Osmind (YC S20) – software for better mental health therapies

Hi HN! We are Lucia and Jimmy, co-founders at Osmind (https://www.osmind.org/). We build software that helps mental health doctors treat their patients in evidence-based, data-driven ways. Along the way, we develop better methods of diagnosing and treating people in a personalized manner.

Jimmy and I met at Stanford in a healthcare IT class at Stanford last year where I wrapped up my MBA and Jimmy is on leave from medical school. We’ve dedicated our personal and professional efforts to healthcare - I led operations and business at AI-driven neuroscience biotech Verge Genomics (S15) and Jimmy founded multiple healthcare nonprofits across digital health, care delivery, and research. Like many, we’ve seen too many of our loved ones fail to find the right mental health treatment for them. We realized we want to build something to help -- and we’re optimistic that neuroscience and psychiatry are on the verge of a revolution. We’ve built Osmind to maximize access to innovative mental health treatments for those who need it the most.

Over 20M Americans who suffer from treatment-resistant mental health conditions, which means they’ve tried and failed two or more conventional treatments. Oftentimes, finding the right mental health treatment means years of trial & error and suffering. On top of that, patients with treatment-resistant mental health conditions annually cost $900B+ in direct medical spend, twice as much as people with less severe versions of the same conditions. Researchers and doctors just haven’t been able to find mental health therapies that work well (conventional antidepressants have an estimated ~30% effectiveness rate). This is because pharma lacks sufficient understanding of mental health pathophysiology while clinicians lack the right data on what treatments work best for which people.

We approach this problem in two ways: 1) we build software for doctors and 2) generate insights for better development of therapies, treatment algorithms, and diagnostics.

First, we sell an electronic health record (EHR) to doctors working with treatment-resistant mental health patients. Our EHR enables doctors to measure how patients are doing in between appointments via an integrated patient mobile app to drive personalized, improved clinical decision-making. For example, we can use data science to automatically detect symptom exacerbation or improvement (from patient-reported outcomes or functional metrics such as activity levels) and get them in for treatments at the right time. This is a rarity for EHRs, especially in treatment-resistant mental health, which is known to lack evidence-based practices and consists of a difficult-to-treat patient population. Our EHR also automates administrative tasks such as collecting intake forms and getting reimbursement from insurance companies. Our ultimate goal is to make recommendations to the doctor on what treatments work best for people based on objective criteria such as their past medical history, demographics, and more. That way, doctors can deliver the best possible care, and patients can get better. We launched the software in June and are serving over 125 clinics nationwide covering over 20,000 patients receiving FDA-approved psychedelic medicine, neuromodulation, and general psychiatry treatment.

Second, we can extract insights from the software to find better and more precise ways of treating individuals. Our software above aggregates clinical, patient-reported, digital, and biological information, which has never been done at scale in mental health. For example, establishing more objective predictors of depression and correlating them with treatment impact can help us diagnose people more precisely and determine what makes one type of treatment better than the other. We can use this information to better design clinical trials that actually succeed, potentially saving billions of dollars of sunk costs to develop therapies that work. New innovation in mental health is on the horizon with the development of efficacious treatments like ketamine, FDA-approved psychedelic medicines, neuromodulation, digital therapeutics, and more. Long term, the holy grail would be to obtain a biological understanding of mental health and find diagnostics and therapies that can end suffering brought on by mental health issues.

We care deeply about patient and clinician privacy as well. Our platform is HIPAA-compliant and protected by end-to-end encryption. We work with independent third parties to verify our compliance and security. Patients own their health data and have the right to all of it. Any analysis we do is always on anonymized and aggregated information and never traceable back to an individual or clinic. We openly state that our mission to advance new treatments to the patients and doctors we work with and have found that the whole field is motivated to help - everyone realizes it’s an all-hands-on-deck movement.

Please drop us a line if you’re at all interested in learning more or have any feedback. We’re also hiring software engineers and would be grateful to be in touch with anyone in this community! You can reach us at [email protected]



Get Top 5 Posts of the Week



best of all time best of today best of yesterday best of this week best of this month best of last month best of this year best of 2022 best of 2021 yc w23 yc s22 yc w22 yc s21 yc w21 yc s20 yc w20 yc s19 yc w19 yc s18 yc w18 yc all-time 3d algorithms animation android [ai] artificial-intelligence api augmented-reality big data bitcoin blockchain book bootstrap bot css c chart chess chrome extension cli command line compiler crypto covid-19 cryptography data deep learning elexir ether excel framework game git go html ios iphone java js javascript jobs kubernetes learn linux lisp mac machine-learning most successful neural net nft node optimisation parser performance privacy python raspberry pi react retro review my ruby rust saas scraper security sql tensor flow terminal travel virtual reality visualisation vue windows web3 young talents


andrey azimov by Andrey Azimov