X-box binding protein 1 (XBP1): a potential role in chemotherapy response,clinical pathologic features,non-inflamed tumour microenvironment for breast cancer

X-box binding protein 1 (XBP1) is mainly expressed in breast cancer (BC) in human cancers. Its tumorigenesis and favourable prognosis are contradictory, and its essential role in chemotherapeutic response and immunosuppression is unknown in BC. The study firstly identified XBP1 who received neoadjuvant chemotherapy (NAC) from {"type":"entrez-geo","attrs":{"text":"GSE25055","term_id":"25055"}}GSE25055 and {"type":"entrez-geo","attrs":{"text":"GSE24460","term_id":"24460"}}GSE24460. Associations between XBP1 expression and clinicopathological characteristics was investigated using Oncomine, TCGA, UALCAN and bc-GenExMiner. The prognostic value of XBP1 was assessed using the Kaplan–Meier Plotter, bc-GenExMiner, {"type":"entrez-geo","attrs":{"text":"GSE25055","term_id":"25055"}}GSE25055, and {"type":"entrez-geo","attrs":{"text":"GSE25056","term_id":"25056"}}GSE25056. Furthermore, we systematically correlated XBP1 and immunological characteristics in the BC tumour microenvironment (TME) using TISIDB, TIMER, {"type":"entrez-geo","attrs":{"text":"GSE25055","term_id":"25055"}}GSE25055, {"type":"entrez-geo","attrs":{"text":"GSE25056","term_id":"25056"}}GSE25056 and TCGA dataset. Finally, an essential role of XBP1 in chemotherapy response was evaluated based on {"type":"entrez-geo","attrs":{"text":"GSE25055","term_id":"25055"}}GSE25055, {"type":"entrez-geo","attrs":{"text":"GSE25065","term_id":"25065"}}GSE25065, {"type":"entrez-geo","attrs":{"text":"GSE24460","term_id":"24460"}}GSE24460, {"type":"entrez-geo","attrs":{"text":"GSE5846","term_id":"5846"}}GSE5846, ROC Plotter and CELL databases. Furthermore, XBP1 mRNA expression levels were obviously highest in BC among human cancers and were significantly related to a good prognosis. In addition, XBP1 mRNA and protein levels were higher in the luminal subtype than in normal tissues and basal-like subtype, which might be attributed to membrane transport-related processes. Apart from BC, negative immunological correlations of XBP1 were not observed in other malignancies. XBP1 might shape the non-inflamed TME in BC. Finally, XBP1 expression was higher in chemo-resistive than chemo-sensitive cases, it had a predictive value and could independently predict chemotherapy response in BC patients receiving NAC. Our study suggests that the essential role of XBP1 in clinical pathologic features, non-inflamed TME, chemotherapy response in BC.     

Expression of the Genetic Suppressor Element 24.2 (GSE24.2) Decreases DNA Damage and Oxidative Stress in X-Linked Dyskeratosis Congenita Cells

The predominant X-linked form of Dyskeratosis congenita results from mutations in DKC1, which encodes dyskerin, a protein required for ribosomal RNA modification that is also a component of the telomerase complex. We have previously found that expression of an internal fragment of dyskerin ({"type":"entrez-geo","attrs":{"text":"GSE24","term_id":"24"}}GSE24.2) rescues telomerase activity in X-linked dyskeratosis congenita (X-DC) patient cells. Here we have found that an increased basal and induced DNA damage response occurred in X-DC cells in comparison with normal cells. DNA damage that is also localized in telomeres results in increased heterochromatin formation and senescence. Expression of a cDNA coding for {"type":"entrez-geo","attrs":{"text":"GSE24","term_id":"24"}}GSE24.2 rescues both global and telomeric DNA damage. Furthermore, transfection of bacterial purified or a chemically synthesized {"type":"entrez-geo","attrs":{"text":"GSE24","term_id":"24"}}GSE24.2 peptide is able to rescue basal DNA damage in X-DC cells. We have also observed an increase in oxidative stress in X-DC cells and expression of {"type":"entrez-geo","attrs":{"text":"GSE24","term_id":"24"}}GSE24.2 was able to diminish it. Altogether our data indicated that supplying {"type":"entrez-geo","attrs":{"text":"GSE24","term_id":"24"}}GSE24.2, either from a cDNA vector or as a peptide reduces the pathogenic effects of Dkc1 mutations and suggests a novel therapeutic approach.     

