Using a Clinically Interpretable End Point Composed of Multiple Outcomes to Evaluate Totality of Treatment Effect in Comparative Oncology Studies.
Ontology highlight
ABSTRACT:
SUBMITTER: Wang X
PROVIDER: S-EPMC10285578 | biostudies-literature | 2023 Jun
REPOSITORIES: biostudies-literature
Publications
Using a Clinically Interpretable End Point Composed of Multiple Outcomes to Evaluate Totality of Treatment Effect in Comparative Oncology Studies.
Wang Xiaofei X McCaw Zachary R ZR Tian Lu L Stinchcombe Thomas E TE Vokes Everett E Ludmir Ethan B EB Wei Lee-Jen LJ
JAMA network open 20230601 6
Similar Datasets
Project description:The application of logistic regression (LR) and Cox Proportional Hazard (CoxPH) models are well-established for evaluating exposure-response (E-R) relationship in large molecule oncology drugs. However, applying machine learning (ML) models on evaluating E-R relationships has not been widely explored. We developed a workflow to train regularized LR/CoxPH and tree-based XGboost (XGB) models, and derive the odds ratios for best overall response and hazard ratios for overall survival, across exposure quantiles to evaluate the E-R relationship using clinical trial datasets. The E-R conclusions between LR/CoxPH and XGB models are overall consistent, and largely aligned with historical pharmacometric analyses findings. Overall, applying this interpretable ML workflow provides a promising alternative method to assess E-R relationships for impacting key dosing decisions in drug development.
| S-EPMC9755920 | biostudies-literature
Project description:Background and objectivesRRT and doubling of serum creatinine are considered the objective hard end points in nephrology intervention trials. Because both are assumed to reflect changes in the filtration capacity of the kidney, drug effects, if present, are attributed to kidney protection. However, decisions to start RRT are not only on the basis of filtration capacity of the kidney, but also on other factors. We therefore compared the time to RRT with the time to a fixed eGFR threshold and assessed the effect of the renoprotective drug irbesartan on both components.Design, setting, participants, & measurementsPost hoc analysis of two clinical trials, the Irbesartan Diabetic Nephropathy Trial (IDNT) and Reduction of End points in Non-insulin dependent diabetes mellitus with the Angiotensin II Antagonist Losartan Trial, in patients with type 2 diabetes and nephropathy. The time to a predefined eGFR level of 11 ml/min per 1.73 m2 (eGFR11), calculated by within-patient linear regression, was compared with the time to RRT or sustained serum creatinine ≥6 mg/dl.ResultsA large difference was observed in the median time to RRT (779 days) compared with eGFR11 (678 days; P=0.01). We also observed a large variation in the difference between the time to RRT and eGFR11. In IDNT, the hazard ratio for the effect of irbesartan on the serum creatinine ≥6.0 mg/dl end point was 0.60 (95% confidence interval, 0.39 to 0.91; P=0.02), whereas it was smaller for the RRT end point (hazard ratio, 0.78; 95% confidence interval, 0.58 to 1.07; P=0.12).ConclusionsThis study shows a difference in the time to RRT and a fixed eGFR threshold, and shows that the effect of an angiotensin receptor blocker on a filtration-based end point versus RRT varies. This implies that evaluating renoprotective effects of drugs with a combined RRT and doubling of serum creatinine end point may result in evaluating other effects beyond renoprotection alone. Future trials should consider registering all parameters that lead to RRT decisions.
| S-EPMC5628725 | biostudies-literature
Project description:BackgroundDeep-learning applications in cardiology typically perform trivial binary classification and are able to discriminate between subjects affected or not affected by a specific cardiac disease. However, this working scenario is very different from the real one, where clinicians are required to recognize the occurrence of one cardiac disease among the several possible ones, performing a multiclass classification. The present work aims to create a new interpretable deep-learning tool able to perform a multiclass classification and, thus, discriminate among several different cardiac diseases.MethodsThe "China Physiological Signal Challenge in 2018" Physionet database was used to develop a multiclass neural network, constructed by the Advanced Repeated Structuring & Learning Procedure (AdvRS&LP). Data, consisting of 6877 12-lead 10-second electrocardiograms, was processed to obtain 252 electrocardiographic and vectorcardiographic input features, used to classify the data into eight classes (normal sinus rhythm, atrial fibrillation, first-degree atrioventricular block, left bundle branch block, right bundle branch block, premature atrial contraction, premature ventricular contraction, and unknown). Classification performance was evaluated by the area under the curve of the receiver operating characteristics. Clinical interpretability was assessed by standard statistical analysis and the local interpretable model-agnostic explainer algorithm.ResultsPerformance ranged from 89.88% to 90.10% (95.98 ± 3.32%) in the learning dataset and from 69.15% to 91.14% (83.65 ± 8.24%) in the testing dataset. These results are good considering the difficult, realistic multiclass classification task.ConclusionsThe proposed multiclass neural network constructed using the AdvRS&LP represents a promising deep-learning tool for discriminating several cardiac diseases while ensuring clinical interpretability.
