The theme of the 25th Society for Clinical Data Management (SCDM) annual conference in Baltimore was to raise awareness of the upcoming trends in the industry and reflect on how they will affect the clinical data management community.
The leadership forum convened a day ahead of the conference. It was an excellent opportunity for industry experts to come together, present their views and discuss how emerging study designs, regulations, and technology innovations are reshaping the role and profile of clinical data management. The core of our discussions was the first of 3 whitepapers from the SCDM released in June 2019, “The Evolution of Clinical Data Management to Clinical Data Science.”
As part of the build-up to the Royal Statistical Society’s 2019 Conference in Belfast, PHASTAR's Head of Statistical Research, Jennifer Rogers, will be taking part in an interactive conversation hosted by the BBC Statistics and Big Data. Jennifer will be joined by Presenter & Writer Timandra Harkness and Journalist Michael Blastland. The conversation will be hosted by BBC Northern Ireland's William Crawley.
There is considerable hype surrounding Machine learning (ML) and Artificial Intelligence (AI) yet despite that, these technologies are real and powerful and this is starting to be realised in healthcare. In this article we briefly discuss ML and AI alongside some key healthcare examples including how ML has added value in clinical trials with hands on examples performed by experts from PHASTAR’s newly established data science team.
Although the terms AI and ML are frequently used interchangeably, they are not the same thing. AI is a broad concept that effectively describes how a machine can simulate natural human intelligence to solve a complex problem. AI is of course a moving target; based on those capabilities that a human possesses but a machine doesn’t. ML is one of the ways humans hope to achieve AI, where a machine can learn on its own without being programmed explicitly and without our constant supervision.
Integration of data from a number of clinical trials for an Integrated Summary of Safety (ISS) and Efficacy (ISE) requires careful planning and includes the following planning steps [see ICH M4]:
Assess the analysis and reporting requirement for the ISS/ISE
Consider these requirements against pre-existing study level analysis and reporting
Determine what data types need integrating across studies and at what level (SDTM/ADaM) the integration should occur at.
Assess the analysis and reporting requirement for the ISS/ISE
Before starting integrating data across studies it is key to have a clear understanding of what questions the ISS/ISE is trying to answer and how these requirements differ to those already answered by the individual studies.
In medical research, information on the outcomes of a treatment may be available from a number of clinical studies with similar treatment protocols. When the studies are considered individually, they may be either too small or too limited in scope to come to a general conclusion about the effect of the treatment. Meta-analysis, defined as the statistical analysis of a large collection of analytic results for the purpose of integrating the findings, attempts to combine the results of multiple studies in order to gain statistical power, strengthen the evidence about possible treatment effects and, in adequately-powered studies, learn more about subgroups and possible interactions.
In its simplest form, meta-analysis uses what are known as frequentist fixed-effect approaches, with weighted averages of fully aggregated data (obtained from publications), to compare two treatment groups. For example, this may use information on the mean weight loss and standard deviation for an active and placebo drug from five trials. More advanced methodologies (such as random-effects models, meta-regression, and Bayesian approaches) allow the researcher to incorporate complex data structures (such as subgroup data, or individual patient data (IPD)). Note that higher model complexity carries both advantages and disadvantages.
