Using cross-validation to evaluate predictive accuracy of survival risk classifiers based on high-dimensional data

Bioinformatics analysis of PSAT1 loss identifies downstream pathways regulated in EGFR mutant NSCLC and a selective gene signature for predicting the risk of relapse

The majority of malignant tumors exhibit an altered metabolic phenotype that ultimately provides the required energy and molecular precursors necessary for unregulated cell division. Within this, phosphoserine aminotransferase 1 (PSAT1) is involved in de novo serine biosynthesis and its activity promotes various biochemical processes, including one-carbon metabolism. It also directly generates α-ketoglutarate (α-KG), a Kreb cycle intermediate and epigenetic-regulating metabolite. Prior studies examining PSAT1 depletion have identified individual affected downstream pathways, such as GSK3β and E2F, in several cancer types, including non-small-cell lung cancer (NSCLC). However, global gene expression examination in response to PSAT1 loss, particularly in EGFR mutant NSCLC, has not been unexplored. Transcriptional profiling of EGFR mutant NSCLC cells with or without stable knock-down of PSAT1 identified differentially expressed genes (DEGs) enriched in several metabolic pathways required for cell division, including amino acid and nucleotide biosynthesis. Supplementation studies involving non-essential amino acids, nucleosides and α-KG partially restored defects in anchorage-independent growth due to the knockdown of PSAT1. Kyoto Encyclopedia of Genes and Genomes and Gene Ontology enrichment analysis identified potential impacts on actin cytoskeleton arrangement and β-catenin activity, which were rescued by PSAT1 re-expression. Finally, a comparative analysis of PSAT1 DEGs against transcripts enriched in patient EGFR mutant lung tumors identified a gene signature that is associated with overall and relapse-free survival (RFS) and was able to distinguish low or high-risk populations for RFS in early-stage EGFR mutant NSCLC. Overall, investigating genes altered by PSAT1 loss confirmed known PSAT1-regulated cellular pathways, identified a previously unknown role in the mediation of cytoskeleton arrangement in EGFR mutant NSCLC cells and allowed for the characterization of a gene signature with putative predictive potential for RFS in early-stage disease.

Circulating cell-free and extracellular vesicles-derived microRNA as prognostic biomarkers in patients with early-stage NSCLC: results from RESTING study

BACKGROUND

Factors to accurately stratify patients with early-stage non-small cell lung cancer (NSCLC) in different prognostic groups are still needed. This study aims to investigate 1) the prognostic potential of circulating cell-free (CF) and extracellular vesicles (EVs)-derived microRNA (miRNAs), and 2) their added value with respect to known prognostic factors (PFs).

METHODS

The RESTING study is a multicentre prospective observational cohort study on resected stage IA-IIIA patients with NSCLC. The primary end-point was disease-free survival (DFS), and the main analyses were carried out separately for CF- and EV-miRNAs. CF- and EV-miRNAs were isolated from plasma, and miRNA-specific libraries were prepared and sequenced. To reach the study aims, three statistical models were specified: one using the miRNA data only (Model 1); one using both miRNAs and known PFs (age, gender, and pathological stage) (Model 2), and one using the PFs alone (Model 3). Five-fold cross-validation (CV) was used to assess the predictive performance of each. Standard Cox regression and elastic net regularized Cox regression were used.

RESULTS

A total of 222 patients were enrolled. The median follow-up time was 26.3 (95% CI 25.4-27.6) months. From Model 1, three CF-miRNAs and 21 EV-miRNAs were associated with DFS. In Model 2, two CF-miRNAs (miR-29c-3p and miR-877-3p) and five EV-miRNAs (miR-181a-2-3p, miR-182-5p, miR-192-5p, miR-532-3p and miR-589-5p) remained associated with DFS. From pathway enrichment analysis, TGF-beta and NOTCH were the most involved pathways.

CONCLUSION

This study identified promising prognostic CF- and EV-miRNAs that could be used as a non-invasive, cost-effective tool to aid clinical decision-making. However, further evaluation of the obtained miRNAs in an external cohort of patients is warranted.

Risk Factors and Nomogram Model for Hepatocellular Carcinoma Development in Chronic Hepatitis B Patients with Low-Level Viremia

Background and aim: Patients with chronic hepatitis B patients (CHB) with low-level viremia (LLV) are not necessarily at low risk of developing hepatocellular carcinoma (HCC). The question of whether CHB patients with LLV require immediate antiviral agent (AVT) or long-term AVT remains controversial. The study aims to investigate the risk of HCC development and the risk factors in CHB patients with LLV and construct a nomogram model predicting the risk of HCC. Methods: We conducted a retrospective cohort study that enrolled 16,895 CHB patients from January 2008 to December 2020. The patients were divided into three groups for comparison: the LLV group, maintained virological response (MVR) group and HBV-DNA>2000 group. The cumulative incidence of progression to HCC was assessed. Cox regression analysis was performed to determine the final risk factors, and a nomogram model was constructed. The 10-fold Cross-Validation method was utilized for internal validation. Results: A total of 408 new cases of HCC occurred during the average follow-up period of 5.78 years. The 3, 5, and 10-year cumulative HCC risks in the LLV group were 3.56%, 4.96%, and 9.51%, respectively. There was a significant difference in the cumulative risk of HCC between the HBV-DNA level > 2000 IU/mL and LLV groups (p = 0.049). Independent risk factors for HCC development in LLV group included male gender, age, presence of cirrhosis, and platelets count. The Area Under the Curve (AUC) values for the 3-year and 5-year prediction from our HCC risk prediction model were 0.75 and 0.76, respectively. Conclusion: Patients with LLV and MVR are still at risk for developing HCC. The nomogram established for CHB patient with LLV, incorporating identified significant risk factors, serves as an effective tool for predicting HCC-free outcomes. This nomogram model provides valuable information for determining appropriate surveillance strategies and prescribing AVT.

C-reactive protein as robust laboratory value associated with prognosis in patients with stage III non-small cell lung cancer (NSCLC) treated with definitive radiochemotherapy

To evaluate the prognostic value of biomarkers from peripheral blood obtained as routine laboratory assessment for overall survival in a cohort of stage III non-small cell lung cancer (NSCLC) patients treated with definitive radiochemotherapy at a high-volume cancer center. Seven blood biomarkers from 160 patients treated with definitive radiochemotherapy for stage III NSCLC were analyzed throughout the course treatment. Parameters were preselected using univariable and multivariable proportional hazards analysis and were assessed for internal validity using leave-one-out cross validation. Cross validated classifiers including biomarkers in addition to important clinical parameters were compared with classifiers containing the clinical parameters alone. An increased C-reactive protein (CRP) value in the final week of radiotherapy was found as a prognostic factor for overall survival, both as a continuous (HR 1.099 (1.038-1.164), p < 0.0012) as well as categorical variable splitting data at the median value of 1.2 mg/dl (HR 2.214 (1.388-3.531), p < 0.0008). In the multivariable analysis, the CRP value-maintained significance with an HR of 1.105 (1.040-1.173) and p-value of 0.0012. The cross validated classifier using CRP at the end of radiotherapy in addition to clinical parameters separated equally sized high and low risk groups more distinctly than a classifier containing the clinical parameters alone (HR = 2.786 (95% CI 1.686-4.605) vs. HR = 2.287 (95% CI 1.407-3.718)). Thus, the CRP value at the end of radiation therapy has successfully passed the crucial cross-validation test. The presented data on CRP levels suggests that inflammatory markers may become increasingly important during definitive radiochemotherapy, particularly with the growing utilization of immunotherapy as a consolidation therapy for stage III NSCLC.

HER2 quantitative continuous scoring for accurate patient selection in HER2 negative trastuzumab deruxtecan treated breast cancer

Many targeted cancer therapies rely on biomarkers assessed by scoring of immunohistochemically (IHC)-stained tissue, which is subjective, semiquantitative, and does not account for expression heterogeneity. We describe an image analysis-based method for quantitative continuous scoring (QCS) of digital whole-slide images acquired from baseline human epidermal growth factor receptor 2 (HER2) IHC-stained breast cancer tissue. Candidate signatures for patient stratification using QCS of HER2 expression on subcellular compartments were identified, addressing the spatial distribution of tumor cells and tumor-infiltrating lymphocytes. Using data from trastuzumab deruxtecan-treated patients with HER2-positive and HER2-negative breast cancer from a phase 1 study (NCT02564900; DS8201-A-J101; N = 151), QCS-based patient stratification showed longer progression-free survival (14.8 vs 8.6 months) with higher prevalence of patient selection (76.4 vs 56.9%) and a better cross-validated log-rank p value (0.026 vs 0.26) than manual scoring based on the American Society of Clinical Oncology / College of American Pathologists guidelines. QCS-based features enriched the HER2-negative subgroup by correctly predicting 20 of 26 responders.

An integrated radiology-pathology machine learning classifier for outcome prediction following radical prostatectomy: Preliminary findings

Objectives

To evaluate the added benefit of integrating features from pre-treatment MRI (radiomics) and digitized post-surgical pathology slides (pathomics) in prostate cancer (PCa) patients for prognosticating outcomes post radical-prostatectomy (RP) including a) rising prostate specific antigen (PSA), and b) extraprostatic-extension (EPE).

Methods

Multi-institutional data (N = 58) of PCa patients who underwent pre-treatment 3-T MRI prior to RP were included in this retrospective study. Radiomic and pathomic features were extracted from PCa regions on MRI and RP specimens delineated by expert clinicians. On training set (D1, N = 44), Cox Proportional-Hazards models MR, MP and MRaP were trained using radiomics, pathomics, and their combination, respectively, to prognosticate rising PSA (PSA > 0.03 ng/mL). Top features from MRaP were used to train a model to predict EPE on D1 and test on external dataset (D2, N = 14). C-index, Kalplan-Meier curves were used for survival analysis, and area under ROC (AUC) was used for EPE. MRaP was compared with the existing post-treatment risk-calculator, CAPRA (MC).

Results

Patients had median follow-up of 34 months. MRaP (c-index = 0.685 ± 0.05) significantly outperformed MR (c-index = 0.646 ± 0.05), MP (c-index = 0.631 ± 0.06) and MC (c-index = 0.601 ± 0.071) (p < 0.0001). Cross-validated Kaplan-Meier curves showed significant separation among risk groups for rising PSA for MRaP (p < 0.005, Hazard Ratio (HR) = 11.36) as compared to MR (p = 0.64, HR = 1.33), MP (p = 0.19, HR = 2.82) and MC (p = 0.10, HR = 3.05). Integrated radio-pathomic model MRaP (AUC = 0.80) outperformed MR (AUC = 0.57) and MP (AUC = 0.76) in predicting EPE on external-data (D2).

