Abstractive Health vs xCures (2026)

AI Health Index verifiedSeptember 30, 2026
Verdict

Both retrieve a patient's records from outside institutions and turn them into something a clinician can use. Abstractive Health retrieves records through Carequality and CommonWell and summarizes them, with every summary sentence linked to its source note. It adds question answering with citations and chart alerts that clinicians define in plain language. Clinicians use it as a web app, a SMART on FHIR app, a Chrome extension or an API, at a published price. xCures sells the Clinical Clarity Engine, which retrieves records through exchanges, national networks, direct connections and record requests. Two large language model approaches turn them into structured, source linked data and answer clinical questions with citations. Output is normalized to FHIR R4 and OHDSI vocabularies and delivered through a public API. The trust page publishes an accuracy table for four extractors and a 95 percent threshold before an extractor enters production. Choose Abstractive Health for sourced summaries a clinician can start on without a sales call; choose xCures for records turned into structured data for checklists and analysis.

The case for Abstractive Health
  • A clinician should be able to start on a free account or at $99 a month.
  • You want the business associate agreement readable before signup, at every tier.
  • You want a peer reviewed study of the summaries with its error rate published.
The case for xCures
  • You need records structured as data, normalized to FHIR R4 and OHDSI vocabularies.
  • Your work runs on clinical questions answered with citations, such as cancer stage at diagnosis.
  • You want a published accuracy threshold before any extractor enters production.

This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. Abstractive Health and xCures are each graded against the same capability taxonomy, from each vendor's own public materials and the regulatory record, under the AI Health Index verification standard. No vendor pays for placement, and no vendor has reviewed this page. How this evidence is graded

At a Glance

Plain facts

Fact Abstractive Health xCures
Primary category Clinical Summarization & Chart Review Clinical Decision Support
Founded 2022 2018
Headquarters New York, New York, United States Oakland, California
Website abstractivehealth.com xcures.com
Attribute Matrix

Side by Side

Select any grade to read the note behind it.

Axis
A
Abstractive Health
X
xCures
AI Centrality
Autonomy and Oversight Model
Model and Technology Transparency
Model Supply Chain Disclosure
Clinical and Operational Evidence
AI Safety and PHI Stewardship
HIPAA and BAA Posture
Security Certifications and Trust Center
FDA and Regulatory Status
AI Governance and Bias Disclosure
AI Liability and Recourse
EHR and Interoperability Depth
Deployment Model and Data Residency
Commercial Transparency
Setting and Specialty Coverage
Change Log

Product updates

The latest logged changes from each vendor, newest first, each linked to its source.

xCures

  • EHR / interoperability

    xCures added Care Team endpoints to its API.

    Source
All 1 xCures update →
Citable Summaries

Each vendor in one paragraph

Written to be quoted whole. Each paragraph opens the AI Health Index profile of the vendor: what the product is, who buys it and what it does.

Abstractive Health

Abstractive Health retrieves a patient's records from the national exchange networks and summarizes them, with every sentence of the summary linked to the source note it came from. The company is a Carequality implementer; its search looks for records around a patient's current and prior addresses, and it normalizes CCDA, FHIR R4, PDF and scanned documents into one record, with the original files downloadable.

Source: AI Health Index, September 2026

xCures

xCures sells the Clinical Clarity Engine, which retrieves a patient's records from across the United States and turns them into structured, source linked data. Retrieval runs through health information exchanges, qualified health information networks, direct record connections and traditional record requests, and two large language model approaches extract structured data, normalized to FHIR R4 and OHDSI vocabularies, and answer clinical questions with citations to the documents used.

Source: AI Health Index, September 2026

FAQ

Questions buyers ask

How do Abstractive Health and xCures work with the EHR?

For Abstractive Health, the company is a Carequality implementer, lists CommonWell on its home page, and retrieves CCDA, FHIR R4, PDF and scanned documents into one normalized record, with the original files downloadable and exports in PDF, FHIR and JSON.

The Privacy and Security Notice says that for exchange through TEFCA xCures does not provide bidirectional services. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 30, 2026. No vendor pays for placement.

Which settings and specialties do Abstractive Health and xCures cover?

In Abstractive Health's case, the company names outpatient, inpatient and emergency use, pre-visit review, handoff notes, transitions of care and discharge summaries, and population work for the CMS ACCESS model; its case studies cover reproductive endocrinology and VA community care. The peer reviewed validation covers emergency to inpatient handoff notes at one site, and the SBIR study outpatient chart review by two physicians.

For xCures, the site sells to providers, diagnostics laboratories, value based care organizations and channel partners, and describes the Engine as working across conditions. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 30, 2026. No vendor pays for placement.

What evidence is published for Abstractive Health and xCures?

With Abstractive Health, the home page says "Clinically proven" and cites the company's JAMA Network Open study (Hartman 2024): a retrospective single-site cohort of 1,600 emergency records at NewYork-Presbyterian and Weill Cornell, 1,500 used for training and 100 for testing, with a research model (RoBERTa and Llama-2 7B, fine-tuned on premise).

In xCures' case, the trust page reports four extractors at 95.7 to 98.2 percent accuracy from a random 10 percent audit, described as retrospective. The peer reviewed items on the research page are clinical analyses that use xCures data, not evaluations of the Engine. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 30, 2026. No vendor pays for placement.

How much do Abstractive Health and xCures leave to the clinician?

For Abstractive Health, the free tier lets an individual clinician use summaries and alerts with no institutional review.

With xCures, the site's provider line promises "the full patient history for every case", while the trust page's own known limitations say retrieval reads the top ranked documents and not the rest, so relevant information in lower ranked documents can be missed. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 30, 2026. No vendor pays for placement.

Keep Comparing

Related comparisons

Other published head to head assessments involving these vendors or their closest peers.

Disclosure

Both records were reviewed on this site in September 2026. xCures publishes no price. xCures promises providers "the full patient history for every case". Its own trust page says retrieval reads the top ranked documents, so relevant information in lower ranked ones can be missed. Abstractive Health calls itself "Clinically proven" on the strength of its own study. That study tested a research model on 50 emergency handoff summaries rated by three physicians. It found the model marginally inferior to physician notes on usefulness and safety, with an incorrectness rate of 9.6 percent against 2.0 percent. xCures's accuracy figures come from a company preprint on 34 patients and a retrospective audit. xCures may keep de identified data in perpetuity and use it for any purpose. Abstractive Health's privacy policy uses de identified data to refine its models. Neither names the model it runs in production today. Neither publishes accuracy by patient group. Neither describes writing back into the chart.

Ask both what share of a patient's outside records they typically find, and ask xCures how a missed document is found.