I follow regularly the field of sports surgery and new studies published in that subspecialty. It seems the true research gems are only seen in sports surgery… I introduce the recent top 2 studies in this and subsequent post.
I have research interest in ACL reconstruction studies and this study published in the American Journal of Sports Surgery naturally caught my attention: A Randomized Controlled Trial of Bone–Patellar Tendon–Bone Anterior Cruciate Ligament Reconstruction With and Without Lateral Extra-articular Tenodesis: 19-Year Clinical and Radiological Follow-up.
My initial impression was that ok, some lost to follow-up, but otherwise decent sample size considering the long follow-up period. But the best part was hiding in the Methods section. Authors write:
Statistical analysis was performed with EasyMedStat (www.easymedstat.com).
EasyMedStat? If you proceed to that website, you will find the most disturbing content:
Generate biostatistics safely and without statistical knowledge
From www.easymedstat.com
Generate statistics without statistical knowledge? Do we really need to discuss about issues in research reproducibility and misuse of statistical methods when this is going on? Using the same logic as this website, I could set up a website with videos showing how to perform a hip surgery: “Operate patients without anatomical knowledge”. Sure someone might argue that it´s totally different thing. But we need to also ask why we do clinical research? We do it because we want to deliver the best care for our patients. I´d imagine patients were not happy if they know that studies were carried without critical knowledge considering crucial areas in those studies.
I naturally tweeted about this study and tagged Darryn Dahly who has written excellent piece about Statistical Reform.
I continued on this topic little later:
If not for ourselves, for the sake of our patients we need a statistical reform!