Dataset Information

Real-world Independent Testing of e-ASPECTS Software (RITeS): statistical analysis plan [version 1; peer review: 2 approved]

ABSTRACT: Background: Artificial intelligence-based software may automatically detect ischaemic stroke lesions and provide an Alberta Stroke Program Early CT score (ASPECTS) on CT, and identify arterial occlusion and provide a collateral score on CTA. Large-scale independent testing will inform clinical use, but is lacking. We aim to test e-ASPECTS and e-CTA (Brainomix, Oxford UK) using CT scans obtained from a range of clinical studies. Methods: Using prospectively collected baseline CT and CTA scans from 10 national/international clinical stroke trials or registries (total >6600 patients), we will select a large clinically representative sample for testing e-ASPECTS and e-CTA compared to previously acquired independent expert human interpretation (reference standard). Our primary aims are to test agreement between software-derived and masked human expert ASPECTS, and the diagnostic accuracy of e-ASPECTS for identifying all causes of stroke symptoms using follow-up imaging and final clinical opinion as diagnostic ground truth. Our secondary aims are to test when and why e-ASPECTS is more or less accurate, or succeeds/fails to produce results, agreement between e-CTA and human expert CTA interpretation, and repeatability of e-ASPECTS/e-CTA results. All testing will be conducted on an intention-to-analyse basis. We will assess agreement between software and expert-human ratings and test the diagnostic accuracy of software. Conclusions: RITeS will provide comprehensive, robust and representative testing of e-ASPECTS and e-CTA against the current gold-standard, expert-human interpretation.

SUBMITTER: Mair G

PROVIDER: S-EPMC7612993 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:DNA methylation is an important biological process that involves the reversible addition of chemical tags called methyl groups to DNA and affects whether genes are active or inactive. Individual methylation profiles are determined by both genetic and environmental influences. Inter-individual variation in DNA methylation profiles can be exploited to estimate or predict a wide variety of human characteristics and disease risk profiles. Indeed, a number of methylation-based predictors of human traits have been developed and linked to important health outcomes. However, there is an unmet need to communicate the applicability and limitations of state-of-the-art methylation-based predictors to the wider community. To address this need, we have created a secure, web-based interactive platform called ‘MethylDetectR’ which automates the calculation of estimated values or scores for a variety of human traits using blood methylation data. These traits include age, lifestyle traits and high-density lipoprotein cholesterol. Methylation-based predictors often return scores on arbitrary scales. To provide meaning to these scores, users can interactively view how estimated trait scores for a given individual compare against other individuals in the sample. Users can optionally upload binary phenotypes and investigate how estimated traits vary according to case vs. control status for these phenotypes. Users can also view how different methylation-based predictors correlate with one another, and with phenotypic values for corresponding traits in a large reference sample (n = 4,450; Generation Scotland). The ‘MethylDetectR’ platform allows for the fast and secure calculation of DNA methylation-derived estimates for several human traits. This platform also helps to show the correlations between methylation-based scores and corresponding traits at the level of a sample, report estimated health profiles at an individual level, demonstrate how scores relate to important binary outcomes of interest and highlight the current limitations of molecular health predictors.

Project description:Mounting evidence indicates that worldwide, innovation systems are increasing unsustainable. Equally, concerns about inequities in the science and innovation process, and in access to its benefits, continue. Against a backdrop of growing health, economic and scientific challenges global stakeholders are urgently seeking to spur innovation and maximize the just distribution of benefits for all. Open Science collaboration (OS) - comprising a variety of approaches to increase open, public, and rapid mobilization of scientific knowledge - is seen to be one of the most promising ways forward. Yet, many decision-makers hesitate to construct policy to support the adoption and implementation of OS without access to substantive, clear and reliable evidence. In October 2017, international thought-leaders gathered at an Open Science Leadership Forum in the Washington DC offices of the Bill and Melinda Gates Foundation to share their views on what successful Open Science looks like. Delegates from developed and developing nations, national governments, science agencies and funding bodies, philanthropy, researchers, patient organizations and the biotechnology, pharma and artificial intelligence (AI) industries discussed the outcomes that would rally them to invest in OS, as well as wider issues of policy and implementation. This first of two reports, summarizes delegates' views on what they believe OS will deliver in terms of research, innovation and social impact in the life sciences. Through open and collaborative process over the next months, we will translate these success outcomes into a toolkit of quantitative and qualitative indicators to assess when, where and how open science collaborations best advance research, innovation and social benefit. Ultimately, this work aims to develop and openly share tools to allow stakeholders to evaluate and re-invent their innovation ecosystems, to maximize value for the global public and patients, and address long-standing questions about the mechanics of innovation.

Project description:Areas of open science (OS) policy and practice are already relatively well-advanced in several countries and sectors through the initiatives of some governments, funders, philanthropy, researchers and the community. Nevertheless, the current research and innovation system, including in the focus of this report, the life sciences, remains weighted against OS. In October 2017, thought-leaders from across the world gathered at an Open Science Leadership Forum in the Washington DC office of the Bill and Melinda Gates Foundation to share their views on what successful OS looks like. We focused on OS partnerships as this is an emerging model that aims to accelerate science and innovation. These outcomes are captured in a first meeting report: Defining Success in Open Science. On several occasions, these conversations turned to the challenges that must be addressed and new policies required to effectively and sustainably advance OS practice. Thereupon, in this report, we describe the concerns raised and what is needed to address them supplemented by our review of the literature, and suggest the stakeholder groups that may be best placed to begin to take action. It emerges that to be successful, OS will require the active engagement of all stakeholders: while the research community must develop research questions, identify partners and networks, policy communities need to create an environment that is supportive of experimentation by removing barriers. This report aims to contribute to ongoing discussions about OS and its implementation. It is also part of a step-wise process to develop and mobilize a toolkit of quantitative and qualitative indicators to assist global stakeholders in implementing high value OS collaborations. Currently in co-development through an open and international process, this set of measures will allow the generation of needed evidence on the influence of OS partnerships on research, innovation, and critical social and economic goals.

Dataset Information

Real-world Independent Testing of e-ASPECTS Software (RITeS): statistical analysis plan [version 1; peer review: 2 approved]

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets