13th International Congress
THE "NEW FRONTIERS"
OF ARRHYTHMIAS 1998

January 24-31, 1998
Marilleva, Trento, Italy

RT-86

Statistical analysis and epidemiologic methods in the arrhythmologic literature

Catherine Klersy, Angela Pistorio, Moreno Curti, Carmine Tinelli, Donatella De Amici, Gabriella Gabutti*, Andrea Zeccato*.
Scientific Direction, Biometry and *Scientific Library, IRCCS Policlinico San Matteo, Pavia, Italy

Introduction

In the past 10 to 20 years there has been considerable concern in the medical literature on the use of proper statistical design and of proper statistical methods in medical research. Periodically articles have been published both assessing which techniques are used and how frequently they are wrongly used^1-7. All of them are overtly pessimistic and there is no sign of an increase in quality over the years. Further, articles have been also published during the same period with detailed statistical guidelines for writing medical papers^8-10. However the (proper) use of quantitative methods for biomedical research is mandatory in order to generalize through statistical inference, the results obtained in the (random) study sample of the general population. Moreover statistical tools nowadays largely available on personal computers, can lead to misleading conclusions when applied inappropriately or when the design itself is not appropriate.

The arrhythmologic literature being particularly rich of original articles, which can have a large impact on the way of treating arrhythmic patients, a study has been performed to determine: 1) which type of design has been used by the investigators to demonstrate their endpoint; 2) which statistical methods have been used to report findings; 3) the subset of statistical methods a researcher should be familiar with to interpret a majority of such reports; 4) the most common statistical errors that can be observed in these reports.