A novel nonparametric time-dependent precision-recall curve estimator for right-censored survival data

In order to assess prognostic risk for individuals in precision health research, risk prediction models are increasingly used, in which statistical models are used to estimate the risk of future outcomes based on clinical and nonclinical characteristics. The predictive accuracy of a risk score must be assessed before it can be used in routine clinical decision making, where the receiver operator characteristic curves, precision-recall curves, and their corresponding area under the curves are commonly used metrics to evaluate the discriminatory ability of a continuous risk score. Among these the precision-recall curves have been shown to be more informative when dealing with unbalanced biomarker distribution between classes, which is common in rare event, even though except one, all existing methods are proposed for classic uncensored data. This paper is therefore to propose a novel nonparametric estimation approach for the time-dependent precision-recall curve and its associated area under the curve for right-censored data. A simulation is conducted to show the better finite sample property of the proposed estimator over the existing method and a real-world data from primary biliary cirrhosis trial is used to demonstrate the practical applicability of the proposed estimator.

Time-dependent receiver operating characteristic curve estimator for correlated right-censored time-to-event data

In clinical trials, evaluating the accuracy of risk scores (markers) derived from prognostic models for prediction of survival outcomes is of major concern. The time-dependent receiver operating characteristic curve and the corresponding area under the receiver operating characteristic curve are appealing measures to evaluate the predictive accuracy. Several estimation methods have been proposed in the context of classical right-censored data which assumes the event time of individuals are independent. In many applications, however, this may not hold true if, for example, individuals belong to clusters or experience recurrent events. Estimates may be biased if this correlated nature is not taken into account. This paper is then aimed to fill this knowledge gap to introduce a time-dependent receiver operating characteristic curve and the corresponding area under the receiver operating characteristic curve estimation method for right-censored data that take the correlated nature into account. In the proposed method, the unknown status of censored subjects is imputed using conditional survival functions given the marker and frailty of the subjects. An extensive simulation study is conducted to evaluate and demonstrate the finite sample performance of the proposed method. Finally, the proposed method is illustrated using two real-world examples of lung cancer and kidney disease.

The impact of bilateral brachial-ankle pulse wave velocity difference on cardiovascular disease and all-cause mortality

Background

This study aims to investigate the association between an elevated bilateral pulse wave velocity difference (BPWVD) and cardiovascular diseases (CVDs) and all-cause mortality.

Methods

This study included a total of 38,356 participants. A multivariable Cox proportional hazards regression was used to assess the association between high BPWVD and the increased risk of CVDs and all-cause mortality by calculating hazard ratios (HRs) with 95% confidence intervals.

Results

A total of 1,213 cases of CVDs were identified over a mean duration of 6.19 years, including 886 cases of cerebral infarction (CI), 105 cases of intracerebral hemorrhage (ICH), and 222 cases of myocardial infarction (MI), along with 1,182 cases of all-cause mortality. The median BPWVD was 42 cm/s (19-80 cm/s). After adjusting for all confounders and baseline brachial-ankle PWV (baPWV), our analysis revealed a significant correlation between a higher risk of CVDs, MI, and all-cause mortality with an increase in BPWVD per standard deviation. HRs (95% confidence interval) were found to be 1.06 (1.01-1.11), 1.11 (1.02-1.21), and 1.07 (1.04-1.10), respectively. Among the participants with higher baPWV on the left side, the HRs (95% confidence interval) were 1.08 (1.02-1.14) for CVDs, 1.27 (1.10-1.46) for incident ICH, 1.16 (1.00-1.24) for incident MI, and 1.10 (1.07-1.15) for all-cause mortality, for per standard deviation increase in BPWVD.

Conclusions

Our findings reveal a significant correlation between elevated BPWVD and the risks of developing CVDs and all-cause mortality. This highlights the importance of thoroughly evaluating BPWVD as a means of detecting individuals at risk for CVDs and mortality.

Value of enhanced computed tomography in differentiating small mesenchymal tumours of the gastrointestinal from smooth muscle tumours

BACKGROUND

Computed tomography (CT) technology has been gradually used in the differentiation of small mesenchymal tumors of the stomach and intestines from smooth muscle tumours.