Conclusions

Results from this preliminary study suggest that a combination of radiomic and pathomic features can better predict post-surgical outcomes (rising PSA and EPE) compared to either of them individually as well as extant prognostic nomogram (CAPRA).

Cross-validation approaches for penalized Cox regression

Cross-validation is the most common way of selecting tuning parameters in penalized regression, but its use in penalized Cox regression models has received relatively little attention in the literature. Due to its partial likelihood construction, carrying out cross-validation for Cox models is not straightforward, and there are several potential approaches for implementation. Here, we propose a new approach based on cross-validating the linear predictors of the Cox model and compare it to approaches that have been proposed elsewhere. We show that the proposed approach offers an attractive balance of performance and numerical stability, and illustrate these advantages using simulated data as well as analyzing a high-dimensional study of gene expression and survival in lung cancer patients.

Merkel cell carcinoma recurrence risk estimation is improved by integrating factors beyond cancer stage: A multivariable model and web-based calculator

BACKGROUND

Merkel cell carcinoma (MCC) recurs in 40% of patients. In addition to stage, factors known to affect recurrence risk include: sex, immunosuppression, unknown primary status, age, site of primary tumor, and time since diagnosis.

PURPOSE

Create a multivariable model and web-based calculator to predict MCC recurrence risk more accurately than stage alone.

METHODS

Data from 618 patients in a prospective cohort were used in a competing risk regression model to estimate recurrence risk using stage and other factors.

RESULTS

In this multivariable model, the most impactful recurrence risk factors were: American Joint Committee on Cancer stage (P < .001), immunosuppression (hazard ratio 2.05; P < .001), male sex (1.59; P = .003) and unknown primary (0.65; P = .064). Compared to stage alone, the model improved prognostic accuracy (concordance index for 2-year risk, 0.66 vs 0.70; P < .001), and modified estimated recurrence risk by up to 4-fold (18% for low-risk stage IIIA vs 78% for high-risk IIIA over 5 years).

LIMITATIONS

Lack of an external data set for model validation.

CONCLUSION/RELEVANCE

As demonstrated by this multivariable model, accurate recurrence risk prediction requires integration of factors beyond stage. An online calculator based on this model (at merkelcell.org/recur) integrates time since diagnosis and provides new data for optimizing surveillance for MCC patients.

Nuclear medicine radiomics in digestive system tumors: Concept, applications, challenges, and future perspectives

Radiomics aims to develop novel biomarkers and provide relevant deeper subvisual information about pathology, immunophenotype, and tumor microenvironment. It uses automated or semiautomated quantitative analysis of high-dimensional images to improve characterization, diagnosis, and prognosis. Recent years have seen a rapid increase in radiomics applications in nuclear medicine, leading to some promising research results in digestive system oncology, which have been driven by big data analysis and the development of artificial intelligence. Although radiomics advances one step further toward the non-invasive precision medical analysis, it is still a step away from clinical application and faces many challenges. This review article summarizes the available literature on digestive system tumors regarding radiomics in nuclear medicine. First, we describe the workflow and steps involved in radiomics analysis. Subsequently, we discuss the progress in clinical application regarding the utilization of radiomics for distinguishing between various diseases and evaluating their prognosis, and demonstrate how radiomics advances this field. Finally, we offer our viewpoint on how the field can progress by addressing the challenges facing clinical implementation.

Urine metabolomics for assessing fertility-sparing treatment efficacy in endometrial cancer: a non-invasive approach using ultra-performance liquid chromatography mass spectrometry

OBJECTIVE

This study aimed to reveal the urine metabolic change of endometrial cancer (EC) patients during fertility-sparing treatment and establish non-invasive predictive models to identify patients with complete remission (CR).

METHOD

This study enrolled 20 EC patients prior to treatment (PT) and 22 patients with CR, aged 25-40 years. Eligibility criteria consisted of stage IA high-grade EC, lesions confined to endometrium, normal hepatic and renal function, normal urine test, no contraindication for fertility-sparing treatment and no prior therapy. Urine samples were analyzed using ultraperformance liquid chromatography mass spectrometry (UPLC-MS), a technique chosen for its high sensitivity and resolution, allows for rapid, accurate identification and quantification of metabolites, providing a comprehensive metabolic profile and facilitating the discovery of potential biomarkers. Analytical techniques were employed to determine distinct metabolites and altered metabolic pathways. The statistical analyses were performed using univariate and multivariate analyses, logistic regression and receiver operating characteristic (ROC) curves to discover and validate the potential biomarker models.

RESULTS

A total of 108 different urine metabolomes were identified between CR and PT groups. These metabolites were enriched in ascorbate and aldarate metabolism, one carbon pool by folate, and some amino acid metabolisms pathways. A panel consisting of Baicalin, 5beta-1,3,7 (11)-Eudesmatrien-8-one, Indolylacryloylglycine, Edulitine, and Physapubenolide were selected as biomarkers, which demonstrated the best predictive ability with the AUC values of 0.982/0.851 in training/10-fold-cross-validation group, achieving a sensitivity of 0.975 and specificity of 0.967, respectively.

CONCLUSION

The urine metabolic analysis revealed the metabolic changes in EC patients during the fertility-sparing treatment. The predictive biomarkers present great potential diagnostic value in fertility-sparing treatments for EC patients, offering a less invasive means of monitoring treatment efficacy. Further research should explore the mechanistic underpinnings of these metabolic changes and validate the biomarker panel in larger, diverse populations due to the small sample size and single-institution nature of our study.

Revisiting Concurrent Radiation Therapy, Temozolomide, and the Histone Deacetylase Inhibitor Valproic Acid for Patients with Glioblastoma-Proteomic Alteration and Comparison Analysis with the Standard-of-Care Chemoirradiation

BACKGROUND

Glioblastoma (GBM) is the most common brain tumor with an overall survival (OS) of less than 30% at two years. Valproic acid (VPA) demonstrated survival benefits documented in retrospective and prospective trials, when used in combination with chemo-radiotherapy (CRT).

PURPOSE

The primary goal of this study was to examine if the differential alteration in proteomic expression pre vs. post-completion of concurrent chemoirradiation (CRT) is present with the addition of VPA as compared to standard-of-care CRT. The second goal was to explore the associations between the proteomic alterations in response to VPA/RT/TMZ correlated to patient outcomes. The third goal was to use the proteomic profile to determine the mechanism of action of VPA in this setting.

MATERIALS AND METHODS

Serum obtained pre- and post-CRT was analyzed using an aptamer-based SOMAScan® proteomic assay. Twenty-nine patients received CRT plus VPA, and 53 patients received CRT alone. Clinical data were obtained via a database and chart review. Tests for differences in protein expression changes between radiation therapy (RT) with or without VPA were conducted for individual proteins using two-sided t-tests, considering p-values of <0.05 as significant. Adjustment for age, sex, and other clinical covariates and hierarchical clustering of significant differentially expressed proteins was carried out, and Gene Set Enrichment analyses were performed using the Hallmark gene sets. Univariate Cox proportional hazards models were used to test the individual protein expression changes for an association with survival. The lasso Cox regression method and 10-fold cross-validation were employed to test the combinations of expression changes of proteins that could predict survival. Predictiveness curves were plotted for significant proteins for VPA response (p-value < 0.005) to show the survival probability vs. the protein expression percentiles.

RESULTS

A total of 124 proteins were identified pre- vs. post-CRT that were differentially expressed between the cohorts who received CRT plus VPA and those who received CRT alone. Clinical factors did not confound the results, and distinct proteomic clustering in the VPA-treated population was identified. Time-dependent ROC curves for OS and PFS for landmark times of 20 months and 6 months, respectively, revealed AUC of 0.531, 0.756, 0.774 for OS and 0.535, 0.723, 0.806 for PFS for protein expression, clinical factors, and the combination of protein expression and clinical factors, respectively, indicating that the proteome can provide additional survival risk discrimination to that already provided by the standard clinical factors with a greater impact on PFS. Several proteins of interest were identified. Alterations in GALNT14 (increased) and CCL17 (decreased) (p = 0.003 and 0.003, respectively, FDR 0.198 for both) were associated with an improvement in both OS and PFS. The pre-CRT protein expression revealed 480 proteins predictive for OS and 212 for PFS (p < 0.05), of which 112 overlapped between OS and PFS. However, FDR-adjusted p values were high, with OS (the smallest p value of 0.586) and PFS (the smallest p value of 0.998). The protein PLCD3 had the lowest p-value (p = 0.002 and 0.0004 for OS and PFS, respectively), and its elevation prior to CRT predicted superior OS and PFS with VPA administration. Cancer hallmark genesets associated with proteomic alteration observed with the administration of VPA aligned with known signal transduction pathways of this agent in malignancy and non-malignancy settings, and GBM signaling, and included epithelial-mesenchymal transition, hedgehog signaling, Il6/JAK/STAT3, coagulation, NOTCH, apical junction, xenobiotic metabolism, and complement signaling.

CONCLUSIONS

Differential alteration in proteomic expression pre- vs. post-completion of concurrent chemoirradiation (CRT) is present with the addition of VPA. Using pre- vs. post-data, prognostic proteins emerged in the analysis. Using pre-CRT data, potentially predictive proteins were identified. The protein signals and hallmark gene sets associated with the alteration in the proteome identified between patients who received VPA and those who did not, align with known biological mechanisms of action of VPA and may allow for the identification of novel biomarkers associated with outcomes that can help advance the study of VPA in future prospective trials.

Development of PSMA-PET-guided CT-based radiomic signature to predict biochemical recurrence after salvage radiotherapy

PURPOSE

To develop a CT-based radiomic signature to predict biochemical recurrence (BCR) in prostate cancer patients after sRT guided by positron-emission tomography targeting prostate-specific membrane antigen (PSMA-PET).

MATERIAL AND METHODS

Consecutive patients, who underwent 68Ga-PSMA11-PET/CT-guided sRT from three high-volume centers in Germany, were included in this retrospective multicenter study. Patients had PET-positive local recurrences and were treated with intensity-modulated sRT. Radiomic features were extracted from volumes of interests on CT guided by focal PSMA-PET uptakes. After preprocessing, clinical, radiomics, and combined clinical-radiomic models were developed combining different feature reduction techniques and Cox proportional hazard models within a nested cross validation approach.

