Jonathan H Chen Profile picture
Physician Data Scientist - Assistant Professor - Center for Biomedical Informatics Research + Division of Hospital Medicine - Stanford Department of Medicine
21 Oct 18
Closing the loop on #Diagnostics #Tweetorial with example #AppleWatch #AFib #Screening. From a company website: "Atrial fibrillation is a silent killer. The heart arrhythmia causes more life-threatening strokes than any other chronic condition, and will affect 1 in 4 of us."
"But the sad fact is that atrial fibrillation often goes unnoticed: It is estimated that 40% of those who experience the heart condition are completely unaware of it."
Using #AppleWatch technology and #DeepLearning #AI #ML, a device algorithm can reportedly detect atrial fibrillation with high accuracy (c-statistic 93%).
Read 44 tweets
5 Oct 18
#Tweetorial on #Diagnostics and #Screening interpretation.
An otherwise healthy 40 year old woman comes to you after reading on the internet about a terrible disease that one in a thousand women get, and a highly accurate test that can save her life.
The test is over 99% accurate in people with the disease. For those without disease, the test is only wrong 5% of the time.

You order this test and it comes back positive. The woman anxiously asks you, do I have the disease? What is the chance this woman has the disease?
Assuming they weren't immediately fooled by the "test is only wrong 5 % of the time," most I've asked correctly recognize the stats provided are Sensitivity = 99% and Specificity = 95%, and that the objective is to determine the Positive Predictive Value.
Read 21 tweets