echoloc
Get started
echoloc/ Companies/ MedReview Inc.

MedReview Inc. Tech Stack

Clinical payment integrity platform using ML to detect medical claim errors

Hospitals and Health Care New York, New York 201–500 employees Founded 1974 Privately Held
medreview.us LinkedIn

MedReview operates a physician-led claims auditing platform built on a modern data stack (Databricks, Azure Synapse, ClickHouse, PyTorch, TensorFlow) paired with HL7/FHIR clinical standards. The tech reflects a shift from legacy batch infrastructure toward real-time ingest and MLOps—active projects include a real-time data ingestion framework and ML model deployment pipeline—while the senior-skewed hiring mix (10 of 16 roles) and emphasis on HITRUST certification readiness suggest the company is scaling both clinical rigor and compliance depth simultaneously.

Tech Stack 81 technologies

Core StackAzure Data Factory Databricks ClickHouse Python PyTorch TensorFlow MLflow Kubeflow Terraform Kafka Jira Confluence Azure DevOps GitLab CI/CD AWS SQL Server Docker Kubernetes scikit-learn Tableau Power BI Azure Synapse Azure Machine Learning HL7 FHIR Bicep Azure Event Hubs Azure GCP Bash+49 more

What MedReview Inc. Is Building

◆Challenges

  • Reducing improper payments
  • Managing appeals from non-participating providers
  • Evolving legacy data infrastructure
  • Optimizing clickhouse for large-scale ingestion
  • Ensuring hitrust/hipaa compliance
  • Ensuring timely resolution of appeals
  • Improving financial accuracy
  • Cost containment
  • Coding accuracy
  • Readmission reduction

▲Active Projects

  • Develop and update drg clinical validation review criteria
  • Develop and update model language for review activity
  • Quality assurance activities related to clinical review programs
  • Real-time data ingestion framework
  • Mlops pipeline for model deployment
  • Hitrust certification readiness
  • Payment integrity (pi) operations
  • Clinical validation of diagnosis codes
  • Implementation of new clients
  • Affinitē unified data platform

Hiring Activity

Accelerating15 roles · 10 in 30d

Department

Data
5
Healthcare
4
Ops
4
Engineering
2
Product
1

Seniority

Senior
10
Mid
5
Director
1

Notable leadership hires: Medical Director, Director of Coding

Company intelligence

Find more companies like MedReview Inc. by tech stack, pain points and active projects

Get started free

About MedReview Inc.

MedReview identifies inaccurate medical claims for health insurance payers and hospital systems. Founded in 1974, the company combines physician-led clinical review with machine learning to flag billing errors, DRG coding mistakes, and utilization patterns that deviate from clinical norms. Services span pre- and post-pay audits, readmission reviews, prior authorization, and case management. The platform processes claims through a hybrid workflow: algorithms surface high-risk cases, then physician reviewers document findings before reassignment or appeal. The company operates across the full claims lifecycle—from initial validation through appeals resolution—and maintains internal case management and quality assurance functions.

HeadquartersNew York, New York
Company Size201–500 employees
Founded1974
Hiring MarketsUnited States

Frequently Asked Questions

What is MedReview's tech stack?

Core: Databricks, Azure Synapse, ClickHouse, and SQL Server for data; Python, PyTorch, TensorFlow, scikit-learn for ML; Kafka and Azure Event Hubs for streaming; Kubernetes, Docker, Terraform for infrastructure; Tableau and Power BI for reporting. HL7/FHIR standards for clinical data integration.

What are MedReview's main pain points?

Reducing improper payments at scale; managing appeals from non-participating providers; evolving legacy data infrastructure; optimizing ClickHouse for large-scale ingestion; ensuring HITRUST/HIPAA compliance; improving coding accuracy; readmission reduction; cost containment.

How this profile is built

MedReview Inc.'s technology stack, projects, and hiring signals are inferred from public hiring and company data — career pages, public listings, and company web presence — then clustered and de-duplicated. Figures are estimates that refresh over time. Read our full methodology →

This is not an official vendor or customer list. It is a technology-adoption signal inferred from public data, intended for B2B research.