Circulating lncRNA UCA1 and lncRNA PGM5-AS1 act as potential diagnostic biomarkers for early-stage colorectal cancer

Background: Colorectal cancer (CRC) is one of the most common and significant malignant diseases worldwide. In the present study, we evaluated two long non-coding RNAs (lncRNAs) in CRC patients as diagnostic markers for early-stage CRC.Methods: Using Gene Expression Omnibus (GEO) datasets {"type":"entrez-geo","attrs":{"text":"GSE102340","term_id":"102340"}}GSE102340, {"type":"entrez-geo","attrs":{"text":"GSE126092","term_id":"126092"}}GSE126092, {"type":"entrez-geo","attrs":{"text":"GSE109454","term_id":"109454"}}GSE109454 and {"type":"entrez-geo","attrs":{"text":"GSE115856","term_id":"115856"}}GSE115856, 14 differentially expressed lncRNAs were identified between cancer and adjacent tissues, among which, the two most differentially expressed were confirmed using quantitative real-time polymerase chain reaction (qRT-PCR) in 200 healthy controls and 188 CRC patients. A receiver operating characteristic (ROC) analysis was employed to evaluate the diagnostic accuracy for CRC.Results: From four GEO datasets, three up-regulated and eleven down-regulated lncRNAs were identified in CRC tissues, among which, lncRNA urothelial carcinoma-associated 1 (UCA1) and lncRNA phosphoglucomutase 5-antisense RNA 1 (PGM5-AS1) were the most significantly up- and down-regulated lncRNAs in CRC patient plasma, respectively. The area under the ROC curve was calculated to be 0.766, 0.754 and 0.798 for UCA1, PGM5-AS1 and the combination of these two lncRNAs, respectively. Moreover, the diagnostic potential of these two lncRNAs was even higher for the early stages of CRC. The combination of UCA1 and PGM5-AS1 enhanced the AUC to 0.832, and when the lncRNAs were used with carcinoembryonic antigen (CEA), the AUC was further improved to 0.874.Conclusion: In the present study, we identified two lncRNAs, UCA1 and PGM5-AS1, in CRC patients’ plasma, which have the potential to be used as diagnostic biomarkers of CRC.     

Identification of potential biomarkers in dengue via integrated bioinformatic analysis

Dengue fever virus (DENV) is a global health threat that is becoming increasingly critical. However, the pathogenesis of dengue has not yet been fully elucidated. In this study, we employed bioinformatics analysis to identify potential biomarkers related to dengue fever and clarify their underlying mechanisms. The results showed that there were 668, 1901, and 8283 differentially expressed genes between the dengue-infected samples and normal samples in the {"type":"entrez-geo","attrs":{"text":"GSE28405","term_id":"28405"}}GSE28405, {"type":"entrez-geo","attrs":{"text":"GSE38246","term_id":"38246"}}GSE38246, and {"type":"entrez-geo","attrs":{"text":"GSE51808","term_id":"51808"}}GSE51808 datasets, respectively. Through overlapping, a total of 69 differentially expressed genes (DEGs) were identified, of which 51 were upregulated and 18 were downregulated. We identified twelve hub genes, including MX1, IFI44L, IFI44, IFI27, ISG15, STAT1, IFI35, OAS3, OAS2, OAS1, IFI6, and USP18. Except for IFI44 and STAT1, the others were statistically significant after validation. We predicted the related microRNAs (miRNAs) of these 12 target genes through the database miRTarBase, and finally obtained one important miRNA: has-mir-146a-5p. In addition, gene ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment were carried out, and a protein–protein interaction (PPI) network was constructed to gain insight into the actions of DEGs. In conclusion, our study displayed the effectiveness of bioinformatics analysis methods in screening potential pathogenic genes in dengue fever and their underlying mechanisms. Further, we successfully predicted IFI44L and IFI6, as potential biomarkers with DENV infection, providing promising targets for the treatment of dengue fever to a certain extent.     

