2022 AOSSM Annual Meeting Recordings with CME-How to Review a Large Database Study

Video Transcription

Video Summary

In this video, the speaker discusses large database studies and their strengths and limitations. They define a large database study as a study of a large collection of data that encompasses records at a state, multi-state, or national level, reporting on more than one procedure or subspecialty. The speaker highlights the strengths of large database studies, such as the quantity of data and the ability to report on rare patient groups or complications. However, they also acknowledge the limitations, such as the quality of the data and the lack of detailed information specific to a diagnosis or procedure. The speaker discusses statistical issues, including confidence intervals of rates and simultaneous testing and multiple hypotheses. They also emphasize the importance of accurately classifying and counting data, as well as evaluating the numerators and denominators chosen by authors. The role of chance in prospective and retrospective analyses is also discussed. Lastly, the speaker suggests using adjusted p-values, such as through Bonferroni corrections, and considering clinically significant differences when interpreting the findings of large database studies.

Asset Caption

James L. Carey, MD, MPH

Keywords

large database studies

strengths and limitations

quantity of data

rare patient groups

statistical issues

data classification