MedAI Verdict
Patient triage

AI Patient Triage

EH

Ellipsis Health

by Ellipsis Health, Inc.  ·  US

Last verified

Sage, an autonomous voice AI care manager that makes outreach and assessment calls for health plans and health systems.

At a glance

Pricing
No public price. Pricing unit (per call, minute or member) not stated.
HIPAA
Attested
SOC 2
Type II
EHRs
—
Founded
—
HQ
US
On this page

Independent score  ·  By our public rubric

29/100Niche fit

Not rated: too little independent evidence yet.

How it’s computed →
  • Regulatory & Compliance
    13/28.6

    HIPAA + (SOC2 or BAA) attested

  • Clinical Integration
    0/26

    No EHR integrations listed

  • Evidence Strength
    9.8/20

    2 peer-reviewed papers

  • Vendor & Market
    3/18

    Seed-stage or unfunded

  • Sentiment & Transparency
    2.5/5

    Pricing on request, no public amounts

▸ Show all 11 dimensions

Regulatory & Compliance

  • FDA clearance0/16

    No FDA clearance listed

  • HIPAA / SOC2 / BAA13/13

    HIPAA + (SOC2 or BAA) attested

Clinical Integration

  • EHR integrations (count)0/14

    No EHR integrations listed

  • Top-3 EHR coverage (Epic / Oracle / Athena)0/8

    None of the top-3 EHRs covered

  • Bidirectional write-back0/4

    No bidirectional write-back documented

Evidence Strength

  • Peer-reviewed papers10/14

    2 peer-reviewed papers

  • RCT / meta-analysis / systematic review0/6

    No RCT, meta-analysis, or systematic review

Vendor & Market

  • Funding & adoption signal3/12

    Seed-stage or unfunded

  • Years in market0/6

    Founded year not recorded

Sentiment & Transparency

  • Pricing transparency3/5

    Pricing on request, no public amounts

Scored November 2, 2026 · Public scoring method v1.2.0

Sage, an autonomous voice AI care manager that makes outreach and assessment calls for health plans and health systems.

No public price. Pricing unit (per call, minute or member) not stated. HIPAA + SOC 2 Type II attested.

Evidence record

FDA decisions

No FDA decision cited in our research as of November 2, 2026.

Peer-reviewed

2 studies on PubMed: 2 other, published 2022 to 2026. Read the literature summary

Verification
  • Score computed November 2, 2026, method 1.2.0
  • Review written November 2, 2026
Cite this record

MedAI Verdict, Ellipsis Health record, https://medaiverdict.com/tools/ellipsis-health, version November 2, 2026

Bottom line

Ellipsis Health sells Sage, a voice agent that makes outreach and assessment calls for health plans and health systems, and the vendor also lists inbound calls. The work is enrollment, benefits checks, health risk assessments, discharge check-ins and satisfaction surveys. Sage is a care-management caller, so the buyer is a plan or system with a large assessment workload, and a clinic wanting a symptom line is outside what the product pages describe. The peer-reviewed papers under the company name study an older speech-analysis app.

What does a Sage call cover?

The vendor describes Sage as making "fully autonomous virtual care management calls," around the clock. The product and FAQ pages list enrollment, benefits and eligibility checks, health risk assessments, care and discharge assessments, HCAHPS and satisfaction surveys, adherence, transitions of care and "Friday tuck-ins."

Oversight is described as a "human-in-the-loop approach for complex cases." The vendor says a team of physicians, nurses and care managers validates every Sage update before deployment. The pages describe no crisis or suicidality protocol, and escalation to nurses does not appear on the product page. Sage is "multilingual," with no language named.

Which papers carry the Ellipsis name?

Four papers study the company's speech technology, all with Ellipsis employees among the authors and conflict-of-interest statements.