AIM

To explore the value of enhanced CT in the differentiation of small mesenchymal tumors of the stomach and intestines from smooth muscle tumours.

METHODS

Clinical data of patients with gastric mesenchymal or gastric smooth muscle tumours who were treated in our hospital from May 2018 to April 2023 were retrospectively analysed. Patients were divided into the gastric mesenchymal tumor group and the gastric smooth muscle tumor group respectively (n = 50 cases per group). Clinical data of 50 healthy volunteers who received physical examinations in our hospital during the same period were selected and included in the control group. Serum levels of carcinoembryonic antigen (CEA), alpha-fetoprotein (AFP), carbohydrate antigen 19-9 (CA19-9), CA-125 and cytokeratin 19 fragment antigen 21-1 were compared among the three groups. The value of CEA and CA19-9 in the identification of gastric mesenchymal tumours was analysed using the receiver operating characteristic (ROC) curve. The Kappa statistic was used to analyse the consistency of the combined CEA and CA19-9 test in identifying gastric mesenchymal tumours.

RESULTS

CEA levels varied among the three groups in the following order: The gastric mesenchymal tumour group > the control group > the gastric smooth muscle tumour group. CA19-9 levels varied among the three groups in the following order: The gastric mesenchymal group > the gastric smooth muscle group > the control group, the difference was statistically significant (P < 0.05). ROC analysis showed that the area under the curve of CEA and CA19-9 was 0. 879 and 0. 782, respectively.

CONCLUSION

Enhanced CT has shown value in differentiating small mesenchymal tumors of the stomach and intestines from smooth muscle tumors.

A semi-parametric approach for time-dependent ROC curves with nonignorable missing biomarker

The main purpose of this paper is to survey the statistical inference for covariate-specific time-dependent receiver operating characteristic (ROC) curves with nonignorable missing continuous biomarker values. To construct time-dependent ROC curves, we consider a joint model which assumes that the failure time depends on the continuous biomarker and the covariates through a Cox proportional hazards model and that the continuous biomarker depends on the covariates through a semiparametric location model. Assuming a purely parametric model on the propensity score, we utilize instrumental variables to deal with the identifiable issue and estimate the unknown parameters of the propensity score by a simple and efficient method. In addition, when the propensity score is estimated, we develop HT and AIPW approaches to estimate our interested quantities. In the presence of nonignorable missing biomarker, our AIPW estimators of the interested quantities are still doubly robust when the true propensity score is a special parametric logistic model. At last, simulation studies are conducted to assess the performance of our proposed approaches, and a real data analysis is also carried out to illustrate its application.

The different predictive value of mean platelet volume-to-lymphocyte ratio for postoperative recurrence between non-muscular invasive bladder cancer patients treated with intravesical chemotherapy and intravesical chemohyperthermia

Introduction

The inflammatory response plays a potential role in postoperative recurrence in patients with non-muscular invasive bladder cancer (NMIBC). We aimed to investigate whether platelet-to-lymphocyte ratio (PLR), mean platelet volume to lymphocyte ratio (MPVLR), and the systemic immune-inflammatory index (SII) have prognostic values in NMIBC treated with conventional intravesical chemotherapy or intravesical Chemohyperthermia (CHT) and the differences between them.

Materials and methods

A retrospective cohort study was conducted on 222 patients with NMIBC treated with Intravesical Chemotherapy or Intravesical CHT between January 2016 and December 2020. Within a week before surgery, PLR, MPVLR, and SII were determined based on routine blood settling. The optimal cutoff value of each index was determined using the receiver operating characteristic curve, and various groups were categorized accordingly. The factors influencing the prognosis of NMIBC patients receiving various treatments were investigated using the Kaplan- Meier survival curve and the Cox regression model.

Results

69 cases (46.3%) in the gemcitabine (GEM) group had tumor recurrence and 19 (12.8%) of them progressed to muscle-invasive bladder cancer (MIBC) or got metastasis, while 19 cases (26.0%) in the CHT group recurred and 2 (2.7%) progressed. Elevated PLR, MPVLR, and SII were associated with higher recurrence rates in the GEM group. Meanwhile, PLR and MPVLR were the independent risk factors. While in the CHT group, high PLR and SII were related to postoperative recurrence and none of them were independent risk factors.