Immune implication of an autophagy-related prognostic signature in uveal melanoma

Uveal Melanoma (UM) is a rare cancer deriving from melanocytes within the uvea. It has a high rate of metastasis, especially to the liver, and a poor prognosis thereafter. Autophagy, an intracellular programmed digestive process, has been associated with the development and progression of cancers, with controversial pro- and anti-tumour roles. Although previous studies have been conducted on autophagy-related genes (ARGs) in various cancer types, its role in UM requires a deeper understanding for improved diagnosis and development of novel therapeutics. In the present study, Zheng et al. used univariate Cox regression followed by least absolute shrinkage and selection operator (Lasso) regression to identify a robust 9-ARG signature prognostic of survival in a total of 230 patients with UM. The authors used the Cancer Genome Atlas (TCGA) UM cohort as a training cohort (n=80) to identify the signature and validated it in another four independent cohorts of 150 UM patients from the Gene Expression Omnibus (GEO) repository ({"type":"entrez-geo","attrs":{"text":"GSE22138","term_id":"22138"}}GSE22138, {"type":"entrez-geo","attrs":{"text":"GSE27831","term_id":"27831"}}GSE27831, {"type":"entrez-geo","attrs":{"text":"GSE44295","term_id":"44295"}}GSE44295 and {"type":"entrez-geo","attrs":{"text":"GSE84976","term_id":"84976"}}GSE84976). This 9-ARG signature was also significantly associated with the enrichment of cancer hallmarks, including angiogenesis, IL6-KJAK-STAT3 signalling, reactive oxygen species pathway and oxidative phosphorylation. More importantly, this signature is associated with immune-related functional pathways and immune cell infiltration. Thus, this 9-ARG signature predicts prognosis and provides deeper insights into the immune mechanisms in UM, with potential implications for future immunotherapy.     

Up‐regulated SAMD9L modulated by TLR2 and HIF‐1α as a promising biomarker in tuberculosis

The aim of this study was to identify potential biomarkers of TB in blood and determine their function in Mtb‐infected macrophages. First of all, WGCNA was used to analyse 9451 genes with significant changes in TB patients’ whole blood. The 220 interferon‐γ‐related genes were identified, and then 30 key genes were screened using Cytoscape. Then, the AUC values of key genes were calculated to further narrow the gene range. Finally, we identified 9 genes from {"type":"entrez-geo","attrs":{"text":"GSE19444","term_id":"19444"}}GSE19444. ROC analysis showed that SAMD9L, among 9 genes, had a high diagnostic value (AUC = 0.925) and a differential diagnostic value (AUC>0.865). To further narrow down the range of DEGs, the top 10 hub‐connecting genes were screened from monocytes ({"type":"entrez-geo","attrs":{"text":"GSE19443","term_id":"19443"}}GSE19443). Finally, we obtained 4 genes (SAMD9L, GBP1, GBP5 and STAT1) by intersections of genes from monocytes and whole blood. Among them, it was found that the function of SAMD9L was unknown after data review, so this paper studied this gene. Our results showed that SAMD9L is up‐regulated and suppresses cell necrosis, and might be regulated by TLR2 and HIF‐1α during Mtb infection. In addition, miR‐181b‐5p is significantly up‐regulated in the peripheral blood plasma of tuberculosis patients, which has a high diagnostic value (AUC = 0.969).     

Structural Variation-Associated Expression Changes Are Paralleled by Chromatin Architecture Modifications

Copy number variants (CNVs) influence the expression of genes that map not only within the rearrangement, but also to its flanks. To assess the possible mechanism(s) underlying this “neighboring effect”, we compared intrachromosomal interactions and histone modifications in cell lines of patients affected by genomic disorders and control individuals. Using chromosome conformation capture (4C-seq), we observed that a set of genes flanking the Williams-Beuren Syndrome critical region (WBSCR) were often looping together. The newly identified interacting genes include AUTS2, mutations of which are associated with autism and intellectual disabilities. Deletion of the WBSCR disrupts the expression of this group of flanking genes, as well as long-range interactions between them and the rearranged interval. We also pinpointed concomitant changes in histone modifications between samples.We conclude that large genomic rearrangements can lead to chromatin conformation changes that extend far away from the structural variant, thereby possibly modulating expression globally and modifying the phenotype.GEO Series accession number: {"type":"entrez-geo","attrs":{"text":"GSE33784","term_id":"33784"}}GSE33784, {"type":"entrez-geo","attrs":{"text":"GSE33867","term_id":"33867"}}GSE33867.     

