Current treatment guidelines
are outdated and costly

Our machine learning model gets patients suffering from depression the right medication from the start.

In the Press:
Verywell Health
Science Based,Peer-Reviewed Research

Depression is widespread and its cost is often overlooked or misunderstood, adding thousands in per capita health costs per year.

boosts remission rates from 33% to 51%, resulting in annual savings of over $700 per patient.

Made possible thanks to research by George Mason University.

Step 1

Refer

Refer your patients to our service. This can be as simple as adding a link or QR code to your intake packet. On their own time, they'll answer questions about their medical history.

Step 2

Data Analysis

We run our artificial intelligence model, powered by data from millions of individuals, to identify the antidepressants that are most likely to alleviate your patient's depression.

Step 3

Share

We provide you with a targeted list of the antidepressants most likely to result in symptom improvement for your patient.

Questions?

Email Us
OR
Call (415) 275-0164

Advisory Board:

Farrokh Alemi, PhD

Professor of Health Informatics, George Mason University
Formerly at Veteran's Health Administration, Georgetown University

Farrokh's specialty is in the analysis of large data available in electronic health records. He has produced over 120 peer-reviewed publications and three books, contributing to the fields of predictive medicine, precision medicine, analysis of cost, comparative effectiveness of medications, and more. He is a pioneer in the online care of patients and has provided Congressional testimony on the role of the internet in health delivery. He has started three venture capital backed businesses, and his work forms the basis of Teahorse's technology.