Conclusion

The preoperative clinical inflammatory indexes PLR, SII, and MPVLR have certain predictive value for the postoperative recurrence-free survival (RFS) in NMIBC patients treated with intravesical chemotherapy while PLR and SII can predict the prognosis of NMIBC patients treated with intravesical CHT, which indicates that intravesical CHT may stop tumor recurrence by influencing the effect of mean platelet volume on tumor growth through some unknown mechanisms.

A microRNA Prognostic Signature in Patients with Diffuse Intrinsic Pontine Gliomas through Non-Invasive Liquid Biopsy

Simple Summary

Diffuse intrinsic pontine glioma (DIPG) is a neuro-radiologically defined tumor of the brainstem, primarily affecting children, with most diagnoses occurring between 5 and 7 years of age. Surgical removal in DIPGs is not feasible. Subsequent tumor progression is almost universal and no biomarker for predicting the course of the disease has entered into clinical practice so far. Under these premises, it is essential to develop reliable biomarkers that are able to improve outcomes and stratify patients using non-invasive methods to determine tumor profiles. We designed a study assessing circulating miRNA expression by a high-throughput platform and divided patients into training and validation phases in order to disclose a potential signature with clinical impact. Our results for the first time have proved the usefulness of blood-circulating nucleic acids as powerful, easy-to-assay molecular markers of disease status in DIPG.

Abstract

Diffuse midline gliomas (DMGs) originate in the thalamus, brainstem, cerebellum and spine. This entity includes tumors that infiltrate the pons, called diffuse intrinsic pontine gliomas (DIPGs), with a rapid onset and devastating neurological symptoms. Since surgical removal in DIPGs is not feasible, the purpose of this study was to profile circulating miRNA expression in DIPG patients in an effort to identify a non-invasive prognostic signature with clinical impact. Using a high-throughput platform, miRNA expression was profiled in serum samples collected at the time of MRI diagnosis and prior to radiation and/or systemic therapy from 47 patients enrolled in clinical studies, combining nimotuzumab and vinorelbine with concomitant radiation. With progression-free survival as the primary endpoint, a semi-supervised learning approach was used to identify a signature that was also tested taking overall survival as the clinical endpoint. A signature comprising 13 circulating miRNAs was identified in the training set (n = 23) as being able to stratify patients by risk of disease progression (log-rank p = 0.00014; HR = 7.99, 95% CI 2.38–26.87). When challenged in a separate validation set (n = 24), it confirmed its ability to predict progression (log-rank p = 0.00026; HR = 5.51, 95% CI 2.03–14.9). The value of our signature was also confirmed when overall survival was considered (log-rank p = 0.0021, HR = 4.12, 95% CI 1.57–10.8). We have identified and validated a prognostic marker based on the expression of 13 circulating miRNAs that can shed light on a patient’s risk of progression. This is the first demonstration of the usefulness of nucleic acids circulating in the blood as powerful, easy-to-assay molecular markers of disease status in DIPG. This study provides Class II evidence that a signature based on 13 circulating miRNAs is associated with the risk of disease progression.

Time-dependent ROC curve estimation for interval-censored data

The receiver-operating characteristic (ROC) curve is the most popular graphical method for evaluating the classification accuracy of a diagnostic marker. In time-to-event studies, the subject's event status is time-dependent, and hence, time-dependent extensions of ROC curve have been proposed. However, in practice, the calculation of this curve is not straightforward due to the presence of censoring that may be of different types. Existing methods focus on the more standard and simple case of right-censoring and neglect the general case of mixed interval-censored data that may involve left-, right-, and interval-censored observations. In this context, we propose and study a new time-dependent ROC curve estimator. We also consider some summary measures (area under the ROC curve and Youden index) traditionally associated with ROC as well as the Youden-based cutoff estimation method. The proposed method uses available data very efficiently. To this end, the unknown status (positive or negative) of censored subjects are estimated from the data via the estimation of the conditional survival function given the marker. For that, we investigate both model-based and nonparametric approaches. We also provide variance estimates and confidence intervals using Bootstrap. A simulation study is conducted to investigate the finite sample behavior of the proposed methods and to compare their performance with a competitor. Globally, we observed better finite sample performances for the proposed estimators. Finally, we illustrate the methods using two data sets one from a hypobaric decompression sickness study and the other from an oral health study. The proposed methods are implemented in the R package cenROC.