RESULTS

Among 99 patients, median interval until BCR was the radiomic models outperformed clinical models and combined clinical-radiomic models for prediction of BCR with a C-index of 0.71 compared to 0.53 and 0.63 in the test sets, respectively. In contrast to the other models, the radiomic model achieved significantly improved patient stratification in Kaplan-Meier analysis. The radiomic and clinical-radiomic model achieved a significantly better time-dependent net reclassification improvement index (0.392 and 0.762, respectively) compared to the clinical model. Decision curve analysis demonstrated a clinical net benefit for both models. Mean intensity was the most predictive radiomic feature.

CONCLUSION

This is the first study to develop a PSMA-PET-guided CT-based radiomic model to predict BCR after sRT. The radiomic models outperformed clinical models and might contribute to guide personalized treatment decisions.

Prophylactic cranial irradiation-related lymphopenia affects survival in patients with limited-stage small cell lung cancer

Background

The study aimed to identify the relations of the absolute lymphocyte count (ALC) nadir during prophylactic cranial irradiation (PCI) and patient outcomes in limited-stage small cell lung cancer (LS-SCLC).

Methods

We analyzed 268 L S-SCLC patients who underwent PCI from 2012 to 2019. ALC values were collected prior, during, and 3 months post PCI. Kaplan-Meier and Cox regression analyses were performed to assess the relation of ALC to patient prognosis. Two nomograms were developed on the basis of clinical variables for survival prediction.

Results

Compared with the ALC before PCI (1.13 × 10⁹ cells/L), the ALC nadir during PCI was significantly reduced by 0.68 × 10⁹ cells/L (P < 0.001) and raised to 1.02 × 10⁹ cells/L 3 months post PCI. Patients with a low ALC nadir during PCI (<0.68 × 10⁹ cells/L) had inferior progression free survival (PFS) (median PFS: 17.2 m vs. 43.7 m, P = 0.019) and overall survival (OS) (median OS: 29.0 m vs 39.1 m, P = 0.012). Multivariate Cox analysis revealed that age, smoking history, clinical stage, and ALC nadir were independent OS (P = 0.006, P = 0.005, P < 0.001 and P = 0.027, respectively), as well as independent PFS predictors (P = 0.032, P = 0.012, P = 0.012 and P = 0.018, respectively). After internal cross-validation, the corrected concordance indices of the predictive nomograms for PFS and OS were 0.637 and 0.663, respectively.

Conclusion

LS-SCLC patients with a low ALC nadir during PCI likely have worse survival outcomes. Dynamic evaluation of the ALC during PCI is recommended for LS-SCLC patients.

Statistical analysis of high-dimensional biomedical data: a gentle introduction to analytical goals, common approaches and challenges

BACKGROUND

In high-dimensional data (HDD) settings, the number of variables associated with each observation is very large. Prominent examples of HDD in biomedical research include omics data with a large number of variables such as many measurements across the genome, proteome, or metabolome, as well as electronic health records data that have large numbers of variables recorded for each patient. The statistical analysis of such data requires knowledge and experience, sometimes of complex methods adapted to the respective research questions.

METHODS

Advances in statistical methodology and machine learning methods offer new opportunities for innovative analyses of HDD, but at the same time require a deeper understanding of some fundamental statistical concepts. Topic group TG9 "High-dimensional data" of the STRATOS (STRengthening Analytical Thinking for Observational Studies) initiative provides guidance for the analysis of observational studies, addressing particular statistical challenges and opportunities for the analysis of studies involving HDD. In this overview, we discuss key aspects of HDD analysis to provide a gentle introduction for non-statisticians and for classically trained statisticians with little experience specific to HDD.

RESULTS

The paper is organized with respect to subtopics that are most relevant for the analysis of HDD, in particular initial data analysis, exploratory data analysis, multiple testing, and prediction. For each subtopic, main analytical goals in HDD settings are outlined. For each of these goals, basic explanations for some commonly used analysis methods are provided. Situations are identified where traditional statistical methods cannot, or should not, be used in the HDD setting, or where adequate analytic tools are still lacking. Many key references are provided.

CONCLUSIONS

This review aims to provide a solid statistical foundation for researchers, including statisticians and non-statisticians, who are new to research with HDD or simply want to better evaluate and understand the results of HDD analyses.

The combination of supervised and unsupervised learning based risk stratification and phenotyping in pulmonary arterial hypertension-a long-term retrospective multicenter trial

BACKGROUND

Accurate risk stratification in pulmonary arterial hypertension (PAH), a devastating cardiopulmonary disease, is essential to guide successful therapy. Machine learning may improve risk management and harness clinical variability in PAH.

METHODS

We conducted a long-term retrospective observational study (median follow-up: 67 months) including 183 PAH patients from three Austrian PAH expert centers. Clinical, cardiopulmonary function, laboratory, imaging, and hemodynamic parameters were assessed. Cox proportional hazard Elastic Net and partitioning around medoid clustering were applied to establish a multi-parameter PAH mortality risk signature and investigate PAH phenotypes.

RESULTS

Seven parameters identified by Elastic Net modeling, namely age, six-minute walking distance, red blood cell distribution width, cardiac index, pulmonary vascular resistance, N-terminal pro-brain natriuretic peptide and right atrial area, constituted a highly predictive mortality risk signature (training cohort: concordance index = 0.82 [95%CI: 0.75 - 0.89], test cohort: 0.77 [0.66 - 0.88]). The Elastic Net signature demonstrated superior prognostic accuracy as compared with five established risk scores. The signature factors defined two clusters of PAH patients with distinct risk profiles. The high-risk/poor prognosis cluster was characterized by advanced age at diagnosis, poor cardiac output, increased red cell distribution width, higher pulmonary vascular resistance, and a poor six-minute walking test performance.

CONCLUSION

Supervised and unsupervised learning algorithms such as Elastic Net regression and medoid clustering are powerful tools for automated mortality risk prediction and clinical phenotyping in PAH.

Association of Combined Exposure to Ambient Air Pollutants, Genetic Risk, and Incident Rheumatoid Arthritis: A Prospective Cohort Study in the UK Biobank

BACKGROUND

Evidence for a potential link between air pollution and rheumatoid arthritis (RA) is inconsistent, and the modified effect of genetic susceptibility on the relationship between air pollution and RA has not been well studied.

OBJECTIVE

Using a general population cohort from the UK Biobank, this study aimed to investigate the associations between various air pollutants and the risk of incident RA and to further estimate the impact of combined exposure to ambient air pollutants on the risk of developing RA under the modification effect of genetic predisposition.

METHODS

A total of 342,973 participants with completed genotyping data and who were free of RA at baseline were included in the study. An air pollution score was constructed by summing the concentrations of each pollutant weighted by the regression coefficients with RA from single-pollutant models to assess the combined effect of air pollutants, including particulate matter (PM) with diameters ≤ 2.5 μ m (PM 2.5 ), between 2.5 and 10 μ m (PM 2.5 - 10 ), and ≤ 10 μ m (PM 10 ), as well as nitrogen dioxide (NO 2 ) and nitrogen oxides (NO x ). In addition, the polygenic risk score (PRS) of RA was calculated to characterize individual genetic risk. The Cox proportional hazard model was used to estimate hazard ratios (HRs) and 95% confidence intervals (95% CIs) of associations of single air pollutant, air pollution score, or PRS with incident RA.

RESULTS

During a median follow-up time of 8.1 y, 2,034 incident events of RA were recorded. The HRs (95% CIs) of incident RA per interquartile range increment in PM 2.5 , PM 2.5 - 10 , PM 10 , NO 2 , and NO x were 1.07 (1.01, 1.13), 1.00 (0.96, 1.04), 1.01 (0.96, 1.07), 1.03 (0.98, 1.09), and 1.07 (1.02, 1.12), respectively. We also found a positive exposure-response relationship between air pollution score and RA risk (p Trend = 0.000053 ). The HR (95% CI) of incident RA was 1.14 (1.00, 1.29) in the highest quartile group compared with the lowest quartile group of the air pollution score. Furthermore, the results of the combined effect of air pollution score and PRS on the RA risk showed that the risk of RA incidence in the highest genetic risk and air pollution score group was almost twice that of the lowest genetic risk and air pollution score group [incidence rate (IR) per 100,000 person-years: 98.46 vs. 51.19, and HR = 1.73 (95% CI: 1.39, 2.17) vs. 1 (reference)], although no statistically significant interaction between the air pollution and genetic risk for incident RA was found (p Interaction > 0.05 ).

DISCUSSION

The results revealed that long-term combined exposure to ambient air pollutants might increase the risk of RA, particularly in those with high genetic risk. https://doi.org/10.1289/EHP10710.

Long-Term Air Pollution, Genetic Susceptibility, and the Risk of Depression and Anxiety: A Prospective Study in the UK Biobank Cohort

BACKGROUND

Depression and anxiety are two mental disorders that are often comorbid. However, the associations of long-term air pollution exposure with depression and anxiety remain inconclusive.

OBJECTIVE

We conducted a cross-sectional and prospective study to examine the associations of ambient exposure to particulate matter (PM) with a diameter of ≤2.5μm (PM2.5), ≤10μm (PM10), and 2.5-10μm (PMcoarse), nitrogen oxides (NOx), and nitrogen dioxide (NO2) with the risk of depression and anxiety in the UK Biobank.

METHODS

This study included 398,241 participants from the UK Biobank, 128,456 of whom participated the 7-y online mental health survey. A total of 345,876 individuals were free of depression and anxiety at baseline; of those, 16,185 developed incident mental disorders during a median of 8.7 y of follow-up. Depression and anxiety were assessed using hospital admission records and mental health questionnaires. Associations of air pollution with prevalent and incident mental disorders were examined using logistic regression and Cox regression models, respectively.

RESULTS

Elevated levels of the five air pollutants were associated with higher odds of mental disorders at baseline. Levels of four pollutants but not PMcoarse were also associated with higher odds and risks of mental disorders during follow-up; specifically, hazard ratios [HR, 95% confidence interval (CI)] of an interquartile range increase in PM2.5, PM10, NOx, and NO2 for incident mental disorders were 1.03 (95% CI: 1.01, 1.05), 1.06 (95% CI: 1.04, 1.08), 1.03 (95% CI: 1.01, 1.05), and 1.06 (95% CI: 1.04, 1.09), respectively. An air pollution index reflecting combined effects of pollutants also demonstrated a positive association with the risk of mental disorders. HR (95% CI) of incident mental disorders were 1.11 (95% CI: 1.05, 1.18) in the highest quintile group in comparison with the lowest quintile of the air pollution index. We further observed that the associations between air pollution and mental disorders differed by a genetic risk score based on single nucleotide polymorphisms previously associated with genetic susceptibility to mental disorders in the UK Biobank cohort.