| S-EPMC11742852 | biostudies-literature
Project description:BackgroundHypertension comprises a heterogeneous range of phenotypes. We asked whether underlying genetic structure could explain a part of this heterogeneity.MethodsOur study sample comprised N=198 148 FinnGen participants (56% women, mean age 58 years) and N=21 168 well-phenotyped FINRISK participants (53% women, mean age 50 years). First, we identified genetic hypertension components with an unsupervised Bayesian non-negative matrix factorization algorithm using public genome-wide association data for 144 genetic hypertension variants and 16 clinical traits. For these components, we computed their (1) cross-sectional associations with clinical traits in FINRISK using linear regression and (2) longitudinal associations with incident adverse outcomes in FinnGen using Cox regression.ResultsWe observed 4 genetic hypertension components corresponding to recognizable clinical phenotypes: obesity (high body mass index), dyslipidemia (low high-density lipoprotein cholesterol and high triglycerides), hypolipidemia (low low-density lipoprotein cholesterol and low total cholesterol), and short stature. In FINRISK, all hypertension components had robust associations with their respective clinical characteristics. In FinnGen, the Obesity component was associated with increased diabetes risk (hazard ratio per 1 SD increase 1.08 [Bonferroni corrected CI, 1.05-1.10]) and the Hypolipidemia component with increased autoimmune disease risk (hazard ratio per 1 SD increase 1.05 [Bonferroni corrected CI, 1.03-1.07]). In addition, all hypertension components were related to both hypertension and cardiovascular disease.ConclusionsOur unsupervised analysis demonstrates that the genetic basis of hypertension can be understood as a mixture of 4 broad, clinically interpretable components capturing disease heterogeneity. These components could be used to stratify individuals into specific genetic subtypes and, therefore, to benefit personalized health care and pharmaceutical research.
| S-EPMC9558213 | biostudies-literature
Project description:BackgroundThe availability of large epidemiological or clinical data storing biological samples allow to study the prognostic value of novel biomarkers, but efficient designs are needed to select a subsample on which to measure them, for parsimony and economical reasons. Two-phase stratified sampling is a flexible approach to perform such sub-sampling, but literature on stratification variables to be used in the sampling and power evaluation is lacking especially for survival data.MethodsWe compared the performance of different sampling designs to assess the prognostic value of a new biomarker on a time-to-event endpoint, applying a Cox model weighted by the inverse of the empirical inclusion probability.ResultsOur simulation results suggest that case-control stratified (or post stratified) by a surrogate variable of the marker can yield higher performances than simple random, probability proportional to size, and case-control sampling. In the presence of high censoring rate, results showed an advantage of nested case-control and counter-matching designs in term of design effect, although the use of a fixed ratio between cases and controls might be disadvantageous. On real data on childhood acute lymphoblastic leukemia, we found that optimal sampling using pilot data is greatly efficient.ConclusionsOur study suggests that, in our sample, case-control stratified by surrogate and nested case-control yield estimates and power comparable to estimates obtained in the full cohort while strongly decreasing the number of patients required. We recommend to plan the sample size and using sampling designs for exploration of novel biomarker in clinical cohort data.
| S-EPMC8091513 | biostudies-literature
Project description:Cytometry technologies are essential tools for immunology research, providing high-throughput measurements of the immune cells at the single-cell level. Existing approaches in interpreting and using cytometry measurements include manual or automated gating to identify cell subsets from the cytometry data, providing highly intuitive results but may lead to significant information loss, in that additional details in measured or correlated cell signals might be missed. In this study, we propose and test a deep convolutional neural network for analyzing cytometry data in an end-to-end fashion, allowing a direct association between raw cytometry data and the clinical outcome of interest. Using nine large cytometry by time-of-flight mass spectrometry or mass cytometry (CyTOF) studies from the open-access ImmPort database, we demonstrated that the deep convolutional neural network model can accurately diagnose the latent cytomegalovirus (CMV) in healthy individuals, even when using highly heterogeneous data from different studies. In addition, we developed a permutation-based method for interpreting the deep convolutional neural network model. We were able to identify a CD27- CD94+ CD8+ T cell population significantly associated with latent CMV infection, confirming the findings in previous studies. Finally, we provide a tutorial for creating, training, and interpreting the tailored deep learning model for cytometry data using Keras and TensorFlow (https://github.com/hzc363/DeepLearningCyTOF).