Decoding health status transitions of over 200 000 patients with traumatic brain injury from preceding injury to the injury event

For centuries, the study of traumatic brain injury (TBI) has been centred on historical observation and analyses of personal, social, and environmental processes, which have been examined separately. Today, computation implementation and vast patient data repositories can enable a concurrent analysis of personal, social, and environmental processes, providing insight into changes in health status transitions over time. We applied computational and data visualization techniques to categorize decade-long health records of 235,003 patients with TBI in Canada, from preceding injury to the injury event itself. Our results highlighted that health status transition patterns in TBI emerged along with the projection of comorbidity where many disorders, social and environmental adversities preceding injury are reflected in external causes of injury and injury severity. The strongest associations between health status preceding TBI and health status at the injury event were between multiple body system pathology and advanced age-related brain pathology networks. The interwoven aspects of health status on a time continuum can influence post-injury trajectories and should be considered in TBI risk analysis to improve prevention, diagnosis, and care.

A Novel Immune-Gene Pair Signature Revealing the Tumor Microenvironment Features and Immunotherapy Prognosis of Muscle-Invasive Bladder Cancer

Immunotherapy has been a milestone for muscle-invasive bladder cancer (MIBC), but only a small portion of patients can benefit from it. Therefore, it is crucial to develop a robust individualized immune-related signature of MIBC to identify patients potentially benefiting from immunotherapy. The current study identified patients from the Cancer Genome Atlas (TCGA) and immune genes from the ImmPort database, and used improved data analytical methods to build up a 45 immune-related gene pair signature, which could classify patients into high-risk and low-risk groups. The signature was then independently validated by a Gene Expression Omnibus (GEO) dataset and IMvigor210 data. The subsequent analysis confirmed the worse survival outcomes of the high-risk group in both training (p < 0.001) and validation cohorts (p = 0.018). A signature-based risk score was proven to be an independent risk factor of overall survival (p < 0.001) and could predict superior clinical net benefit compared to other clinical factors. The CIBERSORT algorithm revealed the low-risk group had increased CD8⁺ T cells plus memory-activated CD4⁺ T-cell infiltration. The low-risk group also had higher expression of PDCD1 (PD-1), CD40, and CD27, and lower expression of CD276 (B7-H3) and PDCD1LG2 (PD-L2). Importantly, IMvigor210 data indicated that the low-risk group had higher percentage of “inflamed” phenotype plus less “desert” phenotype, and the survival outcomes were significantly better for low-risk patients after immunotherapy (p = 0.014). In conclusion, we proposed a novel and promising prognostic immune-related gene pair (IRGP) signature of MIBC, which could provide us a panoramic view of the tumor immune microenvironment of MIBC and independently identify MIBC patients who might benefit from immunotherapy.

A lipid metabolism-related genes prognosis biomarker associated with the tumor immune microenvironment in colorectal carcinoma

Background and aim

Lipid metabolic reprogramming is considered to be a new hallmark of malignant tumors. The purpose of this study was to explore the expression profiles of lipid metabolism-related genes (LMRG) in colorectal cancer (CRC).

Methods

The lipid metabolism statuses of 500 CRC patients from the Cancer Genome Atlas (TCGA) and 523 from the Gene Expression Omnibus (GEO GSE39582) database were analyzed. The risk signature was constructed by univariate Cox regression and least absolute shrinkage and selection operator (LASSO) Cox regression.

Results

A novel four-LMRG signature (PROCA1, CCKBR, CPT2, and FDFT1) was constructed to predict clinical outcomes in CRC patients. The risk signature was shown to be an independent prognostic factor for CRC and was associated with tumour malignancy. Principal components analysis demonstrated that the risk signature could distinguish between low- and high-risk patients. There were significantly differences in abundances of tumor-infiltrating immune cells and mutational landscape between the two risk groups. Patients in the low-risk group were more likely to have higher tumor mutational burden, stem cell characteristics, and higher PD-L1 expression levels. Furthermore, a genomic-clinicopathologic nomogram was established and shown to be a more effective risk stratification tool than any clinical parameter alone.