Single-cell transcriptomics analysis reveals intratumoral heterogeneity and identifies a gene signature associated with prognosis of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) tumors exhibit high heterogeneity. However, current understanding of tumor cell heterogeneity of HCC and the association with prognosis remains very limited. In the present study, we collected and examined tumor tissue from one HCC patient by single-cell RNA sequencing (scRNA-seq). We identified 5753 cells and 16 clusters including hepatocytes/cancer cells, T cells, macrophages, endothelial cells, fibroblasts, NK cells, neutrophils, and B cells. In six tumor cell subclusters, we identified a cluster of proliferative tumor cells associated with poor prognosis. We downloaded scRNA-seq data of {"type":"entrez-geo","attrs":{"text":"GSE125449","term_id":"125449"}}GSE125449 from the NCBI-GEO as validation dataset, and found that a cluster of hepatocytes exhibited high proliferation activity in HCC. Furthermore, we identified a gene signature related to the proliferation of HCC cells. This gene signature is efficient to classify HCC patients into two groups with distinct prognosis in both TCGA and ICGC database cohorts. Our results reveal the intratumoral heterogeneity of HCC at single cell level and identify a gene signature associated with HCC prognosis.     

TGF-β-induced PLEK2 promotes metastasis and chemoresistance in oesophageal squamous cell carcinoma by regulating LCN2

Oesophageal squamous cell carcinoma (ESCC) has a relatively unfavourable prognosis due to metastasis and chemoresistance. Our previous research established a comprehensive ESCC database ({"type":"entrez-geo","attrs":{"text":"GSE53625","term_id":"53625"}}GSE53625). After analysing data from TCGA database and {"type":"entrez-geo","attrs":{"text":"GSE53625","term_id":"53625"}}GSE53625, we found that PLEK2 predicted poor prognosis in ESCC. Moreover, PLEK2 expression was also related to the overall survival of ESCC patients undergoing chemotherapy. Repression of PLEK2 decreased the proliferation, migration, invasion and chemoresistance of ESCC cells in vitro and decreased tumorigenicity and distant metastasis in vivo. Mechanistically, luciferase reporter assay and chromatin immunoprecipitation assay suggested that TGF-β stimulated the process that Smad2/3 binds to the promoter sequences of PLEK2 and induced its expression. RNA-seq suggested LCN2 might a key molecular regulated by PLEK2. LCN2 overexpression in PLEK2 knockdown ESCC cells reversed the effects of decreased migration and invasion. In addition, TGF-β induced the expression of LCN2, but the effect disappeared when PLEK2 was knockdown. Moreover, AKT was phosphorylated in all regulatory processes. This study detected the major role of PLEK2 in driving metastasis and chemoresistance in ESCC by regulating LCN2, which indicates the potential use of PLEK2 as a biomarker to predict prognosis and as a therapeutic target for ESCC.Subject terms: Cancer, Molecular biology     

A 16-Gene Signature Distinguishes Anaplastic Astrocytoma from Glioblastoma

Anaplastic astrocytoma (AA; Grade III) and glioblastoma (GBM; Grade IV) are diffusely infiltrating tumors and are called malignant astrocytomas. The treatment regimen and prognosis are distinctly different between anaplastic astrocytoma and glioblastoma patients. Although histopathology based current grading system is well accepted and largely reproducible, intratumoral histologic variations often lead to difficulties in classification of malignant astrocytoma samples. In order to obtain a more robust molecular classifier, we analysed RT-qPCR expression data of 175 differentially regulated genes across astrocytoma using Prediction Analysis of Microarrays (PAM) and found the most discriminatory 16-gene expression signature for the classification of anaplastic astrocytoma and glioblastoma. The 16-gene signature obtained in the training set was validated in the test set with diagnostic accuracy of 89%. Additionally, validation of the 16-gene signature in multiple independent cohorts revealed that the signature predicted anaplastic astrocytoma and glioblastoma samples with accuracy rates of 99%, 88%, and 92% in TCGA, {"type":"entrez-geo","attrs":{"text":"GSE1993","term_id":"1993"}}GSE1993 and {"type":"entrez-geo","attrs":{"text":"GSE4422","term_id":"4422"}}GSE4422 datasets, respectively. The protein-protein interaction network and pathway analysis suggested that the 16-genes of the signature identified epithelial-mesenchymal transition (EMT) pathway as the most differentially regulated pathway in glioblastoma compared to anaplastic astrocytoma. In addition to identifying 16 gene classification signature, we also demonstrated that genes involved in epithelial-mesenchymal transition may play an important role in distinguishing glioblastoma from anaplastic astrocytoma.     