DISCUSSION

To our knowledge, this research is one of the largest cohort studies that demonstrates an association between mental health disorders and exposure to long-term air pollution, which could be further enhanced by genetic predisposition. https://doi.org/10.1289/EHP10391.

Spatial heterogeneity of cancer associated protein expression in immunohistochemically stained images as an improved prognostic biomarker

The identification of new tumor biomarkers for patient stratification before therapy, for monitoring of disease progression, and for characterization of tumor biology plays a crucial role in cancer research. The status of these biomarkers is mostly scored manually by a pathologist and such scores typically, do not consider the spatial heterogeneity of the protein's expression in the tissue. Using advanced image analysis methods, marker expression can be determined quantitatively with high accuracy and reproducibility on a per-cell level. To aggregate such per-cell marker expressions on a patient level, the expression values for single cells are usually averaged for the whole tissue. However, averaging neglects the spatial heterogeneity of the marker expression in the tissue. We present two novel approaches for quantitative scoring of spatial marker expression heterogeneity. The first approach is based on a co-occurrence analysis of the marker expression in neighboring cells. The second approach accounts for the local variability of the protein's expression by tiling the tissue with a regular grid and assigning local spatial heterogeneity phenotypes per tile. We apply our novel scores to quantify the spatial expression of four different membrane markers, i.e., HER2, CMET, CD44, and EGFR in immunohistochemically (IHC) stained tissue sections of colorectal cancer patients. We evaluate the prognostic relevance of our spatial scores in this cohort and show that the spatial heterogeneity scores clearly outperform the marker expression average as a prognostic factor (CMET: p-value=0.01 vs. p-value=0.3).

Comparative Study of Chronic Kidney Disease Predictor Performance Given Insufficient Training Dataset

This study compares the performance of Logistic Regression and Classification and Regression Tree model implementations in predicting chronic kidney disease outcomes from predictor variables, given insufficient training data. Imputation of missing data was performed using a technique based on k-nearest neighbours. The dataset was arbitrarily split into 10 % training set and 90 % test set to simulate a dearth of training data. Accuracy was mainly considered for the quantitative performance assessment together with ROC curves, area under the ROC curve values and confusion matrix pairs. Validation of the results was done using a shuffled 5-fold cross-validation procedure. Logistic regression produced an average accuracy of about 99 % compared to about 97 % the decision tree produced.

Discovery of pathway-independent protein signatures associated with clinical outcome in human cancer cohorts

Proteomic data provide a direct readout of protein function, thus constituting an information-rich resource for prognostic and predictive modeling. However, protein array data may not fully capture pathway activity due to the limited number of molecules and incomplete pathway coverage compared to other high-throughput technologies. For the present study, our aim was to improve clinical outcome prediction compared to published pathway-dependent prognostic signatures for The Cancer Genome Atlas (TCGA) cohorts using the least absolute shrinkage and selection operator (LASSO). RPPA data is particularly well-suited to the LASSO due to the relatively low number of predictors compared to larger genomic data matrices. Our approach selected predictors regardless of their pathway membership and optimally combined their RPPA measurements into a weighted risk score. Performance was assessed and compared to that of the published signatures using two unbiased approaches: 1) 10 iterations of threefold cross-validation for unbiased estimation of hazard ratio and difference in 5-year survival (by Kaplan-Meier method) between predictor-defined high and low risk groups; and 2) a permutation test to evaluate the statistical significance of the cross-validated log-rank statistic. Here, we demonstrate strong stratification of 445 renal clear cell carcinoma tumors from The Cancer Genome Atlas (TCGA) into high and low risk groups using LASSO regression on RPPA data. Median cross-validated difference in 5-year overall survival was 32.8%, compared to 25.2% using a published receptor tyrosine kinase (RTK) prognostic signature (median hazard ratios of 3.3 and 2.4, respectively). Applicability and performance of our approach was demonstrated in three additional TCGA cohorts: ovarian serous cystadenocarcinoma (OVCA), sarcoma (SARC), and cutaneous melanoma (SKCM). The data-driven LASSO-based approach is versatile and well-suited for discovery of new protein/disease associations.

Machine learning based survival prediction in Glioma using large-scale registry data

Gliomas are the most common central nervous system tumors exhibiting poor clinical outcomes. The ability to estimate prognosis is crucial for both patients and providers in order to select the most appropriate treatment. Machine learning (ML) allows for sophisticated approaches to survival prediction using real world clinical parameters needed to achieve superior predictive accuracy. We employed Cox Proportional hazards (CPH) model, Support Vector Machine (SVM) model, Random Forest (RF) model in a large glioma dataset (3462 patients, diagnosed 2000-2018) to explore the most optimal approach to survival prediction. Features employed were age, sex, surgical resection status, tumor histology and tumor site, administration of radiation therapy (RT) and chemotherapy status. Concordance index (c-index) was employed to assess the accuracy of survival time prediction. All three models performed well with prediction accuracy (CI 0.767, 0.771, 0.57 for CPH, SVM, RF models respectively) with the best performance achieved when incorporating RT and chemotherapy administration status which emerged as key predictive features. Within the subset of glioblastoma patients, similar prediction accuracy was achieved. These findings should prompt stricter clinician oversight over registry data accuracy through quality assurance as we move towards meaningful predictive ability using ML approaches in glioma.

Cellular Density in Adult Glioma, Estimated with MR Imaging Data and a Machine Learning Algorithm, Has Prognostic Power Approaching World Health Organization Histologic Grading in a Cohort of 1181 Patients

BACKGROUND AND PURPOSE

Recent advances in machine learning have enabled image-based prediction of local tissue pathology in gliomas, but the clinical usefulness of these predictions is unknown. We aimed to evaluate the prognostic ability of imaging-based estimates of cellular density for patients with gliomas, with comparison to the gold standard reference of World Health Organization grading.

MATERIALS AND METHODS

Data from 1181 (207 grade II, 246 grade III, 728 grade IV) previously untreated patients with gliomas from a single institution were analyzed. A pretrained random forest model estimated voxelwise tumor cellularity using MR imaging data. Maximum cellular density was correlated with the World Health Organization grade and actual survival, correcting for covariates of age and performance status.

RESULTS

A maximum estimated cellular density of >7681 nuclei/mm2 was associated with a worse prognosis and a univariate hazard ratio of 4.21 (P < .001); the multivariate hazard ratio after adjusting for covariates of age and performance status was 2.91 (P < .001). The concordance index between maximum cellular density (adjusted for covariates) and survival was 0.734. The hazard ratio for a high World Health Organization grade (IV) was 7.57 univariate (P < .001) and 5.25 multivariate (P < .001). The concordance index for World Health Organization grading (adjusted for covariates) was 0.761. The maximum cellular density was an independent predictor of overall survival, and a Cox model using World Health Organization grade, maximum cellular density, age, and Karnofsky performance status had a higher concordance (C = 0.764; range 0.748-0.781) than the component predictors.

CONCLUSIONS

Image-based estimation of glioma cellularity is a promising biomarker for predicting survival, approaching the prognostic power of World Health Organization grading, with added values of early availability, low risk, and low cost.

Machine learning-guided covariate selection for time-to-event models developed from a small sample of real-world patients receiving bevacizumab treatment

Therapeutic outcomes in patients with metastatic colorectal cancer (mCRC) receiving bevacizumab treatment are highly variable, and a reliable predictive factor is not available. Progression-free survival (PFS) and overall survival (OS) were recorded from an observational, prospective study after 5 years of follow-up, including 46 patients with mCRC receiving bevacizumab treatment. Three vascular endothelial growth factor (VEGF)-A and two intercellular adhesion molecule-1 genes polymorphisms, age, gender, weight, dosing scheme, and co-treatments were collected. Given the relatively small number of events (37 [80%] for the PFS and 26 [57%] for the OS), to study the effect of these covariates on PFS and OS, a covariate analysis was performed using statistical and supervised machine learning techniques, including Cox regression, penalized Cox regression techniques (least absolute shrinkage and selection operator [LASSO], ridge regression, and elastic net), survival trees, and survival forest. The predictive performance of each method was evaluated in bootstrapped samples, using prediction error curves and the area under the curve of the receiver operating characteristic. The LASSO penalized Cox-regression model showed the best overall performance. Nonlinear mixed effects (NLME) models were developed, and a conventional stepwise covariate search was performed. Then, covariates identified as important by the LASSO model were included in the base NLME models developed for PFS and OS, resulting in improved models as compared to those obtained with the stepwise covariate search. It was shown that having gene polymorphisms in VEGFA (rs699947 and rs1570360) and ICAM1 (rs1799969) are associated with a favorable clinical outcome in patients with mCRC receiving bevacizumab treatment.

Computational Analysis of High-Dimensional DNA Methylation Data for Cancer Prognosis

Developing cancer prognostic models using multiomics data is a major goal of precision oncology. DNA methylation provides promising prognostic biomarkers, which have been used to predict survival and treatment response in solid tumor or plasma samples. This review article presents an overview of recently published computational analyses on DNA methylation for cancer prognosis. To address the challenges of survival analysis with high-dimensional methylation data, various feature selection methods have been applied to screen a subset of informative markers. Using candidate markers associated with survival, prognostic models either predict risk scores or stratify patients into subtypes. The model's discriminatory power can be assessed by multiple evaluation metrics. Finally, we discuss the limitations of existing studies and present the prospects of applying machine learning algorithms to fully exploit the prognostic value of DNA methylation.

