Cancer Research, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea 5 Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea 6 Blueprint Medicines Corporation, Cambridge, Massachusetts, USA 7 Department of Radiation Oncology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea Correspondence to: Kyu-Pyo Kim, email: kkp1122@amc.seoul.kr Keywords: cholangiocarcinoma, intrahepatic, FGF19, FGFR4 Received: February 08, 2017      Accepted: March 20, 2017      Published: April 07, 2017 ABSTRACT Background: The fibroblast growth factor receptor 4 (FGFR4) pathway is an essential regulatory component of bile acid synthesis, and its relationship with hepatocellular carcinoma (HCC) has been reported. We investigated the gene expression and clinical significance of FGFR4 and related pathways in intrahepatic cholangiocarcinoma (iCCA). Results: The median age was 56 years (range 30–78) and 34 patients (74%) were male. Six patients (13%) had hepatitis B virus infection, with or without liver cirrhosis. Overall survival was significantly associated with FGFR4 ( p = 0.004), FGF19 ( p = 0.047), FGF21 ( p = 0.04), and KLB ( p = 0.03) expression. In the multivariate analysis with potential prognostic factors, high expression of FGF19 , FGF21 , and FGFR4 was significantly associated with better survival. In the analysis using the TCGA iCCA dataset, mRNA overexpression of at least 1 of the FGFR4-related genes was significantly associated with better disease-free survival ( p = 0.02). Materials and Methods: We assessed the expression of 98 genes in formalin-fixed paraffin embedded tumor tissue specimens from 46 patients with surgically resected iCCA using a NanoString platform. This included 10 FGF pathway genes (e.g. FGFR1-4, KLB, FGF3, 4, 19, 21, and 23 ), 19 distal marker genes (e.g. CYP7A1 and CYP17A1 ), 31 genes relevant to HCC and iCCA (e.g. AFP , TS ), 18 copy number variation matched genes, and 20 control genes. Log-transformation of gene expression was performed for normalization and statistical analysis. Overall survival was correlated with gene expression (< median vs. ≥ median) using a log-rank test. The prognostic impact of FGFR4-related genes was validated using the public TCGA dataset for iCCA. Conclusions: Our results indicate that mRNA expression of FGFR4-related genes may be a biomarker to define the distinctive molecular phenotype of iCCA. Future preclinical and clinical validation is required to define the role of the FGFR4 pathway in iCCA.

/pdf/multiplexed-gene-expression-profiling-identifies-the-fgfr4-1aoqhixfvp.pdf

Multiplexed gene expression profiling identifies the FGFR4 pathway as a novel biomarker in intrahepatic cholangiocarcinoma

Median linear regression modeling is a natural approach for analyzing censored survival or failure time data. A median linear model lends itself to a simple interpretation that is particularly suitable for making direct predictions of survival or failure times. We propose a new, unique, and efficient algorithm for tree-structured median regression modeling that combines the merits of both a median regression model and a tree-structured model. We propose and discuss loss functions for constructing this tree-structured median model and investigate their effects on the determination of tree size. We also propose a split covariate selection algorithm by using residual analysis (RA) rather than loss function reduction. The RA approach allows for the selection of the correct split covariate fairly well, regardless of the distribution of covariates. The loss function with the transformed data performs well in comparison to that with raw or uncensored data in determining the right tree size. Unlike other survival trees, the proposed median regression tree is useful in directly predicting survival or failure times for partitioned homogeneous patient groups as well as in revealing and interpreting complex covariate structures. Furthermore, a median regression tree can be easily generalized to a quantile regression tree with a user-chosen quantile between 0 and 1. We have demonstrated the proposed method with two real data sets and have compared the results with existing regression trees.

Median Regression Tree for Analysis of Censored Survival Data

Neuroendocrine differentiation in extrahepatic bile duct carcinomas and its prognostic significance

To evaluate thread sign of biliary intraductal papillary mucinous neoplasm (B-IPMN) on magnetic resonance imaging (MRI). Thread sign was defined as intraductal linear or curvilinear hypointense striations. Two radiologists independently evaluated the presence and location of thread sign on MR cholangiography (thin-slice, thick-slab and 3D MRC) and axial MR images (T2 TSE, T2 HASTE and DWI) in patients with B-IPMN (n = 38) and in matched control groups with benign (n = 36) or malignant (n = 35) biliary diseases. Sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) of thread sign for diagnosing B-IPMN were evaluated. Thread sign was observed only in patients with B-IPMN on MRC (44.7–52.6 % [17/38–20/38], P < 0.001) and axial MR images (31.6 % [12/38], P < 0.001), except in one patient with recurrent pyogenic cholangitis on MRC (2.8 %, 1/36). The sensitivity, specificity, accuracy, PPV and NPV of thread sign for diagnosing B-IPMN on MRC were 0.53, 0.99, 0.83, 0.95 and 0.80, respectively (reader 1) and 0.45, 1.0, 0.81, 1.0 and 0.77, respectively (reader 2). Thread sign was detected mainly at the extrahepatic bile duct (52.6 %, 20/38). B-IPMN can manifest thread sign, a novel specific MR finding, mainly at the extrahepatic bile duct on MRI, especially on MRC. • Some B-IPMNs manifest thread sign within the bile ducts on MRI.
 • Thread sign is a highly specific finding for B-IPMN on MRI.
 • MRC is superior to axial T2WI and DWI for detecting thread sign.

Thread sign in biliary intraductal papillary mucinous neoplasm: a novel specific finding for MRI.

Objective To investigate the characteristic radiologic features of post-ischemic stricture, which can then be implemented to differentiate that specific disease from other similar bowel diseases, with an emphasis on computed tomography (CT) features. Materials and methods Eight patients with a diagnosis of ischemic bowel disease, who were also diagnosed with post-ischemic stricture on the basis of clinical or pathologic findings, were included. Detailed clinical data was collected from the available electronic medical records. Two radiologists retrospectively reviewed all CT images. Pathologic findings were also analyzed. Results The mean interval between the diagnosis of ischemic bowel disease and stricture formation was 57 days. The severity of ischemic bowel disease was variable. Most post-ischemic strictures developed in the ileum (n = 5), followed by the colon (n = 2) and then the jejunum (n = 1). All colonic strictures developed in the "watershed zone." The pathologic features of post-ischemic stricture were deep ulceration, submucosal/subserosal fibrosis and chronic transmural inflammation. The mean length of the post-ischemic stricture was 7.4 cm. All patients in this study possessed one single stricture. On contrast-enhanced CT, most strictures possessed concentric wall thickening (87.5%), with moderate enhancement (87.5%), mucosal enhancement (50%), or higher enhancement in portal phase than arterial phase (66.7%). Conclusion Post-ischemic strictures develop in the ileum, jejunum and colon after an interval of several weeks. In the colonic segment, strictures mainly occur in the "watershed zone." Typical CT findings include a single area of concentric wall thickening of medium length (mean, 7.4 cm), with moderate and higher enhancement in portal phase and vasa recta prominence.

/pdf/post-ischemic-bowel-stricture-ct-features-in-eight-cases-59x2cio0wp.pdf

Seung-Mo Hong

Papers

Multiplexed gene expression profiling identifies the FGFR4 pathway as a novel biomarker in intrahepatic cholangiocarcinoma

Median Regression Tree for Analysis of Censored Survival Data

Neuroendocrine differentiation in extrahepatic bile duct carcinomas and its prognostic significance

Thread sign in biliary intraductal papillary mucinous neoplasm: a novel specific finding for MRI.

Post-Ischemic Bowel Stricture: CT Features in Eight Cases.