MedAI Verdict
Decision support

Clinical Decision Support

eCART logo

eCART

by AgileMD  ·  US

Last verified

Early warning software that scores hospitalized ward patients for risk of deterioration from EHR data, for use by trained clinicians.

Visit eCART (opens in new tab)Read our methodology

At a glance

Pricing
No public price. There is no pricing page; the site offers a demo request only.
HIPAA
Attested
SOC 2
Type II
EHRs
—
Founded
—
HQ
US
On this page

Independent score  ·  By our public rubric

56/100Solid choice

Editorial rating 4.0 / 5

How it’s computed →
  • Regulatory & Compliance
    22/22

    FDA cleared (1 K-number on record)

  • Clinical Integration
    0/11.6

    No EHR integrations listed

  • Evidence Strength
    21/30

    5 peer-reviewed papers

  • Vendor & Market
    3/18

    Seed-stage or unfunded

  • Sentiment & Transparency
    1.3/2.5

    Pricing on request, no public amounts

▸ Show all 11 dimensions

Regulatory & Compliance

  • FDA clearance12/12

    FDA cleared (1 K-number on record)

  • HIPAA / SOC2 / BAA10/10

    HIPAA + (SOC2 or BAA) attested

Clinical Integration

  • EHR integrations (count)0/6

    No EHR integrations listed

  • Top-3 EHR coverage (Epic / Oracle / Athena)0/5

    None of the top-3 EHRs covered

  • Bidirectional write-back0/1

    No bidirectional write-back documented

Evidence Strength

  • Peer-reviewed papers21/21

    5 peer-reviewed papers

  • RCT / meta-analysis / systematic review0/9

    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 transparency1/3

    Pricing on request, no public amounts

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

Early warning software that scores hospitalized ward patients for risk of deterioration from EHR data, for use by trained clinicians.

No public price. There is no pricing page; the site offers a demo request only. HIPAA + SOC 2 Type II attested.

Evidence record

FDA decisions
Peer-reviewed

5 studies on PubMed: 5 other, published 2024 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, eCART record, https://medaiverdict.com/tools/agilemd, version November 2, 2026

Change history
View every change to this record

Bottom line

eCART is a ward deterioration score from AgileMD, a San Francisco company, built to warn staff before a hospitalized adult dies or goes to the ICU. FDA cleared it through a 510(k) in June 2024, and its published record is long, though much of it comes from the group that developed it. It fits a hospital with ward-based staff ready to respond to a flag. An ICU or an outpatient clinic falls outside the indication.

What did the FDA clear in 2024?

K233253 was cleared on June 21, 2024 as the eCARTv5 Clinical Deterioration Suite (21 CFR 870.2210, product code QNL, "Medium-Term Adjunctive Predictive Cardiovascular Indicator"). The vendor announced the clearance on June 25, 2024. The indication is automated risk stratification and early warning for impending deterioration, defined as death or ICU transfer, in hospitalized ward patients aged 18 and over, used by trained medical professionals.

The predicate is CLEWICU (K200717), with PeraServer and PeraTrend (K172959) as a reference device. K233253 is AgileMD's only 510(k). Scoring starts when any vital sign is charted and uses validated EHR data such as nurse-confirmed vitals. The vendor says the High, Moderate or Average score updates in real time.

Who wrote the eCART papers?

A 2024 JAMA Network Open paper (PMID 39405061) compared six early warning scores across more than 362,000 ward encounters at Yale New Haven Health. According to a summary of the paper, eCART had the best accuracy. The comparators were the Epic Deterioration Index, Rothman Index, NEWS, NEWS2 and MEWS, and the authors include eCART developers. A 2024 medRxiv preprint (PMID 38562803) covers development and prospective validation of eCARTv5.

PubMed returns 18 hits for the score with deterioration terms, and many come from the University of Chicago group tied to the vendor. AgileMD reports a 13% relative mortality reduction at Yale since go-live, citing a Becker's article of August 19, 2025. A third-party blog from Quentir argues that the response team matters as much as the score.

What else does AgileMD sell?

The vendor describes Clinical Pathways as order sets, calculators and documentation inside the EHR. A release of October 20, 2019 announced QuantHC merging with AgileMD, and a $2 million NIH SBIR Phase II grant was announced on October 12, 2021. The homepage claims more than 400 hospitals and 150,000 clinical users.