Image analysis reveals molecularly distinct patterns of TILs in NSCLC associated with treatment outcome

Despite known histological, biological, and clinical differences between lung adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC), relatively little is known about the spatial differences in their corresponding immune contextures. Our study of over 1000 LUAD and LUSC tumors revealed that computationally derived patterns of tumor-infiltrating lymphocytes (TILs) on H&E images were different between LUAD (N = 421) and LUSC (N = 438), with TIL density being prognostic of overall survival in LUAD and spatial arrangement being more prognostically relevant in LUSC. In addition, the LUAD-specific TIL signature was associated with OS in an external validation set of 100 NSCLC treated with more than six different neoadjuvant chemotherapy regimens, and predictive of response to therapy in the clinical trial CA209-057 (n = 303). In LUAD, the prognostic TIL signature was primarily comprised of CD4+ T and CD8+ T cells, whereas in LUSC, the immune patterns were comprised of CD4+ T, CD8+ T, and CD20+ B cells. In both subtypes, prognostic TIL features were associated with transcriptomics-derived immune scores and biological pathways implicated in immune recognition, response, and evasion. Our results suggest the need for histologic subtype-specific TIL-based models for stratifying survival risk and predicting response to therapy. Our findings suggest that predictive models for response to therapy will need to account for the unique morphologic and molecular immune patterns as a function of histologic subtype of NSCLC.

Development of Anticancer Peptides Using Artificial Intelligence and Combinational Therapy for Cancer Therapeutics

Cancer is a group of diseases causing abnormal cell growth, altering the genome, and invading or spreading to other parts of the body. Among therapeutic peptide drugs, anticancer peptides (ACPs) have been considered to target and kill cancer cells because cancer cells have unique characteristics such as a high negative charge and abundance of microvilli in the cell membrane when compared to a normal cell. ACPs have several advantages, such as high specificity, cost-effectiveness, low immunogenicity, minimal toxicity, and high tolerance under normal physiological conditions. However, the development and identification of ACPs are time-consuming and expensive in traditional wet-lab-based approaches. Thus, the application of artificial intelligence on the approaches can save time and reduce the cost to identify candidate ACPs. Recently, machine learning (ML), deep learning (DL), and hybrid learning (ML combined DL) have emerged into the development of ACPs without experimental analysis, owing to advances in computer power and big data from the power system. Additionally, we suggest that combination therapy with classical approaches and ACPs might be one of the impactful approaches to increase the efficiency of cancer therapy.

A Predictive Model of Noncardia Gastric Adenocarcinoma Risk Using Antibody Response to Helicobacter pylori Proteins and Pepsinogen

BACKGROUND

Blood-based biomarkers for gastric cancer risk stratification could facilitate targeting screening to people who will benefit from it most. The ABC Method, which stratifies individuals by their Helicobacter pylori infection and serum-diagnosed chronic atrophic gastritis status, is currently used in Japan for this purpose. Most gastric cancers are caused by chronic H. pylori infection, but few studies have explored the capability of antibody response to H. pylori proteins to predict gastric cancer risk in addition to established predictors.

METHODS

We used the least absolute shrinkage and selection operator (Lasso) to build a predictive model of noncardia gastric adenocarcinoma risk from serum data on pepsinogen and antibody response to 13 H. pylori antigens as well as demographic and lifestyle factors from a large international study in East Asia.

RESULTS

Our best model had a significantly (P < 0.001) higher AUC of 73.79% [95% confidence interval (CI), 70.86%-76.73%] than the ABC Method (68.75%; 95% CI, 65.91%-71.58%). At 75% specificity, the new model had greater sensitivity than the ABC Method (58.67% vs. 52.68%) as well as NPV (68.24% vs. 66.29%).

CONCLUSIONS

Along with serologically defined chronic atrophic gastritis, antibody response to the H. pylori proteins HP 0305, HP 1564, and UreA can improve the prediction of gastric cancer risk.

IMPACT

The new risk stratification model could help target more invasive gastric screening resources to individuals at high risk.

Scalable algorithms for semiparametric accelerated failure time models in high dimensions

Semiparametric accelerated failure time (AFT) models are a useful alternative to Cox proportional hazards models, especially when the assumption of constant hazard ratios is untenable. However, rank-based criteria for fitting AFT models are often nondifferentiable, which poses a computational challenge in high-dimensional settings. In this article, we propose a new alternating direction method of multipliers algorithm for fitting semiparametric AFT models by minimizing a penalized rank-based loss function. Our algorithm scales well in both the number of subjects and number of predictors, and can easily accommodate a wide range of popular penalties. To improve the selection of tuning parameters, we propose a new criterion which avoids some common problems in cross-validation with censored responses. Through extensive simulation studies, we show that our algorithm and software is much faster than existing methods (which can only be applied to special cases), and we show that estimators which minimize a penalized rank-based criterion often outperform alternative estimators which minimize penalized weighted least squares criteria. Application to nine cancer datasets further demonstrates that rank-based estimators of semiparametric AFT models are competitive with estimators assuming proportional hazards in high-dimensional settings, whereas weighted least squares estimators are often not. A software package implementing the algorithm, along with a set of auxiliary functions, is available for download at github.com/ajmolstad/penAFT.

Predicting survival in patients with glioblastoma using MRI radiomic features extracted from radiation planning volumes

BACKGROUND

Quantitative image analysis using pre-operative magnetic resonance imaging (MRI) has been able to predict survival in patients with glioblastoma (GBM). The study explored the role of postoperative radiation (RT) planning MRI-based radiomics to predict the outcomes, with features extracted from the gross tumor volume (GTV) and clinical target volume (CTV).

METHODS

Patients with IDH-wildtype GBM treated with adjuvant RT having MRI as a part of RT planning process were included in the study. 546 features were extracted from each GTV and CTV. A LASSO Cox model was applied, and internal validation was performed using leave-one-out cross-validation with overall survival as endpoint. Cross-validated time-dependent area under curve (AUC) was constructed to test the efficacy of the radiomics model, and clinical features were used to generate a combined model. Analysis was done for the entire group and in individual surgical groups-gross total excision (GTR), subtotal resection (STR), and biopsy.

RESULTS

235 patients were included in the study with 57, 118, and 60 in the GTR, STR, and biopsy subgroup, respectively. Using the radiomics model, binary risk groups were feasible in the entire cohort (p < 0.01) and biopsy group (p = 0.04), but not in the other two surgical groups individually. The integrated AUC (iAUC) was 0.613 for radiomics-based classification in the biopsy subgroup, which improved to 0.632 with the inclusion of clinical features.

CONCLUSION

Imaging features extracted from the GTV and CTV regions can lead to risk-stratification of GBM undergoing biopsy, while the utility in other individual subgroups needs to be further explored.

Two-Stage Adaptive Design for Prognostic Biomarker Signatures with a Survival Endpoint

Cancer biomarker discoveries typically involve utilizing patient specimens. In practice, there is often strong desire to preserve high quality biospecimens for studies that are most likely to yield useful information. Previously, we proposed a two-stage adaptive design for binary endpoints which terminates the biomarker study in a futility interim if the model performance is unsatisfactory. In this work, we extend the two-stage design framework to accommodate time-to-event endpoints. The first stage of the procedure involves testing whether the measure of discrimination for survival models (C-index) exceeds a pre-specified threshold. We describe the computation of cross-validated C-index and evaluation of the statistical significance using re-sampling techniques. The second stage involves an independent model validation. Our simulation studies show that under the null hypothesis, the proposed design maintains type I error at the nominal level and has high probabilities of terminating the study early. Under the alternative hypothesis, power of the design is a function of the true event proportion, the sample size, and the targeted improvement in the discriminant measure. We apply the method to design of a prognostic biomarker study in patients with triple-negative breast cancer. Some practical aspects of the proposed method are discussed.

Radiomic Signatures of Posterior Fossa Ependymoma: Molecular Subgroups and Risk Profiles

BACKGROUND

The risk profile for posterior fossa ependymoma (EP) depends on surgical and molecular status [Group A (PFA) versus Group B (PFB)]. While subtotal tumor resection is known to confer worse prognosis, MRI-based EP risk-profiling is unexplored. We aimed to apply machine learning strategies to link MRI-based biomarkers of high-risk EP and also to distinguish PFA from PFB.

METHODS

We extracted 1800 quantitative features from presurgical T2-weighted (T2-MRI) and gadolinium-enhanced T1-weighted (T1-MRI) imaging of 157 EP patients. We implemented nested cross-validation to identify features for risk score calculations and apply a Cox model for survival analysis. We conducted additional feature selection for PFA versus PFB and examined performance across three candidate classifiers.

RESULTS

For all EP patients with GTR, we identified four T2-MRI-based features and stratified patients into high- and low-risk groups, with 5-year overall survival rates of 62% and 100%, respectively (p < 0.0001). Among presumed PFA patients with GTR, four T1-MRI and five T2-MRI features predicted divergence of high- and low-risk groups, with 5-year overall survival rates of 62.7% and 96.7%, respectively (p = 0.002). T1-MRI-based features showed the best performance distinguishing PFA from PFB with an AUC of 0.86.

CONCLUSIONS

We present machine learning strategies to identify MRI phenotypes that distinguish PFA from PFB, as well as high- and low-risk PFA. We also describe quantitative image predictors of aggressive EP tumors that might assist risk-profiling after surgery. Future studies could examine translating radiomics as an adjunct to EP risk assessment when considering therapy strategies or trial candidacy.

Geometric network analysis provides prognostic information in patients with high grade serous carcinoma of the ovary treated with immune checkpoint inhibitors

Network analysis methods can potentially quantify cancer aberrations in gene networks without introducing fitted parameters or variable selection. A new network curvature-based method is introduced to provide an integrated measure of variability within cancer gene networks. The method is applied to high-grade serous ovarian cancers (HGSOCs) to predict response to immune checkpoint inhibitors (ICIs) and to rank key genes associated with prognosis. Copy number alterations (CNAs) from targeted and whole-exome sequencing data were extracted for HGSOC patients (n = 45) treated with ICIs. CNAs at a gene level were represented on a protein–protein interaction network to define patient-specific networks with a fixed topology. A version of Ollivier–Ricci curvature was used to identify genes that play a potentially key role in response to immunotherapy and further to stratify patients at high risk of mortality. Overall survival (OS) was defined as the time from the start of ICI treatment to either death or last follow-up. Kaplan–Meier analysis with log-rank test was performed to assess OS between the high and low curvature classified groups. The network curvature analysis stratified patients at high risk of mortality with p = 0.00047 in Kaplan–Meier analysis in HGSOC patients receiving ICI. Genes with high curvature were in accordance with CNAs relevant to ovarian cancer. Network curvature using CNAs has the potential to be a novel predictor for OS in HGSOC patients treated with immunotherapy.

Predicting toxicity-related docetaxel discontinuation and overall survival in metastatic castration-resistant prostate cancer: a pooled analysis of open phase 3 clinical trial data

BACKGROUND

Docetaxel is widely used in metastatic castration-resistant prostate cancer (mCRPC), however its optimal use remains unclear in the current treatment landscape. Biomarkers to predict Docetaxel toxicity may help optimize treatment selection. We aimed to create a predictive model for toxicity-related Docetaxel discontinuation (TRDD).

