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.
PHASTAR will be attending Biotech Week Boston 2019, find us at BioPharm America on September 11-12th.
We are keen to discuss our new technology partnership with Medidata, the continued development of PHASTAR's Cambridge team and our plans for expansion to the West Coast and Japan!
Read more about BioPharm America here.