  • A 2022 Frontiers in Psychology study (PMID 35478769) tested the Ellipsis Health App against PHQ-8 and GAD-7 in a senior population and reported an AUC of 0.82 with 61% protocol completion.
  • A 2022 Cancers study (PMID 35205663) covers a speech-based distress screening app for adolescents and young adults.
  • A 2025 JMIR AI study (PMID 40605836) is a retrospective analysis of speech and language models for depression severity in a payor-provider system, using Ellipsis algorithms.
  • A 2026 JMIR Research Protocols paper (PMID 41678797) covers feasibility of the eCARE app for depression and anxiety monitoring in family caregivers of cancer patients.

None evaluates Sage calls. The vendor's own results, 60% less administrative work, 4x ROI and 6x faster enrollment, carry no sources.

Who sells it and who backs it?

Ellipsis Health, Inc. is based in San Francisco, with Mainul Mondal as founder and CEO and Michael Aratow as co-founder and CMO. The site gives no founding year. Listed investors include Khosla Ventures, Greycroft, Salesforce Ventures and CVS Health Ventures, among others, and round sizes are not published. Partners named are NVIDIA and Salesforce Health Cloud.

Customer logos include CVS Health, Optum, Duke Health, Nemours, Genworth, Virta Health, Guardant Health, Agilon, Strive Health and Equality Health, with no count. Testimonials come from the CEO of Vivid Health and the CMO of Twin Health. Sage is sold through a demo request, and the pricing unit (per call, per minute or per member) is not stated.

What does it say about security and integration?

Ellipsis lists HIPAA and GDPR compliance, SOC 2 Type 2 and annual third-party audits. Its FAQ says the AI platform "has achieved HITRUST Certification." Sage "can connect with EHR and case management systems" through an API-first design.

The verdict

A plan or system with assessment, enrollment and post-discharge calls to place at scale will find the call types spelled out, and a clinic wanting an inbound symptom line will not.

Editorial review last generated November 2, 2026. Synthesized from clinician sentiment, peer-reviewed coverage, and our editorial silo picks. Refined by hand where vendor facts change.

What it costs

All tiers are custom-quoted. The vendor does not publish per-provider list pricing.

TierMonthlyAnnualNotes
EnterpriseNot statedNot statedNo public price. Pricing unit (per call, minute or member) not stated.

Source: vendor pricing page. Last checked November 2, 2026.

What deploys cleanly

Carries HIPAA, SOC 2 Type II, HITRUST per vendor documentation. Independent attestation review is the buyer's responsibility before clinical deployment.

What the literature says

2 peer-reviewed studies indexed on PubMed evaluate Ellipsis Health in clinical contexts. The most relevant are shown below, ranked by editorial relevance score combining title match, study design, recency, and journal tier.

Evaluating an AI-Enabled Mobile Mental Health Monitoring Tool Among Family Caregivers of Adults Living With Cancer: Single-Arm Feasibility and Acceptability Trial Protocol. (opens in new tab)
Acquati C, Aratow M, Nazreen T, et al.· JMIR Res Protoc· 2026
Psychological distress, particularly symptoms of depression and anxiety (D&A), is highly prevalent among family caregivers of individuals living with cancer, who often assume central roles in care coordination, treatment adherence, symptom monitoring, and emotional support. Rates of distress among caregivers frequently equal or exceed those observed in patients themselves. Despite increased attention to caregivers' mental health needs, routine distress screening remains limited in oncology care settings. Advances in mobile health technology and artificial intelligence (AI) offer opportunities…
Feasibility of a Machine Learning-Based Smartphone Application in Detecting Depression and Anxiety in a Generally Senior Population. (opens in new tab)
Lin D, Nazreen T, Rutowski T, et al.· Front Psychol· 2022
Depression and anxiety create a large health burden and increase the risk of premature mortality. Mental health screening is vital, but more sophisticated screening and monitoring methods are needed. The Ellipsis Health App addresses this need by using semantic information from recorded speech to screen for depression and anxiety. The primary aim of this study is to determine the feasibility of collecting weekly voice samples for mental health screening. Additionally, we aim to demonstrate portability and improved performance of Ellipsis' machine learning models for patients of various ages.…

See all on PubMed (opens in new tab)