METHODS

Through Project Data Sphere, we accessed individual patient data from the control arms of three frontline mCRPC trials: ASCENT2, VENICE, and MAINSAIL. The inclusion criteria for these trials were all similar and included patients with chemotherapy-naïve mCRPC. The primary outcome was occurrence of TRDD. A competing risks regression (CRR) was used to predict TRDD, after accounting for the occurrence of competing events (death or progression). The output of the model was used as the dependent variable on a classification and regression tree (CART) to identify risk groups for TRDD.

RESULTS

Overall, 1568 patients were considered. Pooled CI of TRDD was 19% after accounting for competing events (death: 474; progression: 59) within 12 months of starting treatment. To build a risk calculator we relied on a CRR that ultimately included age, ECOG performance status, AST, bilirubin, use of analgesics, and presence of diabetes and chronic kidney disease. The CART analysis identified three risk groups that were named: low (model-derived TRDD risk ≤24%), intermediate (25-64%), and high (≥65%) risk group. In each risk group, probability of TRDD during treatment was 14%, 58%, and 79%, and median OS was 24 months, 20 months, and 13 months, respectively (p < 0.001).

CONCLUSIONS

Treatment selection in mCRPC remains a challenge. Our model can help clinicians balance Docetaxel toxicity and efficacy. The three risk categories that we identified correlated with OS and this is particularly useful for an optimal shared decision-making process.

Risk Factors Associated with Preterm Prelabor Rupture of Membranes after Cord Occlusion in Monochorionic Diamniotic Twins

INTRODUCTION

Preterm prelabor rupture of membranes (PPROM) is a common complication after fetal surgeries. The aim of this study was to assess risk factors for and outcomes after PPROM following cord occlusion (CO) in monochorionic diamniotic (MCDA) pregnancies.

METHODS

This was a retrospective cohort study of 188 consecutive MCDA pregnancies treated by bipolar or laser CO, either primarily because of discordant malformation (dMF) or severe selective fetal growth restriction (sFGR), or secondarily when complete bichorionization was not possible in case of twin-to-twin transfusion syndrome (TTTS) or sFGR. Intentional septostomy was performed when needed. The procedure-related PPROM was defined as rupture of membranes <32 weeks' gestation (PROM <32 weeks). Selected pre-, intra-, and early postoperative variables were analyzed by univariate and binomial logistic regression to determine they are correlated to PROM <32 weeks after CO.

RESULTS

Between 2006 and 2017, 188 cases underwent CO. Diagnosis was TTTS in 28.2% (n = 53), severe sFGR in 49.5% (n = 93), and dMF in 22.3% (n = 42). PROM <32 weeks occurred in 21.3% (n = 40), resulting in worse perinatal outcomes, as preterm birth <32 weeks occurred in 80.7% (vs. 8.3%, p = 0.000), procedure-to-delivery interval was 47.5 days (vs. 125, p = 0.000), gestational age (GA) at birth 30.0 weeks (vs. 37.7 weeks, p = 0.000), and survival 65.0% (vs. 91.1%, p = 0.000). In univariate analysis, indication, anterior placenta, cervical length, GA at surgery, operation time, amniodistention and drainage fluid volumes, chorioamniotic membrane separation, and septostomy were selected as relevant factors to be included in the regression model. In a multivariate analysis, TTTS was the only factor associated to PROM <32 weeks (OR 3.5 CI 95% 1.5-7.9).

CONCLUSIONS

PROM <32 weeks after CO increases the risk of preterm delivery. In this cohort, the membrane rupture was more likely when CO was done in the context of TTTS.

PROGNOSTIC VALUE OF POST-INDUCTION CHEMOTHERAPY VOLUMETRIC PET/CT PARAMETERS FOR STAGE IIIA/B NON-SMALL CELL LUNG CANCER PATIENTS RECEIVING DEFINITIVE CHEMORADIOTHERAPY

Purpose/Objective(s): The aim of this follow-up analysis of the ESPATUE phase-3 trial was to explore the prognostic value of post-induction chemotherapy PET metrics in patients with stage III non-small cell lung cancer (NSCLC) who were assigned to receive definitive chemoradiotherapy. Materials/Methods: All eligible patients stage IIIA (cN2) and stage IIIB of the trial received induction chemotherapy consisting of 3 cycles of cisplatin/paclitaxel and chemoradiotherapy up to 45 Gy/1.5 Gy per fraction twice-a-day, followed by a radiation-boost with 2 Gy once per day with concurrent cisplatin/vinorelbine. The protocol definition prescribed a total dose of 65-71 Gy. 18F-FDG-PET/CT (PETpre) was performed at study entry and before concurrent chemoradiotherapy (interim-PET; PETpost). Interim PETpost metrics and known prognostic clinical parameters were correlated in uni- and multivariable survival analyses. Leave-one-out cross-validation was used to show internal validity. Results: Ninety-two patients who underwent 18F-FDG-PET/CT after induction chemotherapy were enrolled. Median MTVpost value was 5.9 ml. Altogether 85 patients completed the whole chemoradiation with the planned total dose of 60-71 Gy. In univariable proportional hazard analysis, each of the parameters MTVpost, SUVmax(post) and TLGmax(post) was associated with overall survival (P < 0.05). Multivariable survival analysis, including clinical and post-induction PET parameters, found TLGmax(post) (hazard ratio: 1.032 (95%-CI: 1.013-1.052) per 100 ml increase) and total radiation dose (hazard ratio: 0.930 (0.902-0.959) per Gray increase) significantly related with overall survival in the whole group of patients, and also in patients receiving a total dose ≥ 60 Gy. The best leave-one-out cross-validated 2 parameter classifier contained TLGmax(post) and total radiation dose. TLGmax(post) was associated with time to distant metastases (P = 0.0018), and SUVmax(post) with time to loco-regional relapse (P = 0.039) in multivariable analysis of patients receiving a total dose ≥ 60 Gy. Conclusion: Post-induction chemotherapy PET parameters demonstrated prognostic significance. Therefore, an interim 18F-FDG-PET/CT is a promising diagnostic modality for guiding individualized treatment intensification.

Predicting local tumour progression after ablation for colorectal liver metastases: CT-based radiomics of the ablation zone

PURPOSE

To assess whether CT-based radiomics of the ablation zone (AZ) can predict local tumour progression (LTP) after thermal ablation for colorectal liver metastases (CRLM).

MATERIALS AND METHODS

Eighty-two patients with 127 CRLM were included. Radiomics features (with different filters) were extracted from the AZ and a 10 mm periablational rim (PAR)on portal-venous-phase CT up to 8 weeks after ablation. Multivariable stepwise Cox regression analyses were used to predict LTP based on clinical and radiomics features. Performance (concordance [c]-statistics) of the different models was compared and performance in an 'independent' dataset was approximated with bootstrapped leave-one-out-cross-validation (LOOCV).

RESULTS

Thirty-three lesions (26 %) developed LTP. Median follow-up was 21 months (range 6-115). The combined model, a combination of clinical and radiomics features, included chemotherapy (HR 0.50, p = 0.024), cT-stage (HR 10.13, p = 0.016), lesion size (HR 1.11, p = <0.001), AZ_Skewness (HR 1.58, p = 0.016), AZ_Uniformity (HR 0.45, p = 0.002), PAR_Mean (HR 0.52, p = 0.008), PAR_Skewness (HR 1.67, p = 0.019) and PAR_Uniformity (HR 3.35, p < 0.001) as relevant predictors for LTP. The predictive performance of the combined model (after LOOCV) yielded a c-statistic of 0.78 (95 %CI 0.65-0.87), compared to the clinical or radiomics models only (c-statistic 0.74 (95 %CI 0.58-0.84) and 0.65 (95 %CI 0.52-0.83), respectively).

CONCLUSION

Combining radiomics features with clinical features yielded a better performing prediction of LTP than radiomics only. CT-based radiomics of the AZ and PAR may have potential to aid in the prediction of LTP during follow-up in patients with CRLM.

Joint exposure to various ambient air pollutants and incident heart failure: a prospective analysis in UK Biobank

AIMS

Little is known about the relation between the long-term joint exposure to various ambient air pollutants and the incidence of heart failure (HF). We aimed to assess the joint association of various air pollutants with HF risk and examine the modification effect of the genetic susceptibility.

METHODS AND RESULTS

This study included 432 530 participants free of HF, atrial fibrillation, or coronary heart disease in the UK Biobank study. All participants were enrolled from 2006 to 2010 and followed up to 2018. The information on particulate matter (PM) with diameters ≤2.5 µm (PM2.5), ≤10 µm (PM10), and between 2.5 and 10 µm (PM2.5-10) as well as nitrogen oxides (NO2 and NOx) was collected. We newly proposed an air pollution score to assess the joint exposure to the five air pollutants through summing each pollutant concentration weighted by the regression coefficients with HF from single-pollutant models. We also calculated the weighted genetic risk score of HF. During a median of 10.1 years (4 346 642 person-years) of follow-up, we documented 4201 incident HF. The hazard ratios (HRs) [95% confidence interval (CI)] of HF for a 10 µg/m3 increase in PM2.5, PM10, PM2.5-10, NO2, and NOx were 1.85 (1.34-2.55), 1.61 (1.30-2.00), 1.13 (0.80-1.59), 1.10 (1.04-1.15), and 1.04 (1.02-1.06), respectively. We found that the air pollution score was associated with an increased risk of incident HF in a dose-response fashion. The HRs (95% CI) of HF were 1.16 (1.05-1.28), 1.19 (1.08-1.32), 1.21 (1.09-1.35), and 1.31 (1.17-1.48) in higher quintile groups compared with the lowest quintile of the air pollution score (P trend <0.001). In addition, we observed that the elevated risk of HF associated with a higher air pollution score was strengthened by the genetic susceptibility to HF.

CONCLUSION

Our results indicate that the long-term joint exposure to various air pollutants including PM2.5, PM10, PM2.5-10, NO2, and NOx is associated with an elevated risk of incident HF in an additive manner. Our findings highlight the importance to comprehensively assess various air pollutants in relation to the HF risk.