| S-EPMC7474669 | biostudies-literature
Project description:ImportanceA surrogate end point (SEP) is an end point used in clinical trials as an alternative for measuring the true clinical benefit. The use of SEPs in trials shortens their duration.ObjectivesTo investigate the use of SEPs in clinical trials to support the approval of anticancer drugs and to determine whether confirmatory studies that use overall survival (OS) as an end point are being conducted in Japan.Design, setting, and participantsIn this cross-sectional study, drug approvals and background information were obtained from publicly available information, such as the Pharmaceuticals and Medical Devices Agency website, for anticancer drugs approved in Japan from January 2001 to December 2020. Data analysis was performed from September 2021 to March 2022.Main outcomes and measuresCharacteristics of approved oncology drugs in Japan, end points for pivotal clinical trials, and outcomes of confirmatory trials using OS as an end point following drug approval.ResultsThere were 299 anticancer drugs approved in Japan during the study period. Of these, 142 (47.5%) were molecular-targeted drugs, the most common of which targeted non-small cell lung cancer. There were 111 (37.1%) anticancer drugs with orphan designation. From 2001 to 2005, OS was used as an end point in 1 approval (3.6%); however, from 2006 to 2020, OS was used in 86 approvals (31.7%). Of the 212 anticancer drugs approved on the basis of SEPs, confirmatory studies with OS as the end point were conducted for only 37 approvals (17.5%); for the remaining 175 approvals, studies are under way for 35 approvals (16.5%), were waivered for 75 approvals (35.4%), and were not conducted for 65 approvals (30.7%). Furthermore, in 20 drug approvals (9.4%), the conducted confirmatory studies were not effective in determining the OS, but the drugs were approved following re-examination.Conclusions and relevanceThe findings of this study suggest that starting from 2005, the use of OS as an end point has increased in studies supporting the approval of anticancer drugs in Japan. However, even after 2005, approximately two-thirds of these approvals were SEP based. Postmarketing surveillance studies of the true end points are necessary to validate the use of SEPs.
| S-EPMC10148198 | biostudies-literature
Project description: Not available
| S-EPMC10007880 | biostudies-literature
Project description:ImportanceObjective response rate (ORR) is an increasingly important end point for accelerated development of highly active anticancer therapies, yet its relationship to regulatory approval is not well characterized.ObjectiveTo identify circumstances in which a high ORR is associated with regulatory approval, and therefore might be an appropriate end point for definitive single-arm studies of anticancer therapies.Data sourceA database of all oncology clinical trials registered at clinicaltrials.gov between October 1, 2007, and September 30, 2010.Study selectionTrials of palliative systemic therapies for 4 measurable solid tumor types, limited to those with trial arms of at least 20 patients reporting ORR per Response Evaluation Criteria in Solid Tumors (RECIST).Data extraction and synthesisA systematic search was used to identify the reported ORR for each eligible treatment arm that had been presented publicly.Main outcomes and measuresFor each treatment regimen, defined as a single-agent or unique combination of agents for 1 cancer type, the mean ORR and the maximum ORR statistically exceeded were calculated, and their association with regulatory approval was studied. A regimen was considered approved for a specific cancer type if it had received regulatory approval in any country for treatment of advanced cancer of that type.ResultsFrom 1800 trials, 874 eligible trial arms in 578 eligible trials were identified; 542 arms had ORR data available for 294 regimens. Maximum ORR and mean ORR were significantly associated with regulatory approval (τ = 0.27, P < .001; τ = 0.12, P = .01); this relationship was stronger for single-agent therapies (τ = 0.49; τ = 0.41) than for combination regimens (τ = 0.28; τ = 0.17). Evaluation of ORR thresholds between 20% and 60% as potential trial end points demonstrated that ORR statistically exceeding 30% with a single agent had 98% specificity and 89% positive predictive value for identifying regimens achieving regulatory approval.Conclusions and relevanceFor single-agent regimens, high ORR was associated with regulatory approval; this relationship was less strong for combination regimens. Our data suggest that high ORR (eg, statistically exceeding an ORR of 30%) is an appropriate end point for single-arm trials aiming to demonstrate breakthrough activity of a single-agent anticancer therapy.
| S-EPMC5574183 | biostudies-literature
Project description:MotivationThe size of available omics datasets is steadily increasing with technological advancement in recent years. While this increase in sample size can be used to improve the performance of relevant prediction tasks in healthcare, models that are optimized for large datasets usually operate as black boxes. In high-stakes scenarios, like healthcare, using a black-box model poses safety and security issues. Without an explanation about molecular factors and phenotypes that affected the prediction, healthcare providers are left with no choice but to blindly trust the models. We propose a new type of artificial neural network, named Convolutional Omics Kernel Network (COmic). By combining convolutional kernel networks with pathway-induced kernels, our method enables robust and interpretable end-to-end learning on omics datasets ranging in size from a few hundred to several hundreds of thousands of samples. Furthermore, COmic can be easily adapted to utilize multiomics data.ResultsWe evaluated the performance capabilities of COmic on six different breast cancer cohorts. Additionally, we trained COmic models on multiomics data using the METABRIC cohort. Our models performed either better or similar to competitors on both tasks. We show how the use of pathway-induced Laplacian kernels opens the black-box nature of neural networks and results in intrinsically interpretable models that eliminate the need for post hoc explanation models.Availability and implementationDatasets, labels, and pathway-induced graph Laplacians used for the single-omics tasks can be downloaded at https://ibm.ent.box.com/s/ac2ilhyn7xjj27r0xiwtom4crccuobst/folder/48027287036. While datasets and graph Laplacians for the METABRIC cohort can be downloaded from the above mentioned repository, the labels have to be downloaded from cBioPortal at https://www.cbioportal.org/study/clinicalData?id=brca\_metabric. COmic source code as well as all scripts necessary to reproduce the experiments and analysis are publicly available at https://github.com/jditz/comics.
| S-EPMC10311322 | biostudies-literature