Dataset Information

Beyond Correlations, Sensitivities, and Specificities: A Roadmap for Demonstrating Utility of Advanced Imaging in Oncology Treatment and Clinical Trial Design.

ABSTRACT: Despite the widespread belief that advanced imaging should be very helpful in guiding oncology treatment decision and improving efficiency and success rates in treatment clinical trials, its acceptance has been slow. Part of this is likely attributable to gaps in study design and statistical methodology for these imaging studies. Also, results supporting the performance of the imaging in these roles have largely been insufficient to justify their use within the design of a clinical trial or in treatment decision making. Statistically significant correlations between the imaging results and clinical outcomes are often incorrectly taken as evidence of adequate performance. Assessments of whether the imaging can outperform standard techniques or meaningfully supplement them are also frequently neglected. This paper provides guidance on study designs and statistical analyses for evaluating the performance of advanced imaging in the various roles in treatment decision guidance and clinical trial conduct. Relevant methodology from the imaging literature is reviewed; gaps in the literature are addressed using related concepts from the more extensive genomic and in vitro biomarker literature.

SUBMITTER: Huang EP

PROVIDER: S-EPMC5547568 | biostudies-other | 2017 Aug

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Beyond Correlations, Sensitivities, and Specificities: A Roadmap for Demonstrating Utility of Advanced Imaging in Oncology Treatment and Clinical Trial Design.

Huang Erich P EP Lin Frank I FI Shankar Lalitha K LK

Academic radiology 20170426 8

Despite the widespread belief that advanced imaging should be very helpful in guiding oncology treatment decision and improving efficiency and success rates in treatment clinical trials, its acceptance has been slow. Part of this is likely attributable to gaps in study design and statistical methodology for these imaging studies. Also, results supporting the performance of the imaging in these roles have largely been insufficient to justify their use within the design of a clinical trial or in t ...[more]

PMID: 28456570

Similar Datasets

Project description:Across the life sciences, processing next generation sequencing data commonly relies upon a computationally expensive process where reads are mapped onto a reference sequence. Prior to such processing, however, there is a vast amount of information that can be ascertained from the reads, potentially obviating the need for processing, or allowing optimized mapping approaches to be deployed. Here, we present a method termed FlexTyper which facilitates a "reverse mapping" approach in which high throughput sequence queries, in the form of k-mer searches, are run against indexed short-read datasets in order to extract useful information. This reverse mapping approach enables the rapid counting of target sequences of interest. We demonstrate FlexTyper's utility for recovering depth of coverage, and accurate genotyping of SNP sites across the human genome. We show that genotyping unmapped reads can correctly inform a sample's population, sex, and relatedness in a family setting. Detection of pathogen sequences within RNA-seq data was sensitive and accurate, performing comparably to existing methods, but with increased flexibility. We present two examples of ways in which this flexibility allows the analysis of genome features not well-represented in a linear reference. First, we analyze contigs from African genome sequencing studies, showing how they distribute across families from three distinct populations. Second, we show how gene-marking k-mers for the killer immune receptor locus allow allele detection in a region that is challenging for standard read mapping pipelines. The future adoption of the reverse mapping approach represented by FlexTyper will be enabled by more efficient methods for FM-index generation and biology-informed collections of reference queries. In the long-term, selection of population-specific references or weighting of edges in pan-population reference genome graphs will be possible using the FlexTyper approach. FlexTyper is available at https://github.com/wassermanlab/OpenFlexTyper.

Project description:BackgroundInstrumented gait analysis (IGA) has been around for a long time but has never been shown to be useful for improving patient outcomes. In this study we demonstrate the potential utility of IGA by showing that machine learning models are better able to estimate treatment outcomes when they include both IGA and clinical (CLI) features compared to when they include CLI features alone.DesignWe carried out a retrospective analysis of data from ambulatory children diagnosed with cerebral palsy who were seen at least twice at our gait analysis center. Individuals underwent a variety of treatments (including no treatment) between sequential gait analyses. We fit Bayesian Additive Regression Tree (BART) models that estimated outcomes for mean stance foot progression to demonstrate the approach. We built two models: one using CLI features only, and one using CLI and IGA features. We then compared the models' performance in detail. We performed similar, but less detailed, analyses for a number of other outcomes. All results were based on independent test data from a 70%/30% training/testing split.ResultsThe IGA model was more accurate than the CLI model for mean stance-phase foot progression outcomes (RMSEIGA = 11∘, RMSECLI = 13∘) and explained more than 1.5 × as much of the variance (R2IGA = .45, R2CLI = .28). The IGA model outperformed the CLI model for every level of treatment complexity, as measured by number of simultaneous surgeries. The IGA model also exhibited superior performance for estimating outcomes of mean stance-phase knee flexion, mean stance-phase ankle dorsiflexion, maximum swing-phase knee flexion, gait deviation index (GDI), and dimensionless speed.InterpretationThe results show that IGA has the potential to be useful in the treatment planning process for ambulatory children diagnosed with cerebral palsy. We propose that the results of machine learning outcome estimators-including estimates of uncertainty-become the primary IGA tool utilized in the clinical process, complementing the standard medical practice of conducting a through patient history and physical exam, eliciting patient goals, reviewing relevant imaging data, and so on.

Dataset Information

Beyond Correlations, Sensitivities, and Specificities: A Roadmap for Demonstrating Utility of Advanced Imaging in Oncology Treatment and Clinical Trial Design.

Publications

Beyond Correlations, Sensitivities, and Specificities: A Roadmap for Demonstrating Utility of Advanced Imaging in Oncology Treatment and Clinical Trial Design.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets