Medicine Peer-Reviewed Journal: K’s Results Match With Physician Diagnosis 85% of the Time

By K Health
Medically reviewed checkmarkMedically reviewed
November 8, 2019

Medicine recently published an article titled “A patient like me – an algorithm-based program to inform patients on the likely conditions people with symptoms like theirs have.

We’re excited to share that the study found that K’s results matched with patients’ ultimate diagnosis by a licensed physician more than 85% of the time!

K is now the first and only intelligent symptom checker tool to be assessed by a peer-reviewed study, and the high level of accuracy the study found reinforces the value of K’s unique approach.

By applying natural language processing and machine learning to real world medical cases, instead of trying to write enough rules to cover a subject as complex as human health effectively, we’ve built the most intelligent symptom checker in the world.

“This study was the first of its kind to explore how we can use anonymized medical data to create a healthcare system that helps us learn from people like us, and create new digital access points to primary care,” said Professor Varda Shalev, author of the study and Director at the Institute for Health Research and Innovation at Maccabi Healthcare Services.

“This research showed the enormous opportunity to create a new category in healthcare with an intelligent machine that grows smarter over time and can transform access and cost of healthcare in the U.S. and abroad,” said Allon Bloch, co-founder and CEO of K Health and author of the study.


K Health articles are all written and reviewed by MDs, PhDs, NPs, or PharmDs and are for informational purposes only. This information does not constitute and should not be relied on for professional medical advice. Always talk to your doctor about the risks and benefits of any treatment.

K Health

Reliable, relatable medical information written by hundreds of board-certified clinicians, updated regularly to ensure accuracy.