Marqi Index
Readmission Risk Score
Validation Cohort
n = 5,153
Status
Peer Review
0+
Patients Analyzed
0+
Health Systems
0%
Readmission Reduction
0
Peer-Reviewed Publications
Who Marqi Is Built For
Enterprise-grade risk stratification for healthcare stakeholders who need validated, deployable predictions.
Health Systems
Reduce 30-day readmission penalties under the CMS Hospital Readmissions Reduction Program. Deploy a validated risk model alongside your existing EHR with no rip-and-replace.
Learn morePayers
Stratify your attributed population by 30-day and 365-day risk. Direct case management resources to members who need them, before the admission, not after the claim.
Learn moreTPAs & Employers
Predict catastrophic claim risk in your covered population. Coordinate with stop-loss carriers and care management vendors using a single, validated risk score.
Learn moreTwo products. One mission.
Validated AI infrastructure for predicting and understanding post-discharge risk.
Marqi Index
A peer-reviewed, deployable risk score for 30-day all-cause readmission. Built on real clinical cohorts with AUC 0.807 on temporal validation.
- EHR + claims feature set
- Temporal validation published
- API-ready deployment
- HIPAA compliant
Discharge Risk Intelligence
Turn discharge summaries into structured, auditable risk signals for post-discharge complications, care gaps, and readmission-risk workflows.
- Marqi Risk Prediction Model
- Reliability-gated outputs
- Evidence quotes + audit trails
- Care transition ready
Longevity Blueprint
A comprehensive physician-led health intelligence review that analyzes your full medical history. Powered by MedIQx AI, Blueprint reveals hidden risks, overlooked patterns, and gives you a clear, personalized roadmap to protect your healthspan.
- 5+ years of medical history analysis
- AI-powered risk detection with MedIQx
- 60-minute physician consultation
- Personalized health roadmap
Genetic Risk Analysis
Evaluate hereditary conditions and family history patterns.
AI Pattern Detection
MedIQx identifies hidden risks that traditional checkups miss.
Lab Trend Analysis
Track biomarker changes over time to spot emerging concerns.
Healthspan Roadmap
Actionable recommendations to optimize your long-term health.
The admissions you are paying for are largely predictable.
Hospital readmissions cost the US healthcare system more than $26 billion every year. Model your potential savings with Marqi Index.
Readmission Cost Calculator
Adjust the sliders to model your scenario
Cumulative Cost Comparison
Projected Annual Savings
What Marqi Index Does
From data ingestion to clinical workflow integration in four steps.
Ingests Data You Have
Structured EHR fields and closed claims data. No clinical notes required. No new data collection or workflow change.
Predicts 30-Day Risk
A risk score for the six conditions in CMS HRRP, with an all-cause expansion currently in clinical validation.
Calibrated & Auditable
Every prediction includes a calibrated probability, confidence interval, and clinical signals driving the score.
Workflow Integration
Risk scores delivered to discharge planning, case management, and care coordination. Epic, Cerner, and FHIR-compatible.
Built on real cohorts. Validated against real benchmarks.
The Marqi Index methodology is documented in a manuscript currently under submission at npj Digital Medicine.
Temporal validation, 30-day readmission after AMI. 95% CI: 0.771-0.838.
AMI patients in the development and temporal validation cohort, 2019-2024.
npj Digital Medicine (Nature Portfolio). Full methodology disclosed.
We disclose how the model was built. Including what went wrong.
During Marqi Index development, an AI coding assistant produced a spurious AUC of 0.937 by training on a synthetic patient-level dataset generated from cohort-level aggregates. The error was caught through independent recomputation. The final, validated AUC on real temporal validation data is 0.807.
If you have ever evaluated an AI vendor whose performance claims could not survive a careful audit, you understand why this matters.
Trusted by Quality Leaders
“We were skeptical of another readmission score after years of LACE disappointments. Marqi's transparent validation approach and peer-reviewed methodology finally gave us confidence in the numbers.”
Chief Medical Officer
350-bed Regional Medical Center
The predictive tools your system already has failed to flag the events you are still paying for.
Marqi was founded after a personal experience with a preventable cardiovascular event that current risk tools did not catch. A patient with arteries more than 90 percent blocked, with no symptoms and a regular primary care relationship, was missed by every score in the chart.
That experience defined what Marqi Index has to be: a tool that works on the data systems already collect, that surfaces risk early enough for the care team to act, and that is honest about its limitations.
We are building Marqi Index for the health systems, payers, and TPAs who already know that current risk scoring is not enough.
Common Questions
Quick answers about Marqi Index deployment, validation, and integration.
Stay Ahead of Healthcare AI
Get the latest insights on validated risk prediction, implementation guides, and peer-reviewed research. No spam, unsubscribe anytime.
No spam, unsubscribe anytime. We respect your privacy.
Ready to see validated risk scoring in action?
A 30-minute call covers the Marqi Index product, the validation evidence, the integration approach, and what a pilot looks like in your environment. No deck dump. No sales theater.