Conclusions

This study demonstrated the prognostic value of LMRG and showed that they may be partially involved in the suppressive immune microenvironment formation.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-021-08902-5.

Applying immune-related lncRNA pairs to construct a prognostic signature and predict the immune landscape of stomach adenocarcinoma

Background: Long noncoding RNAs (lncRNAs) are associated with the survival of cancer patients. We constructed an immune-related lncRNA (irlncRNA) pair signature for stomach adenocarcinoma (STAD).Research design and methods: irlncRNAs were identified via coexpression analysis with immune-related genes. Differentially expressed irlncRNAs (DEirlncRNAs) were paired. Least absolute shrinkage and selection operator (LASSO) and multivariate Cox proportional hazards regression methods were used to construct the signature. We calculated the area under the receiver operating characteristic (ROC) curve and determined the best cutoff value according to the Akaike information criterion (AIC). Patients were divided into high - and low-risk groups, and differences in immune cell infiltration, tumor mutation burden (TMB) and drug treatment effects between the groups were explored according to the risk score.Results: An 8-irlncRNA-pair signature was constructed and proven to be a strong prognosis predictor in STAD patients through external verification. Moreover, the risk score was identified as an independent prognostic factor. There were significant differences in immune cell infiltration and the response to several drug treatments between patients with high and low risk scores, and the risk score was negatively correlated with TMB.Conclusions: The signature consisting of 8 irlncRNA pairs showed good prognostic predictive value.

Smoothed time-dependent receiver operating characteristic curve for right censored survival data

The prediction reliability is of primary concern in many clinical studies when the objective is to develop new predictive models or improve existing risk scores. In fact, before using a model in any clinical decision making, it is very important to check its ability to discriminate between subjects who are at risk of, for example, developing certain disease in a near future from those who will not. To that end, the time-dependent receiver operating characteristic (ROC) curve is the most commonly used method in practice. Several approaches have been proposed in the literature to estimate the ROC nonparametrically in the context of survival data. But, except one recent approach, all the existing methods provide a nonsmooth ROC estimator whereas, by definition, the ROC curve is smooth. In this article we propose and study a new nonparametric smooth ROC estimator based on a weighted kernel smoother. More precisely, our approach relies on a well-known kernel method used to estimate cumulative distribution functions of random variables with bounded supports. We derived some asymptotic properties for the proposed estimator. As bandwidth is the main parameter to be set, we present and study different methods to appropriately select one. A simulation study is conducted, under different scenarios, to prove the consistency of the proposed method and to compare its finite sample performance with a competitor. The results show that the proposed method performs better and appear to be quite robust to bandwidth choice. As for inference purposes, our results also reveal the good performances of a proposed nonparametric bootstrap procedure. Furthermore, we illustrate the method using a real data example.

On the validity of time-dependent AUC estimation in the presence of cure fraction

During the last decades, several approaches have been proposed to estimate the time-dependent area under the receiver operating characteristic curve (AUC) of risk tools derived from survival data. The validity of these estimators relies on some regularity assumptions among which a survival function being proper. In practice, this assumption is not always satisfied because a fraction of the population may not be susceptible to experience the event of interest even for long follow-up. Studying the sensitivity of the proposed estimators to the violation of this assumption is of substantial interest. In this paper, we investigate the performance of a nonparametric simple estimator, developed for classical survival data, in the case when the population exhibits a cure fraction. Motivated from the current practice of deriving risk tools in oncology and cardiovascular disease prevention, we also assess the loss, in terms of predictive performance, when deriving risk tools from survival models that do not acknowledge the presence of cure. The simulation results show that the investigated method is valid even under the presence of cure. They also show that risk tools derived from survival models that ignore the presence of cure have smaller AUC compared to those derived from survival models that acknowledge the presence of cure. This was also attested with a real data analysis from a breast cancer study.