The site refers to "native EHR workflows" without naming an EHR. The vendor describes its cloud decision-support engine as SOC 2 and HIPAA compliant. Purchase starts with a demo request, because the site publishes no price.

The verdict

The Yale comparison against the Epic Deterioration Index is a large published comparison, with developer co-authors, and the 13% mortality reduction is the vendor's figure. A hospital that wants evidence from outside the developing group will weigh the University of Chicago authorship behind many of the papers.

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. There is no pricing page; the site offers a demo request only.

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

What deploys cleanly

Carries FDA 510(k), HIPAA, SOC 2 per vendor documentation. Independent attestation review is the buyer's responsibility before clinical deployment.

What the literature says

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

Early Warning Scores With and Without Artificial Intelligence. (opens in new tab)
Edelson DP, Churpek MM, Carey KA, et al.· JAMA Netw Open· 2024
Early warning decision support tools to identify clinical deterioration in the hospital are widely used, but there is little information on their comparative performance. To compare 3 proprietary artificial intelligence (AI) early warning scores and 3 publicly available simple aggregated weighted scores. This retrospective cohort study was performed at 7 hospitals in the Yale New Haven Health System. All consecutive adult medical-surgical ward hospital encounters between March 9, 2019, and November 9, 2023, were included. Simultaneous Epic Deterioration Index (EDI), Rothman Index (RI), eCARTv…
Multicenter Development and Prospective Validation of eCARTv5: A Gradient Boosted Machine Learning Early Warning Score. (opens in new tab)
Churpek MM, Carey KA, Snyder A, et al.· medRxiv· 2024
Early detection of clinical deterioration using machine learning early warning scores may improve outcomes. However, most implemented scores were developed using logistic regression, only underwent retrospective validation, and were not tested in important subgroups. Our objective was to develop and prospectively validate a gradient boosted machine model (eCARTv5) for identifying clinical deterioration on the wards. Multicenter retrospective and prospective observational study. Inpatient admissions to the medical-surgical wards at seven hospitals in three health systems for model development…
DETERIO-LLM: enhancing traditional deterioration risk scores with clinical context and advanced reasoning. (opens in new tab)
Ghanbari G, Ahn JC, Kim E, et al.· JAMIA Open· 2026
Accurate and timely prediction of physiological deterioration in hospitalized patients is essential, but existing deep learning models, which rely solely on structured electronic health record (EHR) data, generate high false-positive rates by missing crucial contextual information in clinical notes. We present DETERIO-LLM, a hybrid prediction model that selectively integrates large language models (LLMs) with a deep learning model (DETERIO) to reclassify borderline-risk alerts using narrative clinical notes. This retrospective study used a cohort of 1000 inpatients (4.6% deterioration prevale…
Causes, Diagnostic Testing, and Treatments Related to Clinical Deterioration Events among High-Risk Ward Patients. (opens in new tab)
Churpek MM, Ingebritsen R, Carey KA, et al.· medRxiv· 2024
Timely intervention for clinically deteriorating ward patients requires that care teams accurately diagnose and treat their underlying medical conditions. However, the most common diagnoses leading to deterioration and the relevant therapies provided are poorly characterized. Therefore, we aimed to determine the diagnoses responsible for clinical deterioration, the relevant diagnostic tests ordered, and the treatments administered among high-risk ward patients using manual chart review. Multicenter retrospective observational study. Inpatient medical-surgical wards at four health systems from…
Comparison of Deep Learning Approaches Using Chest Radiographs for Predicting Clinical Deterioration: Retrospective Observational Study. (opens in new tab)
Rahman M, Gao J, Carey KA, et al.· JMIR AI· 2025
The early detection of clinical deterioration and timely intervention for hospitalized patients can improve patient outcomes. The currently existing early warning systems rely on variables from structured data, such as vital signs and laboratory values, and do not incorporate other potentially predictive data modalities. Because respiratory failure is a common cause of deterioration, chest radiographs are often acquired in patients with clinical deterioration, which may be informative for predicting their risk of intensive care unit (ICU) transfer. This study aimed to compare and validate dif…

See all on PubMed (opens in new tab)

Other decision support

See the full decision support ranking