MicroRNA signatures associated with lymph node metastasis in intramucosal gastric cancer

Although a certain proportion of intramucosal carcinomas (IMCs) of the stomach does metastasize, the majority of patients are currently treated with endoscopic resection without lymph node dissection, and this potentially veils any existing metastasis and may put some patients in danger. In this regard, biological markers from the resected IMC that can predict metastasis are warranted. Here, we discovered unique miRNA expression profiles that consist of 21 distinct miRNAs that are specifically upregulated (miR-628-5p, miR-1587, miR-3175, miR-3620-5p, miR-4459, miR-4505, miR-4507, miR-4720-5p, miR-4742-5p, and miR-6779-5p) or downregulated (miR-106b-3p, miR-125a-5p, miR-151b, miR-181d-5p, miR-486-5p, miR-500a-3p, miR-502-3p, miR-1231, miR-3609, and miR-6831-5p) in metastatic (M)-IMC compared to nonmetastatic (N)-IMC, or nonneoplastic gastric mucosa. Intriguingly, most of these selected miRNAs showed stepwise increased or decreased expression from nonneoplastic tissue to N-IMC to M-IMC. This suggests that common oncogenic mechanisms are gradually intensified during the metastatic process. Using a machine-learning algorithm, we demonstrated that such miRNA signatures could distinguish M-IMC from N-IMC. Gene ontology and pathway analysis revealed that TGF-β signaling was enriched from upregulated miRNAs, whereas E2F targets, apoptosis-related, hypoxia-related, and PI3K/AKT/mTOR signaling pathways, were enriched from downregulated miRNAs. Immunohistochemical staining of samples from multiple institutions indicated that PI3K/AKT/mTOR pathway components, MAPK1, phospho-p44/42 MAPK, and pS6 were highly expressed and the expression of SMAD7, a TGF-β pathway component, was decreased in M-IMC, which could aid in distinguishing M-IMC from N-IMC. The miRNA signature discovered in this study is a valuable biological marker for identifying metastatic potential of IMCs, and provides novel insights regarding the metastatic progression of IMC.

Construction and Evaluation of a Risk Score Model for Autophagy-Related Genes in Esophageal Adenocarcinoma

Background

Several studies have suggested the importance of autophagy during esophageal adenocarcinoma (EAC) development. This study aimed to explore the autophagy-related genes correlated with overall survival in patients with EAC.

Material/Methods

The RNA-seq expression profiles and clinical data of patients with EAC were screened using The Cancer Genome Atlas (TCGA) database. Screening of autophagy-related genes was conducted using the human autophagy database (HADb). Bioinformatic analysis was conducted and included the following: univariate cox, lasso regression, and multivariate cox regression analysis; building overall survival assessment of the prognosis model; drawing the model of receiver operating characteristic (ROC) curve and determining the area under the curve; and a C-index reliability index assessment model through Kaplan-Meier screening of statistically significant genes in the model. The screening results were verified via Oncomine differential expression analysis. Gene set enrichment analysis (GSEA) was further used to analyze the molecular biological functions and related pathways of the gene model.

Results

Through cox regression and ROC analysis, the model showed that the risk score could accurately and independently predict the prognosis of EAC. The screening identified 4 genes: DAPK1, BECN1, ATG5, and VAMP7. GSEA showed that the high and low expression levels of the 4 genes were mainly enriched in biological functions, such as cell production and regulation, and metabolic pathways that maintain cell activity.

Conclusions

Our research found that autophagy was involved in the process of EAC development and that several autophagy-related genes may provide prognostic information and clinical application value for patients with EAC.

Galgo: a bi-objective evolutionary meta-heuristic identifies robust transcriptomic classifiers associated with patient outcome across multiple cancer types

MOTIVATION

Statistical and machine-learning analyses of tumor transcriptomic profiles offer a powerful resource to gain deeper understanding of tumor subtypes and disease prognosis. Currently, prognostic gene-expression signatures do not exist for all cancer types, and most developed to date have been optimized for individual tumor types. In Galgo, we implement a bi-objective optimization approach that prioritizes gene signature cohesiveness and patient survival in parallel, which provides greater power to identify tumor transcriptomic phenotypes strongly associated with patient survival.

RESULTS

To compare the predictive power of the signatures obtained by Galgo with previously studied subtyping methods, we used a meta-analytic approach testing a total of 35 large population-based transcriptomic biobanks of four different cancer types. Galgo-generated colorectal and lung adenocarcinoma signatures were stronger predictors of patient survival compared to published molecular classification schemes. One Galgo-generated breast cancer signature outperformed PAM50, AIMS, SCMGENE and IntClust subtyping predictors. In high-grade serous ovarian cancer, Galgo signatures obtained similar predictive power to a consensus classification method. In all cases, Galgo subtypes reflected enrichment of gene sets related to the hallmarks of the disease, which highlights the biological relevance of the partitions found.

AVAILABILITY AND IMPLEMENTATION

The open-source R package is available on www.github.com/harpomaxx/galgo.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

TCox: Correlation-Based Regularization Applied to Colorectal Cancer Survival Data

Colorectal cancer (CRC) is one of the leading causes of mortality and morbidity in the world. Being a heterogeneous disease, cancer therapy and prognosis represent a significant challenge to medical care. The molecular information improves the accuracy with which patients are classified and treated since similar pathologies may show different clinical outcomes and other responses to treatment. However, the high dimensionality of gene expression data makes the selection of novel genes a problematic task. We propose TCox, a novel penalization function for Cox models, which promotes the selection of genes that have distinct correlation patterns in normal vs. tumor tissues. We compare TCox to other regularized survival models, Elastic Net, HubCox, and OrphanCox. Gene expression and clinical data of CRC and normal (TCGA) patients are used for model evaluation. Each model is tested 100 times. Within a specific run, eighteen of the features selected by TCox are also selected by the other survival regression models tested, therefore undoubtedly being crucial players in the survival of colorectal cancer patients. Moreover, the TCox model exclusively selects genes able to categorize patients into significant risk groups. Our work demonstrates the ability of the proposed weighted regularizer TCox to disclose novel molecular drivers in CRC survival by accounting for correlation-based network information from both tumor and normal tissue. The results presented support the relevance of network information for biomarker identification in high-dimensional gene expression data and foster new directions for the development of network-based feature selection methods in precision oncology.

Primary Vascular Tumors of Bone: A Monoinstitutional Morphologic and Molecular Analysis of 427 Cases With Emphasis on Epithelioid Variants

Recent molecular discoveries have refined vascular bone tumor classification. To investigate the clinical relevance of these refinements, we reviewed all cases of primary vascular bone tumors treated at our Institute. On the basis of morphology, cases were assessed immunohistochemically and molecularly. A total of 427 cases of primary vascular tumor of bone with available follow-up and histologic material were retrieved and reclassified according to the most recent diagnostic criteria as follows: 289 hemangiomas, 38 epithelioid hemangiomas, 21 epithelioid hemangioendotheliomas, 2 retiform hemangioendotheliomas, 1 intraosseous papillary intralymphatic angioendothelioma, 24 pseudomyogenic hemangioendotheliomas, and 52 angiosarcomas (of these, 45 were epithelioid angiosarcomas and 7 spindle cell secondary angiosarcoma). Both epithelioid and classic hemangiomas behave as benign tumors with excellent prognosis. The distinction between cellular and conventional type of epithelioid hemangioma was not associated with a different clinical course. Conversely, epithelioid hemangioendothelioma exhibited a more aggressive clinical behavior than hemangioma, with higher rates of multifocality and distant spread. Immunohistochemical positivity for CAMTA1 or TFE3 did not have a prognostic implication. In epithelioid hemangioendothelioma, the presence of morphologic malignant features was associated with reduced disease-free (P=0.064) and overall survival (P=0.055). Pseudomyogenic hemangioendothelioma featured local aggressiveness in 5/24 patients exhibiting a clinical behavior closer to epithelioid hemangioma than epithelioid hemangioendothelioma. Last, 32/45 patients with epithelioid angiosarcoma died of disease with a median survival time of 10 months from diagnosis. In conclusion, the integration of morphologic, immunohistochemical, and molecular features allows a better stratification of primary vascular tumors of bone with significant prognostic and therapeutic implications.

Polygenic Score for β-Blocker Survival Benefit in European Ancestry Patients With Reduced Ejection Fraction Heart Failure

BACKGROUND

β-Blockers (BBs) are mainstay therapy for heart failure with reduced ejection fraction. However, individual patient responses to BB vary, which may be partially due to genetic variation. The goal of this study was to derive and validate the first polygenic response predictor (PRP) for BB survival benefit in heart failure with reduced ejection fraction patients.

METHODS

Derivation and validation analyses were performed in n=1436 total HF patients of European descent and with ejection fraction <50%. The PRP was derived in a random subset of the Henry Ford Heart Failure Pharmacogenomic Registry (n=248) and then validated in a meta-analysis of the remaining patients from Henry Ford Heart Failure Pharmacogenomic Registry (n=247), the TIME-CHF (Trial of Intensified Versus Standard Medical Therapy in Elderly Patients With Congestive Heart Failure; n=431), and HF-ACTION trial (Heart Failure: a Controlled Trial Investigating Outcomes of Exercise Training; n=510). The PRP was constructed from a genome-wide analysis of BB×genotype interaction predicting time to all-cause mortality, adjusted for Meta-Analysis Global Group in Chronic Heart Failure score, genotype, level of BB exposure, and BB propensity score.

RESULTS

Five-fold cross-validation summaries out to 1000 single-nucleotide polymorphisms identified optimal prediction with a 44 single-nucleotide polymorphism score and cutoff at the 30th percentile. In validation testing (n=1188), greater BB exposure was associated with reduced all-cause mortality in patients with low PRP score (n=251; hazard ratio, 0.19 [95% CI, 0.04-0.51]; P=0.0075) but not high PRP score (n=937; hazard ratio, 0.84 [95% CI, 0.53-1.3]; P=0.448)-a difference that was statistically significant (P interaction, 0.0235). Results were consistent regardless of atrial fibrillation, ejection fraction (≤40% versus 41%-50%), or when examining cardiovascular death.

CONCLUSIONS

Among patients of European ancestry with heart failure with reduced ejection fraction, a PRP distinguished patients who derived substantial survival benefit from BB exposure from a larger group that did not. Additional work is needed to prospectively test clinical utility and to develop PRPs for other population groups and other medications.

