K Achieved up to 85 Percent Match with Ultimate Diagnosis by a Licensed Physician
NEW YORK–(BUSINESS WIRE)–K Health, a digital health company that offers free, personalized healthcare, and the Kahn-Sagol-Maccabi Research and Innovation Institute, led by Professor Varda Shalev at Maccabi Healthcare Services, Israel’s second largest HMO with 2.4 million patients, announced the publication of a research article in Medicine. The article is titled “A patient like me – an algorithm-based program to inform patients on the likely conditions people with symptoms like theirs have.” K Health is now the only health company that offers a symptom checker mobile app that is the subject of a published peer-reviewed study supporting its unique scientific and medical approach. K is also the only company that has built a consumer tool that applies machine learning to the Maccabi Healthcare Services’ database of hundreds of millions of unstructured, anonymized medical data points to create a conversation with users that mirrors a conversation with a human doctor.
The study was approved by the IRB ethical committee in Tel Aviv. Its objective was to develop and evaluate an algorithm-based tool that provides the public with reliable, data-driven health information. To provide better answers for people searching for medical information, the authors applied machine learning and natural language processing to 670 million anonymized notes from patient visits with Maccabi physicians accrued since 1993. They then developed classification algorithms to determine correlations between tens of thousands of symptoms and illnesses, based on patterns of symptoms and personal characteristics.
The authors then created a text-based consumer interface to mimic a conversation that prompts the user to provide additional symptom information, understands the user’s reported symptoms, rules out serious conditions and obtains a better understanding of the user’s health. By creating an automated follow-up that asks about how the user sought treatment and a physician’s diagnosis, the software completes a closed, self-learning loop that learns over time and automatically updates its model with each new conversation.
When compared to the ultimate diagnosis by a licensed physician, the results provided by the software were accurate in 82-85 percent of the use cases included in the study.
“This is the first time that AI is being used, together with a dataset of millions of anonymized records, at a large scale in primary care,” said Allon Bloch, co-founder and CEO of K Health and author of the study. “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.”
“While health data are abundant and present enormous opportunity for us to learn from other people, these data are stored on computers and aren’t being used in constructive ways,” said Professor Varda Shalev, author of the study and Director at the KSM Research and Innovation Institute at Maccabi Healthcare Services. “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.”
About K Health
K Health is a digital health company that offers free personalized healthcare. K has created the first and only AI-driven primary care solution that allows users to see how doctors diagnose and treat similar people with similar symptoms for free by chatting with a cutting-edge AI that has been trained on a uniquely large dataset from billions of anonymized clinical data points. K is trained to ask smart questions about symptoms and to account for medical history, age, gender, and other biomarkers as it investigates each user’s health. Users can then chat with a real, licensed physician for fast, personalized care that costs dramatically less than care options currently available to most consumers. The product is aggregating the wisdom of the entire medical community within one intelligent machine that gets smarter over time. K has millions of users and is frequently the #1 most downloaded app in the App Store’s medical category. K is available in all 50 states, and K Primary Care is available in 38 states, covering 291 million people. The company has raised $50M+ and is headquartered in New York City.
About Maccabi Healthcare Services
Maccabi Healthcare Services, one of the largest health funds in the world, has 2.5 million patients, which represents 25% of the Israeli market share with a nationwide representative distribution. Maccabi has long been recognized, both in Israel and abroad, as a unique and innovative health care system which leads the way in cutting edge medical technology, comprehensive and integrated computerized information systems, cost–effective management, and sophisticated monitoring and evaluation tools. Since 1993, electronic medical records (EMRs) have been implemented in Maccabi, documenting all types of medical information in a central database containing complete data on each patient. This database provides comprehensive, systematic, quality data, of a stable population of patients across their lifetime. The Kahn-Sagol-Maccabi Research and Innovation Institute established and led by Prof. Varda Shalev partners with leading tech and medical entities around the globe in creating the most novel apps, services and scientific publications. We are able to create these remarkable breakthroughs utilizing the unique partnership with Maccabi: its professional abilities and wealth of data.
Moxie Communications Group for K Health