Urgent.News

What's breaking now, across thousands of outlets.

AI

NCQA to use Komodo data, AI tool to develop future HEDIS measures

NCQA researchers will have access to Komodo’s dataset and AI-powered healthcare intelligence platform to explore complex questions. NCQA is solely responsible for developing HEDIS measures.

Komodo Health, a healthcare intelligence company powered by AI, has joined forces with the National Committee for Quality Assurance (NCQA) to modernize the development of healthcare quality measures. This strategic partnership, spanning multiple years, will grant NCQA researchers access to Komodo’s Healthcare Map - a vast repository containing over 330 million de-identified patient journeys.

This allows for a comprehensive analysis of care across various insurance types, care settings, and patient populations from a single, longitudinal data source.

The partnership also sees NCQA gaining access to Komodo’s Marmot, an AI-powered platform that enables the exploration of complex questions with transparent, reproducible results. Web Sun, co-founder and co-CEO of Komodo Health, highlighted the importance of having a comprehensive, current view of patient populations for healthcare organizations, as quality measures define performance understanding and identify areas for care improvement.

This collaboration aims to expedite and streamline the development of new quality measures, ultimately ensuring that the Health Maintenance Organization (HEDIS) measures reflect real-world evidence. Traditionally, developing new quality measures has been a time-consuming process, requiring the aggregation of disparate datasets and extensive field testing with various payers and partners - often taking two to three months for each population studied.

However, with Komodo’s Healthcare Map, NCQA researchers can now efficiently evaluate measures across multiple insurance types using a single, consistent data source.

Already, Komodo Health has supported the development and testing of the Follow-Up After Positive Colorectal Cancer Non-Invasive Screening Test (COF-E) for implementation in Measurement Year 2027. By leveraging lab data and claims information, NCQA was able to significantly reduce the testing time for this measure, down to about a month for Medicare Advantage, Medicaid, and commercial populations.

Looking forward, NCQA is optimistic about advancing HEDIS measures that are based on real-world patterns of care and are actionable for healthcare organizations. They have confidence in Komodo’s Healthcare Map due to its breadth, consistency, and longitudinal coverage. Web Sun emphasized that Komodo is committed to continuously refining the Healthcare Map and expanding its breadth, depth, and longitudinal view of healthcare delivery.

However, Sun also noted that the primary focus is on turning this data into trusted intelligence to inform critical decisions within healthcare organizations. Komodo Health is expected to serve as a key platform supporting HEDIS measure testing activities across NCQA's portfolio, with specific testing approaches remaining driven by individual project needs.

Written by urgent.news from Fierce Healthcare's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at fiercehealthcare.com →

More in AI

Using Scikit-Learn Pipelines: A Cleaner Way to Build Machine Learning Models

If you've spent some time building machine learning models with Python, you've probably had a notebook that looked something like this: X_train = scaler . fit_transform ( X_train ) X_test = scaler .

  • Pipelines connect multiple ML steps into a single workflow
  • Prevent data leakage by applying preprocessing only to training data
  • Keep preprocessing and modeling together for cleaner, maintainable code

Mesmo com GraphRAG, o agent se perde sem contrato de memória

Pessoal, o agent puxou um trecho bonito. Similaridade alta. Confiança alta. Estava no stub errado. Não foi “RAG fraco”. Foi porta errada. Índice caro, lixo na entrada.

  • Agent struggles without memory contract despite GraphRAG technology
  • High cost of index and garbage input identified as problems
  • Contract consists of single source, unique canonic pages, and scopes

More from Friday 28 August →