How does K Health produce results based on symptoms?
We believe relevant health information should be available to all. So we built a novel digital health solution that checks your symptoms against anonymized data from hundreds of millions of patients and doctor visits. We do this using Artificial Intelligence (AI). The rich data-driven approach is described in detail in peer-reviewed medical publications.[1,2] By processing this data intelligently, our free symptom checker shows you how doctors diagnosed and treated people like you with similar symptoms.
Please note that the symptom checker cannot provide a definitive diagnosis or treatment recommendation. It can empower you with free data-driven information personalized to you, but it does not replace consulting with a physician.
What type of data powers K Health’s technology?
K Health’s technology and symptom checker is based on anonymized, real world data from over 400 million patient visits in the US and in Israel. Data used in the development of the app includes patient visits recorded in Maccabi Health Services (MHS) – the second largest Health Maintenance Organization in Israel.
All medical information that powers the K Health symptom checker is reviewed by U.S. board-certified physicians, including specialists in family medicine, pediatrics, emergency medicine, cardiology, and infectious diseases, and in accordance with accepted clinical guidelines.
K Health’s technology has undergone extensive testing by both medical and machine learning experts, as featured in scientific medical publications, and is reviewed on an ongoing basis to ensure the information provided is accurate.
For example, medical information accuracy is reviewed to assure it is in agreement with US regulatory and medical guidelines, including those issued by the CDC and by leading medical associations, such as the American Academy of Pediatrics, American Association of Family Physicians, Infectious Disease Society of America, and the American Heart Association.
The algorithms and information in the app are continuously monitored, validated, and audited by a team of medical, data, and machine learning experts. The results of validation studies conducted with Integrity Family Care in the US, and with MHS in Israel, have also been published in the peer-reviewed medical journal “Medicine.”
K Health is a HIPAA and GDPR compliant health service and employs the “safe harbor method” for de-identification of data. Encrypted transportation is used for all data when it is transferred from the app to K Health servers, and the data is encrypted while it is stored in the database servers. Accounts and all personally identifiable information uploaded by users can be deleted upon request. K Health also regularly monitors systems for possible vulnerabilities and attacks and regularly seeks new ways and third party services for further enhancing the security of services and protection of users’ privacy.
- Koren G, Souroujon D, Shaul R, et al. “A patient like me” – An algorithm-based program to inform patients on the likely conditions people with symptoms like theirs have. Medicine (Baltimore). 2019.
- Perlman A, Vodonos Zilberg A, Bak P, et al. Digital and Remote Care among 71,619 Individuals Seeking COVID-19 Health Information and Services: A Retrospective Cohort Study. J Med Internet Res. Published online September 19, 2020.