Non-parametric individual treatment effect estimation for survival data with random forests

MOTIVATION

Personalized medicine often relies on accurate estimation of a treatment effect for specific subjects. This estimation can be based on the subject's baseline covariates but additional complications arise for a time-to-event response subject to censoring. In this paper, the treatment effect is measured as the difference between the mean survival time of a treated subject and the mean survival time of a control subject. We propose a new random forest method for estimating the individual treatment effect with survival data. The random forest is formed by individual trees built with a splitting rule specifically designed to partition the data according to the individual treatment effect. For a new subject, the forest provides a set of similar subjects from the training dataset that can be used to compute an estimation of the individual treatment effect with any adequate method.

RESULTS

The merits of the proposed method are investigated with a simulation study where it is compared to numerous competitors, including recent state-of-the-art methods. The results indicate that the proposed method has a very good and stable performance to estimate the individual treatment effects. Two examples of application with a colon cancer data and breast cancer data show that the proposed method can detect a treatment effect in a sub-population even when the overall effect is small or nonexistent.

AVAILABILITY AND IMPLEMENTATION

The authors are working on an R package implementing the proposed method and it will be available soon. In the meantime, the code can be obtained from the first author at sami.tabib@hec.ca.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Challenges and Opportunities in Clinical Applications of Blood-Based Proteomics in Cancer

Simple Summary

The traditional approach in identifying cancer related protein biomarkers has focused on evaluation of a single peptide/protein in tissue or circulation. At best, this approach has had limited success for clinical applications, since multiple pathological tumor pathways may be involved during initiation or progression of cancer which diminishes the significance of a single candidate protein/peptide. Emerging sensitive proteomic based technologies like liquid chromatography mass spectrometry (LC-MS)-based quantitative proteomics can provide a platform for evaluating serial serum or plasma samples to interrogate secreted products of tumor–host interactions, thereby revealing a more “complete” repertoire of biological variables encompassing heterogeneous tumor biology. However, several challenges need to be met for successful application of serum/plasma based proteomics. These include uniform pre-analyte processing of specimens, sensitive and specific proteomic analytical platforms and adequate attention to study design during discovery phase followed by validation of discovery-level signatures for prognostic, predictive, and diagnostic cancer biomarker applications.

Abstract

Blood is a readily accessible biofluid containing a plethora of important proteins, nucleic acids, and metabolites that can be used as clinical diagnostic tools in diseases, including cancer. Like the on-going efforts for cancer biomarker discovery using the liquid biopsy detection of circulating cell-free and cell-based tumor nucleic acids, the circulatory proteome has been underexplored for clinical cancer biomarker applications. A comprehensive proteome analysis of human serum/plasma with high-quality data and compelling interpretation can potentially provide opportunities for understanding disease mechanisms, although several challenges will have to be met. Serum/plasma proteome biomarkers are present in very low abundance, and there is high complexity involved due to the heterogeneity of cancers, for which there is a compelling need to develop sensitive and specific proteomic technologies and analytical platforms. To date, liquid chromatography mass spectrometry (LC-MS)-based quantitative proteomics has been a dominant analytical workflow to discover new potential cancer biomarkers in serum/plasma. This review will summarize the opportunities of serum proteomics for clinical applications; the challenges in the discovery of novel biomarkers in serum/plasma; and current proteomic strategies in cancer research for the application of serum/plasma proteomics for clinical prognostic, predictive, and diagnostic applications, as well as for monitoring minimal residual disease after treatments. We will highlight some of the recent advances in MS-based proteomics technologies with appropriate sample collection, processing uniformity, study design, and data analysis, focusing on how these integrated workflows can identify novel potential cancer biomarkers for clinical applications.

A novel method for identifying and distinguishing Cryptococcus neoformans and Cryptococcus gattii by surface-enhanced Raman scattering using positively charged silver nanoparticles

There are approximately 1 million cryptococcal infections per year among HIV+ individuals, resulting in nearly 625,000 deaths. Cryptococcus neoformans and Cryptococcus gattii are the two most common species that cause human cryptococcosis. These two species of Cryptococcus have differences in pathogenicity, diagnosis, and treatment. Cryptococcal infections are usually difficult to identify because of their slow growth in vitro. In addition, the long detection cycle of Cryptococcus in clinical specimens makes the diagnosis of Cryptococcal infections difficult. Here, we used positively charged silver nanoparticles (AgNPs⁺) as a substrate to distinguish between C. neoformans and C. gattii in clinical specimens directly via surface-enhanced Raman scattering (SERS) and spectral analysis. The AgNPs⁺ self-assembled on the surface of the fungal cell wall via electrostatic aggregation, leading to enhanced SERS signals that were better than the standard substrate negatively charged silver nanoparticles (AgNPs). The SERS spectra could also be used as a sample database in the multivariate analysis via orthogonal partial least-squares discriminant analysis. This novel SERS detection method can clearly distinguish between the two Cryptococcus species using principal component analysis. The accuracy of the training data and test data was 100% after a tenfold crossover validation.

Construction and optimization of gene expression signatures for prediction of survival in two-arm clinical trials

Background

Gene expression signatures for the prediction of differential survival of patients undergoing anti-cancer therapies are of great interest because they can be used to prospectively stratify patients entering new clinical trials, or to determine optimal treatment for patients in more routine clinical settings. Unlike prognostic signatures however, predictive signatures require training set data from clinical studies with at least two treatment arms. As two-arm studies with gene expression profiling have been rarer than similar one-arm studies, the methodology for constructing and optimizing predictive signatures has been less prominently explored than for prognostic signatures.

Results

Focusing on two “use cases” of two-arm clinical trials, one for metastatic colorectal cancer (CRC) patients treated with the anti-angiogenic molecule aflibercept, and the other for triple negative breast cancer (TNBC) patients treated with the small molecule iniparib, we present derivation steps and quantitative and graphical tools for the construction and optimization of signatures for the prediction of progression-free survival based on cross-validated multivariate Cox models. This general methodology is organized around two more specific approaches which we have called subtype correlation (subC) and mechanism-of-action (MOA) modeling, each of which leverage a priori knowledge of molecular subtypes of tumors or drug MOA for a given indication. The tools and concepts presented here include the so-called differential log-hazard ratio, the survival scatter plot, the hazard ratio receiver operating characteristic, the area between curves and the patient selection matrix. In the CRC use case for instance, the resulting signature stratifies the patient population into “sensitive” and “relatively-resistant” groups achieving a more than two-fold difference in the aflibercept-to-control hazard ratios across signature-defined patient groups. Through cross-validation and resampling the probability of generalization of the signature to similar CRC data sets is predicted to be high.

Conclusions

The tools presented here should be of general use for building and using predictive multivariate signatures in oncology and in other therapeutic areas.

Development and validation of a nomogram prognostic model for esophageal cancer patients with oligometastases

Platinum-based chemotherapy is recommended as the standard treatment for metastatic esophageal cancer (EC) patients; however, the outcome is poor. Oligometastasis is less aggressive and has limited growth potential. However, the prognostic factors for EC patients with oligometastases was largely unknown. Thus, we intend to determine the prognostic factors, and develop and validate nomograms for prediction of survival for EC patients with oligometastases. In this study, characteristics of 273 oligometastatic EC patients were analyzed using univariate and multivariate Cox models to determine the independent prognostic factors for progression-free survival (PFS) and overall survival (OS). The result showed that history of alcohol consumption, longer tumor, no local radiotherapy for EC, and no local treatment for metastases were independent factors for PFS. Sex, esophageal fistula, number of metastatic organs, and local radiotherapy for EC were independent prognostic factors for OS. On the basis of Cox models, the respective nomogram for prediction of PFS and OS was established with the corrected concordance index of 0.739 and 0.696 after internal cross-validation. In conclusion, local treatment for metastases and local radiotherapy for EC were demonstrated to be beneficial for oligometastatic EC patients, and the validated nomograms are valuable in prognosis prediction and could guide individualized management for these patients.

Structured sparsity regularization for analyzing high-dimensional omics data

The development of new molecular and cell technologies is having a significant impact on the quantity of data generated nowadays. The growth of omics databases is creating a considerable potential for knowledge discovery and, concomitantly, is bringing new challenges to statistical learning and computational biology for health applications. Indeed, the high dimensionality of these data may hamper the use of traditional regression methods and parameter estimation algorithms due to the intrinsic non-identifiability of the inherent optimization problem. Regularized optimization has been rising as a promising and useful strategy to solve these ill-posed problems by imposing additional constraints in the solution parameter space. In particular, the field of statistical learning with sparsity has been significantly contributing to building accurate models that also bring interpretability to biological observations and phenomena. Beyond the now-classic elastic net, one of the best-known methods that combine lasso with ridge penalizations, we briefly overview recent literature on structured regularizers and penalty functions that have been applied in biomedical data to build parsimonious models in a variety of underlying contexts, from survival to generalized linear models. These methods include functions of $\ell _k$-norms and network-based penalties that take into account the inherent relationships between the features. The successful application to omics data illustrates the potential of sparse structured regularization for identifying disease's molecular signatures and for creating high-performance clinical decision support systems towards more personalized healthcare. Supplementary information: Supplementary data are available at Briefings in Bioinformatics online.

2-[18F]FDG PET/CT radiomics in lung cancer: An overview of the technical aspect and its emerging role in management of the disease

Lung cancer is the most common cancer, worldwide, and a major health issue with a remarkable mortality rate. 2-[¹⁸F]fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography (2-[¹⁸F]FDG PET/CT) plays an indispensable role in the management of lung cancer patients. Long-established quantitative parameters such as size, density, and metabolic activity have been and are being employed in the current practice to enhance interpretation and improve diagnostic and prognostic value. The introduction of radiomics analysis revolutionized the quantitative evaluation of medical imaging, revealing data within images beyond visual interpretation. The "big data" are extracted from high-quality images and are converted into information that correlates to relevant genetic, pathologic, clinical, or prognostic features. Technically advanced, diverse methods have been implemented in different studies. The standardization of image acquisition, segmentation and features analysis is still a debated issue. Importantly, a body of features has been extracted and employed for diagnosis, staging, risk stratification, prognostication, and therapeutic response. 2-[¹⁸F]FDG PET/CT-derived features show promising value in non-invasively diagnosing the malignant nature of pulmonary nodules, differentiating lung cancer subtypes, and predicting response to different therapies as well as survival. In this review article, we aimed to provide an overview of the technical aspects used in radiomics analysis in non-small cell lung cancer (NSCLC) and elucidate the role of 2-[¹⁸F]FDG PET/CT-derived radiomics in the diagnosis, prognostication, and therapeutic response.