\n

\n

\n

\n

\n

\n

You can
now register for this event. Registration will close at 12:00 on 2nd Septe
mber 2020.

\n**PSI Members: **Free to attend

\n

\nTo register your place\, p
lease **click here**.<
/p>\n

This webinar will feature presentations from 3
speakers on the topic of Using Visualisations to Help Make Decisions:

\n

\n&bull\; Caroline Caudan - Interactive statistical monitoring to
optimize review of potential study issue with R-Shiny

\n&bull\; Paol
o Eusebi - Effective visualization of uncertainty &ndash\; Where we are an
d where to go

\n&bull\; Michael O&rsquo\;Kelly - Subgroup analysis: a
look at the SEAMOS approach (Standardised Effects Adjusted for Multiple O
verlapping Subgroups)

\n

\nThese presentations were originally p
lanned as part of the 2020 PSI conference in Barcelona\, and have been reo
rganized as a webinar.

\n
\n | \n
| \n |

\n
\; \n\; \n |
\n Caroline is a Statistician with 10 years of experience. S he started her career working on the manufacturing and control part of the pharmaceutical industry in order to improve production and control proces ses. \nFor the last 4 years\, she has been working as a biostatistician on the clinical part of the product development. Since sh e joined Keyrus Biopharma 3 years ago\, she has been involved in the contr ol and analysis of biomarker data\, which led her to take a close interest to graphical representation and data visualization. Following this\, Caro line started to work\, in collaboration with Roche\, on the development of a R Shiny application as a support to statistical monitoring. \n | \n
Background: Statistical Monitoring involves the review of prospective study data coll ected in participating site to detect inconsistencies between patients and between sites in term of trends. \nMethod: A Phase IV s tudy (PRO-MSACTIVE) is currently evaluating ocrelizumab in active relapsin g Multiple Sclerosis patients in France. Specific statistical methods (vol cano plots\, mahalanobis distance\, funnel plot &hellip\;)\, described in a statistical monitoring plan\, have been applied to SDTM database to dete ct potential issues (duplicate records\, under-reporting of AEs or PROs\, outliers\, patients with similar characteristics&hellip\;). An application has been developed using R-Shiny to generate an interactive web app to ea se the identification of site and/or patient during the statistical data r eview meeting. \nResults: The PRO-MSACTIVE study enrolle
d 422 patients by 46 sites between July 2018 and August 2019. The 3 Conclusion: Statistical monitori
ng is useful to identify unusual or clustered data patterns that might be
revealing issues that could impact the data integrity and/or may potential
ly impact patient&rsquo\;s safety. With appropriate interactive data visua
lization\, the important findings can easily be identified/reviewed by stu
dy team and appropriate actions be set up and assigned to the most appropr
iate function for a close follow-up. Interactive statistical monitoring is
time consuming to initiate using R-Shiny\, but time saving from the 1 |

\n
\; \n\; \n | \n Paolo Eusebi is a Consultant Statistician and Statistical Programmer. He is work ing as Contract Statistician for UCB. He is also adjunct Professor of Medi cal Statistics at the Epidemiology Department of Perugia University. His m ain research interests are the application of mixture models in meta-analy sis\, the use of machine learning techniques for subgroup identification a nd the display of uncertainty in scientific communication. He is statistic al reviewer for Lancet Neurology and Associate Editor of BMC Medical Resea rch Methodology. He is an active member of PSI and Data Visualization Soci ety. \n | \n
Statistics is all about uncertainty and uncertainty shows up in different ways in ou r research. If we want to answer questions about the development of the sy mptoms of an individual patient\, we explore the overall distribution of t he patients. For questions about the differences between e.g. treatment gr oups in studies\, we are interested on the precision of the treatment effe ct. And as statisticians we face uncertainty by applying models with limit ed knowledge about the data generating processes. \nThe communication about uncertainty in its different forms plays a central rol e in statistics\, yet it&rsquo\;s not well done in high profile medical jo urnals. A random sample (n=50) was obtained from 777 RCTs papers published in BMJ\, JAMA\, Lancet and NEJM from November 2017 to October 2019. \ nOverall\, uncertainty was not even considered in most of t he plots. Those displaying uncertainty predominantly used whiskers or band s for confidence intervals. However\, confidence intervals only poorly giv e a perception of a distribution. \nThe presentation wi ll showcase different ways to better display uncertainty as inspired from other fields\, including politics and weather forecast. These examples wil l cover also interactive and dynamic plots\, which can enrich data visuali zation experience in electronic media. \nApplications o
f these techniques for clinical trials and other medical data sources will
be shown in addition to demonstrate how communication of uncertainty can
be improved in medical statistics. These applications will make use of bot
h frequentist and Bayesian approaches. |

\n
\n \; \n&nbs p\; \n | \n With colleagues Michael O&rsquo\;Kelly has develope d new methods for missing data that are now widely used in clinical trials . His book authored with Bohdana Ratitch\, &ldquo\;Clinical trials with mi ssing data: a guide for practitioners&rdquo\;\, was published in 2014 by W iley. He has given a PSI course on missing data\, and co-authored a Best P ractice proposal for projects involving Modelling and Simulation\, which w as adopted by the PSI board in 2017. He received the RSS/PSI award for Exc ellence in Pharmaceutical Statistics in 2017\; he is Senior Director with IQVIA Advisory Services Analytics. \n | \n
In 2018\, the P
SI/EFSPI Working Group on Subgroup Analysis issued a White Paper in Pharma
ceutical Statistics\, which noted the usefulness of SEAMOS\, a forest-plot
based approach\, as well as a number of other approaches. SEAMOS resample
s from the data\, using as its criterion the most extreme estimate of trea
tment effect\, compared to the overall estimate of treatment effect. This
presentation explores the SEAMOS approach further\, using an idea due to P
SI/EFSPI Working Group member Tom Parke\, where the candidate subgroups of
the forest plot are assessed collectively\, using as a criterion the over
lap of the multiple confidence intervals of standardised treatment effect
estimates\, where the measure of difference in subgroups is the confidence
level required to preserve overlap of confidence intervals within a set o
f categories (e.g. preserve overlap between male and female\; preserve ove
rlap across regions). SEAMOS and its variants give rise to plots that may
help in understanding the true significance of subgroup differences\; furt
hermore\, some multivariate parametric assessment of the &ldquo\;extremene
ss&rdquo\; of the subgroups in a forest plot is possible\, as well as the
resampling-based approach described in the source paper. This presentation
looks at what can work best in practice\, and when. \n |

\;

END:VEVENT END:VCALENDAR