Can Machine Learning Make Grand Rounds “Grand” Again?

Ruth Smith
April 23, 2019

Grand rounds are not so grand, but can machine learning help make them grand again? Most physicians learn the art of diagnosis in medical school but the art of diagnosing a disease is currently not a straightforward process.  With all the reports about machine learning replacing physicians, it is unlikely physicians will be replaced but can technology help doctors be better?  The concept of grand rounds can be used within machine learning to recognize the very best diagnoses and treatment patterns that can be applied to new patients.

No one knows how grand rounds started but for the medical community they have been an important teaching tool and ritual for physicians. Grand rounds have helped doctors and other healthcare professionals keep up to date in important evolving areas which may be outside their core practice.  In the early days, the patient was traditionally present for the round and would answer questions, explaining medical history and symptoms. Grand rounds have evolved with most sessions now rarely having a patient present and being more like lectures with experienced physicians or research scientist making presentations.

Some hospitals have their own specialized grand rounds. Attending grand rounds is an important supplement to medical school and on-the-job resident training. Grand rounds differs from rounds which is the daily visit by the attending physician and team to the physician’s patients. Rounding with an attending physician is part of medical training and education, but its primary focus is immediate care for the patients on the ward. Grand rounds tends to present the bigger picture, and allows for shared knowledge and expertise within a bigger group setting.

In recent years grand rounds have gone out of vogue, with physicians preferring to attend grand rounds that are more specific to their narrower field or hear presentations at national or international meetings.  With the acceptance of mobile devices and younger physicians coming out of medical school growing up with technology, the instant nature of information has lessened the appeal to hear from experienced physicians as in years past.  Medical educators seek ways to improve engagement as Socratic dialogue gives way to Power Point and Smart Phones.

Could machine learning be the next catalyst to improve grand rounds? Healthcare utilizes years of data that contains treatment patterns and diagnoses, which machines can evaluate in seconds.  In previous blogs I shared our work in detecting Omentum Cancer by reading through biomarkers to find the most meaningful ones to use in diagnosing as well as radiology scans to detect other conditions. Everyday diagnosing of common conditions such as flu, pneumonia, UTI infections as well as more complicated ones like congestive heart failure have patterns associated with them. Computers and machine learning algorithms are getting more and more adept at recognizing patterns – which is what much of diagnostics is about.   Imagine taking the very best physician knowledge and sharing that diagnostic capability among many clinicians. This has been our approach at Intermedix to our Condition Awareness Platform and we like to say we have learned from the best – putting the “grand’ back in grand rounds.    

Ruth Smith

Looking for your next meaningful IT career opportunity?
We’ve got you covered too. Click here to set up a consult.