Statistics For Dummies: Primary Care Doctors’ Inability to Understand Statistical Concepts …

An article and editorial have appeared in the Annals of Internal Medicine demonstrating that primary care physicians do not understand simple statistical data presented to them regarding screening tests for cancer. The consequences, as outlined in an editorial written by a former chairperson of the much maligned Institute of Medicine, is that primary care doctors are over-using cancer screening tests because they do not understand the statistical ramifications and conclusions presented in the study. The editorialist recommends improving statistical courses at the medical school level and improving the editorial comments in journals when these studies appear.

As a primary care physician, out of medical school for 36 years, let me make a suggestion.  Keep It Simple Stupid.   Medical school was a four year program.  The statistics course was a brief three week interlude in the midst of a tsunami of new educational material presented in a new language (the language of “medicalese”) presented en masse in between students being used as cheap labor at all hours of the day to fill in drawing bloods, starting intravenous lines and running errands for the equally overworked interns and residents who were actually being paid to perform these tasks.

While internship and residency included a regular journal club, there was little attention paid to analyzing a paper critically from a statistical mathematical viewpoint.  I suggest applying the KISS principle to analyzing medical research papers. Make the language and definitions clear cut and understandable for the non math majors and non researchers.  We have eliminated the use of Latin, medical abbreviations and other time honored traditions of the profession in the name of clarity and safety.  It’s time to do the same with statistical analysis of research papers. Let authors and reviewers say what they mean at an understandable level. Practicing clinicians do not use this vocabulary regularly enough to master it.

It’s time for creating a “Khan Kollege” You-Tube video on statistical analysis and medical paper review that clinicians can refer to routinely to buff up their understanding of medical research papers.  If the American College of Physicians or American Academy of Family Practitioners already have such programs on their websites I apologize for not knowing where to find it.

Each year the economic advisors who freely give advice to us PCP providers have asked me to add three patients per day per year to my schedule to economically be able to stay in the same place.  Amidst that high volume and need to stay current and need to have some balance in my life I admit my statistical analysis skills have grown rusty.  I believe many of my colleagues have suffered the same fate. When the Medical Knowledge Self Assessment syllabus arrives every other year, the statistics booklet is probably one of the last we look at because not only does it involve re-learning material but you must first re–learn a vocabulary you do not use day to day or week to week.

I will make my effort to re-learn statistics to better understand the literature. It is my professional responsibility to do so. I ask my colleagues in academia to do a better job, however, of explaining and teaching the concepts so the data and the logical conclusions are understandable.