Hims & Hers
AI-driven personalized treatment routing on intake data (MedMatch)
In the first quarter of 2025, Hims & Hers counted more than 1.4 million subscribers on personalized solutions out of nearly 2.4 million, its MedMatch engine routing each patient to a fitting treatment, for revenue of 586 million dollars, up 111%.
Key points
- AI-driven personalized treatment routing on intake data, with clinical validation.
- MedMatch, a proprietary in-house machine learning engine, launched in 2023.
- More than 1.4 million subscribers on personalized solutions out of 2.4 million, Q1 2025 revenue of $586M (+111%).
- Evidence level A, living status confirmed.
Objective
Convert a visitor who fills out a questionnaire into a subscriber of a fitting treatment, by pushing the right formulation and the right care pathway rather than a generic catalog, to increase conversion and anchor the subscription over time.
The deployment
MedMatch, launched in 2023, analyzes intake data to route each patient to the care pathway and formulation that fit them. Personalization has become the foundation of the offering: in the first quarter of 2025, out of nearly 2.4 million subscribers, more than 1.4 million used personalized solutions. Management describes a strategic focus on deepening personalization and tied it to the arrival of a chief technology officer tasked with strengthening AI-driven diagnosis and automation. Q1 2025 revenue reached 586 million dollars, up 111% year over year.
Results Proof A
The personalized subscriber volumes and revenue are published in Hims & Hers's Q1 2025 financial results (official press release, listed company), a primary source consistent with press coverage documenting MedMatch. Results figures = level A.
How it works
Documented architectureThe stack in detail
- outil MedMatch Hims & Hers's proprietary machine learning engine, launched in 2023, which analyzes intake data to route each patient to the fitting care pathway and formulation; the exact techniques are not published
- plateforme Plateforme Hims & Hers (web et app) Carries the intake questionnaire, the subscription, and the delivery of personalized treatments
- outil Workflow de validation clinique In-house circuit through which a network provider confirms or adjusts each recommendation before prescription
How it runs, concretely
For ops teams-
1Intake collection Customer
The patient fills out a health questionnaire and their goals on the platform.
-
2Analysis and routing AI
MedMatch analyzes the data to propose the fitting care pathway and formulation.
-
3Clinical validation Clinical team
A network provider confirms or adjusts the recommendation before prescription.
-
4Subscription and delivery Platform
The personalized treatment is placed on subscription and shipped.
-
5Follow-up and adjustment Data and clinical team
Renewals, effects, and patient feedback feed the adjustment of the recommendations.
The intake questionnaire answers and the treatment history. Without structured intake data and a clinical follow-up loop, the system falls back on a standard offering and loses its conversion value.
How your customers perceive this type of use
Sourced studiesLe paradoxe est documente des deux cotes : 71% des consommateurs attendent des interactions personnalisees et 76% sont frustres quand elles manquent (McKinsey, 2021), mais 75% declarent ne pas acheter aupres d'organisations auxquelles ils ne confient pas leurs donnees (Cisco, 2024). La « creepy line » est localisee : messages recus quelques secondes apres une recherche et suivi de localisation sont les pratiques qui mettent le plus mal a l'aise (Periscope by McKinsey, 2019).
Acceptance conditions
- La confiance dans le traitement des donnees precede l'achat : 75% ne achetent pas sans elle (Cisco 2024)
- Un cadre legal protecteur rassure : 59% des consommateurs disent que des lois fortes sur la vie privee les rendent plus a l'aise pour partager des informations dans des applications IA (Cisco 2024)
- La personnalisation elle-meme est attendue quand elle est consentie : environ la moitie des consommateurs (US 55%, UK 52%) disent s'inscrire souvent ou parfois a des services personnalises (Periscope by McKinsey 2019)
Red lines
- Le message declenche quelques secondes apres une recherche ou un achat : deuxieme ou troisieme cause de malaise selon les pays (Periscope by McKinsey 2019)
- Le suivi de localisation percu comme de la surveillance : 40% de malaise en Allemagne et au Royaume-Uni (Periscope by McKinsey 2019)
- Le mesusage des donnees personnelles par l'IA, devenu la premiere inquietude des consommateurs, a 53% et en hausse (Qualtrics 2025)
Sources: McKinsey & Company 2021 · Periscope by McKinsey 2019 · Cisco 2024 · Qualtrics 2025
How to replicate
Inference, not sourcedData prerequisites
- structured intake questionnaire
- first-party treatment history
- outcomes follow-up loop
Org prerequisites
- network of providers to validate the recommendations
- telehealth regulatory framework
- internal data science team
Possible stack
- recommendation or scoring engine
- cloud (AWS, GCP, or Azure)
- subscription platform
- clinical review workflow
The plan, step by step
- Step 1Structure the intake questionnaire with the clinical team and define the reference set of care pathways and formulations; frame compliance (health data, telehealth, GDPR Article 9 in the EU).Deliverable: Structured intake and pathway reference validated clinically and legally
- Step 2Build the first version of the routing engine (rules then scoring) and the workflow for provider validation before any prescription.Deliverable: Recommendation engine connected to the clinical review circuit
- Step 3Launch a pilot on one vertical with a panel of providers, comparing conversion and relevance against the standard pathway.Deliverable: Pilot in production with a provider adjustment rate on the recommendations
- Step 4Connect the subscription and the follow-up loop: renewals, effects, and patient feedback feed the engine's adjustment.Deliverable: Working follow-up loop and measured retention
- Step 5Extend to other verticals and refine the engine on the accumulated history.Deliverable: Multi-vertical engine with a conversion / retention review
First step: Structure an intake questionnaire usable by a recommendation engine and connect it to a clinical validation workflow.
The same pattern, proven in other industries
Taobao
Real-time product recommendation with deep learning, served across hundreds of scenarios in the app
Amazon
Item-to-item collaborative filtering product recommendation engine, served across every touchpoint
ASOS
catalog-scale deep learning product recommendation, plus a conversational style assistant
Sources
- S1 Hims & Hers Health, Inc. Reports First Quarter 2025 Financial Results Primary archive pending
- S2 Hims & Hers Health, Inc. Reports First Quarter 2025 Financial Results (StockTitan) Secondary archive pending
- S3 Hims & Hers Leads the Charge in AI-Powered Personalized Healthcare Secondary archive pending
An error, newer info, a source?
This page lives on its accuracy. If a figure has moved, if the deployment has changed, or if you have a higher-quality source, tell us. Every sourced correction is verified before publication.