Free to read. Sign up to save your progress and take knowledge-check quizzes.

Sign up free
5 min read·Updated July 2, 2026

Glass Health

Glass Health logoBy Glass Health

Glass Health is a clinician-facing decision support platform that generates ranked differential diagnoses and evidence-based care plans, plus ambient documentation — used by more than 100,000 US clinicians and trainees, and a peer to OpenEvidence.

Listen to this lesson

Free preview · first 0:30
0:00 / 0:30

Audio & video lessons are paid features

Plus unlocks audio streaming. Pro adds downloadable audio, video, certificates, and more.

Plus adds:
  • Audio streaming
  • Downloadable PDFs
  • All AI Playbooks
  • Personalized content
Pro also adds:
  • Certificates of completion
  • Audio MP3 downloads
  • Video lessonssoon
  • & More…soon

Watch this lesson

AI Pro Playbook video — coming soon

Learning Objectives

  • Understand what clinical decision support does for physicians
  • Understand Glass Health's differential-diagnosis workflow
  • Evaluate decision support as reasoning aid, with the clinician accountable

What Is Glass Health?

Glass Health is a clinical decision support platform built for clinicians, not patients. A physician enters a clinical picture — the presenting problem and relevant findings — and Glass generates a ranked differential diagnosis (the ordered list of what could be going on) along with an evidence-based diagnostic and treatment plan, laying out the reasoning so the clinician can evaluate it. It has also added ambient documentation. A Y Combinator company, Glass reported use by more than 100,000 US residents, trainees, and attending physicians, and in 2026 overhauled its platform, pricing, and enterprise offering.

Glass sits alongside catalogued OpenEvidence as a physician-facing decision-support tool, distinguished by its differential-diagnosis workflow — helping a clinician think through possibilities and next steps rather than only retrieving evidence. The essential framing is that Glass supports clinical reasoning: it surfaces diagnoses to consider and evidence to weigh, while the licensed clinician makes the decision and bears responsibility. That framing matters because the failure mode of medical language models is confident, plausible-sounding error, and over-reliance is a real risk. Used as intended — a knowledgeable assistant that broadens a clinician's thinking and speeds access to evidence — it can improve both learning (hence its popularity with trainees) and day-to-day practice.

💡Key Concept

Differential diagnosis: The ranked list of conditions that could explain a patient's presentation. Glass helps generate and reason through it, plus the evidence-based plan — a thinking aid for the clinician, who decides.

⚠️Warning

Reasoning aid, not the decision-maker. Medical language models can produce confident but wrong output. Glass supports the clinician's reasoning; the licensed clinician evaluates the suggestions, makes the call, and is accountable. Over-reliance is the risk to manage.

Tip

Visit Glass Health: glass.health — used by clinicians and trainees, with an enterprise offering.

Pricing

Glass offers individual access alongside enterprise plans for health systems and training programs; core access has free and paid tiers, with organization pricing on request.

IndividualFree and paid tiers
  • Differential-diagnosis generation
  • Evidence-based plans
  • Clinician workflow
EnterpriseCustom quote
  • Health-system and program deployment
  • Ambient documentation
  • Integration and controls

Core Features

Ranked Differential Diagnosis

Generates an ordered list of possible diagnoses for a clinical presentation, with reasoning the clinician can evaluate.

Evidence-Based Care Plans

Produces diagnostic and treatment plans grounded in evidence, giving the clinician a structured starting point.

Ambient Documentation

Adds documentation support so decision-support and note-taking live in one workflow.

Trainee-Friendly

Widely used by residents and trainees as a learning and reasoning aid, reflected in its 100,000-plus user base.

Strengths

  • Differential-diagnosis workflow — supports reasoning, not just retrieval
  • Evidence-based plans — structured, sourced starting points
  • Large clinician user base — 100,000-plus, including many trainees
  • Documentation included — decision support and notes together
  • Enterprise-ready — health-system and program deployment

Limitations and Considerations

  • Confident-error risk — language models can be plausibly wrong
  • Clinician remains accountable — a reasoning aid, not the decision-maker
  • Over-reliance risk — especially for trainees, judgment must be preserved
  • Scope of evidence — outputs are as good as their sourcing
  • Verification needed — suggestions should be checked against the patient

Best Use Cases

Use CaseWhy Glass Health FitsCaveat
Working through a differentialRanked possibilities with reasoningClinician evaluates and decides
Evidence-based planningStructured, sourced care plansVerify against the patient
Training and educationPopular reasoning aid for residentsGuard against over-reliance
Clinician decision supportAlternative or complement to OpenEvidenceAccountability stays with the clinician

Key Takeaways

  • Glass Health is a clinician-facing decision support tool that generates ranked differential diagnoses and evidence-based care plans, plus ambient documentation
  • It is used by more than 100,000 US clinicians and trainees and sits alongside OpenEvidence as physician-facing decision support
  • Its distinguishing feature is the differential-diagnosis workflow — supporting reasoning, not just retrieving evidence
  • It supports clinical reasoning while the licensed clinician makes the decision and remains accountable
  • The key risks are confident model error and over-reliance, so suggestions must be verified against the patient

Save your progress & take the quiz

Sign up free to bookmark lessons, track which modules you've completed, and lock in what you learned with a quick knowledge-check quiz at the end of each lesson.

🧭Recommended for you