Identification of potential genes related to breast cancer brain metastasis in breast cancer patients

Brain metastases (BMs) usually develop in breast cancer (BC) patients. Thus, the molecular mechanisms of breast cancer brain metastasis (BCBM) are of great importance in designing therapeutic strategies to treat or prevent BCBM. The present study attempted to identify novel diagnostic and prognostic biomarkers of BCBM. Two datasets ({"type":"entrez-geo","attrs":{"text":"GSE125989","term_id":"125989"}}GSE125989 and {"type":"entrez-geo","attrs":{"text":"GSE100534","term_id":"100534"}}GSE100534) were obtained from the Gene Expression Omnibus (GEO) database to find differentially expressed genes (DEGs) in cases of BC with and without brain metastasis (BM). A total of 146 overlapping DEGs, including 103 up-regulated and 43 down-regulated genes, were identified. Functional enrichment analysis showed that these DEGs were mainly enriched for functions including extracellular matrix (ECM) organization and collagen catabolic fibril organization. Using protein–protein interaction (PPI) and principal component analysis (PCA) analysis, we identified ten key genes, including LAMA4, COL1A1, COL5A2, COL3A1, COL4A1, COL5A1, COL5A3, COL6A3, COL6A2, and COL6A1. Additionally, COL5A1, COL4A1, COL1A1, COL6A1, COL6A2, and COL6A3 were significantly associated with the overall survival of BC patients. Furthermore, COL6A3, COL5A1, and COL4A1 were potentially correlated with BCBM in human epidermal growth factor 2 (HER2) expression. Additionally, the miR-29 family might participate in the process of metastasis by modulating the cancer microenvironment. Based on datasets in the GEO database, several DEGs have been identified as playing potentially important roles in BCBM in BC patients.     

Gene-expression signature predicts postoperative recurrence in stage I non-small cell lung cancer patients

About 30% stage I non-small cell lung cancer (NSCLC) patients undergoing resection will recur. Robust prognostic markers are required to better manage therapy options. The purpose of this study is to develop and validate a novel gene-expression signature that can predict tumor recurrence of stage I NSCLC patients. Cox proportional hazards regression analysis was performed to identify recurrence-related genes and a partial Cox regression model was used to generate a gene signature of recurrence in the training dataset −142 stage I lung adenocarcinomas without adjunctive therapy from the Director''s Challenge Consortium. Four independent validation datasets, including {"type":"entrez-geo","attrs":{"text":"GSE5843","term_id":"5843"}}GSE5843, {"type":"entrez-geo","attrs":{"text":"GSE8894","term_id":"8894"}}GSE8894, and two other datasets provided by Mayo Clinic and Washington University, were used to assess the prediction accuracy by calculating the correlation between risk score estimated from gene expression and real recurrence-free survival time and AUC of time-dependent ROC analysis. Pathway-based survival analyses were also performed. 104 probesets correlated with recurrence in the training dataset. They are enriched in cell adhesion, apoptosis and regulation of cell proliferation. A 51-gene expression signature was identified to distinguish patients likely to develop tumor recurrence (Dxy = −0.83, P<1e-16) and this signature was validated in four independent datasets with AUC >85%. Multiple pathways including leukocyte transendothelial migration and cell adhesion were highly correlated with recurrence-free survival. The gene signature is highly predictive of recurrence in stage I NSCLC patients, which has important prognostic and therapeutic implications for the future management of these patients.     

Age-related DNA methylation in normal breast tissue and its relationship with invasive breast tumor methylation

Age is a key risk factor for breast cancer and epigenetic alterations may contribute to age-related increases in breast cancer risk, though the relation of age-related methylation in normal breast tissues with altered methylation in breast tumors is unclear. We investigated the relation of age with DNA methylation in normal breast tissues genome-wide using two data sets from the Gene Expression Omnibus (GEO) database ({"type":"entrez-geo","attrs":{"text":"GSE32393","term_id":"32393"}}GSE32393 and {"type":"entrez-geo","attrs":{"text":"GSE31979","term_id":"31979"}}GSE31979). We validated our observations in an independent set of normal breast tissues, examined age-related methylation in normal breast for enrichment of genomic features, and compared age-related methylation in normal tissue with methylation alterations in breast tumors. Between the two array-based methylation data sets, there were 204 CpG loci with significant (P < 0.05) and consistent age-related methylation, 97% of which were increases in methylation. Our validation sets confirmed the direction of age-related DNA methylation changes in all measured regions. Among the 204 age-related CpG loci, we observed a significant enrichment for CpG islands (P = 8.7E-6) and polycomb group protein target genes (P = 0.03). In addition, 24 of the 204 CpGs with age-related methylation in normal breast were significantly differentially methylated between normal and breast tumor tissues. We identified consistent age-related methylation changes in normal breast tissue that are further altered in breast tumors and may represent early events contributing to breast carcinogenesis. This work identifies age-related methylation in normal breast tissue and begins to deconstruct the contribution of aging to epigenetic alterations present in breast tumors.     

Modeling Oncogenic Signaling in Colon Tumors by Multidirectional Analyses of Microarray Data Directed for Maximization of Analytical Reliability

Background

Clinical progression of colorectal cancers (CRC) may occur in parallel with distinctive signaling alterations. We designed multidirectional analyses integrating microarray-based data with biostatistics and bioinformatics to elucidate the signaling and metabolic alterations underlying CRC development in the adenoma-carcinoma sequence.

Methodology/Principal Findings

Studies were performed on normal mucosa, adenoma, and carcinoma samples obtained during surgery or colonoscopy. Collections of cryostat sections prepared from the tissue samples were evaluated by a pathologist to control the relative cell type content. The measurements were done using Affymetrix GeneChip HG-U133plus2, and probe set data was generated using two normalization algorithms: MAS5.0 and GCRMA with least-variant set (LVS). The data was evaluated using pair-wise comparisons and data decomposition into singular value decomposition (SVD) modes. The method selected for the functional analysis used the Kolmogorov-Smirnov test. Expressional profiles obtained in 105 samples of whole tissue sections were used to establish oncogenic signaling alterations in progression of CRC, while those representing 40 microdissected specimens were used to select differences in KEGG pathways between epithelium and mucosa. Based on a consensus of the results obtained by two normalization algorithms, and two probe set sorting criteria, we identified 14 and 17 KEGG signaling and metabolic pathways that are significantly altered between normal and tumor samples and between benign and malignant tumors, respectively. Several of them were also selected from the raw microarray data of 2 recently published studies ({"type":"entrez-geo","attrs":{"text":"GSE4183","term_id":"4183"}}GSE4183 and {"type":"entrez-geo","attrs":{"text":"GSE8671","term_id":"8671"}}GSE8671).

Conclusion/Significance

Although the proposed strategy is computationally complex and labor–intensive, it may reduce the number of false results.     

Doubly Optimized Calibrated Support Vector Machine (DOC-SVM): An Algorithm for Joint Optimization of Discrimination and Calibration

Historically, probabilistic models for decision support have focused on discrimination, e.g., minimizing the ranking error of predicted outcomes. Unfortunately, these models ignore another important aspect, calibration, which indicates the magnitude of correctness of model predictions. Using discrimination and calibration simultaneously can be helpful for many clinical decisions. We investigated tradeoffs between these goals, and developed a unified maximum-margin method to handle them jointly. Our approach called, Doubly Optimized Calibrated Support Vector Machine (DOC-SVM), concurrently optimizes two loss functions: the ridge regression loss and the hinge loss. Experiments using three breast cancer gene-expression datasets (i.e., {"type":"entrez-geo","attrs":{"text":"GSE2034","term_id":"2034"}}GSE2034, {"type":"entrez-geo","attrs":{"text":"GSE2990","term_id":"2990"}}GSE2990, and Chanrion''s datasets) showed that our model generated more calibrated outputs when compared to other state-of-the-art models like Support Vector Machine ( = 0.03,  = 0.13, and <0.001) and Logistic Regression ( = 0.006,  = 0.008, and <0.001). DOC-SVM also demonstrated better discrimination (i.e., higher AUCs) when compared to Support Vector Machine ( = 0.38,  = 0.29, and  = 0.047) and Logistic Regression ( = 0.38,  = 0.04, and <0.0001). DOC-SVM produced a model that was better calibrated without sacrificing discrimination, and hence may be helpful in clinical decision making.