We created a 3-part onboarding series for mimilabs! It illustrates how to join our community and explore open healthcare data with powerful computing tools. Here's Part 1: Welcome to the Community. In this video, you'll learn how to: - Join our vibrant Slack community of healthcare data enthusiasts - Set up your secure access to the platform - Meet mimi-bot, your AI-powered data assistant Stay tuned for Part 2 where we'll dive into our Databricks environment! #HealthcareData #DataAnalytics #Community #Healthcare https://lnkd.in/e8xbMVWS
About us
At mimilabs, we will work on projects nobody has time to work on, e.g., solutions around extreme weather events, underserved communities, small practices and ACOs, and healthcare policies. With our minimalistic yet high-quality engineering, we can make them widely available, beautiful, and meaningful to everybody. We are a mission-driven company focused on long-term wins. Our projects share the common mission of helping patients, providers, and many other stakeholders in the industry. Together, by accumulating these beautiful small things, we will achieve big and sustainable industry changes.
- Website
-
https://mimilabs.ai
External link for mimilabs
- Industry
- Data Infrastructure and Analytics
- Company size
- 1 employee
- Headquarters
- Atlanta, GA
- Type
- Privately Held
- Founded
- 2024
Locations
-
Primary
Get directions
Atlanta, GA 30306, US
Employees at mimilabs
Updates
-
Did you know you can check the claim denial rates of ACA plans? Also, detailed benefits and cost sharing of those plans? Check out at mimilabs! https://lnkd.in/eHtUqh5y
-
Check out our prompt template for exploring what you can do with mimilabs' data! https://lnkd.in/eu_TxY3N
mimi-public-research/2024-12-18_how_to_use_llm_to_discover_high_roi_projects_with_mimilabs_data.md at main · mimilabs/mimi-public-research
github.com
-
Announcing: Placekey is now available on mimilabs! Data is more powerful when joined with disparate sources. Our CEO, Yubin Park, PhD, said this many times - it's like making a data curry! When it comes to data, 1+1 is greater than 2. New insights emerge when we combine different datasets. However, it's often difficult to find organizations willing to share this passion and do more with their data, especially in healthcare. Many immediately want to monetize what they have, rather than exploring what "more" they could achieve by first sharing and combining their data with others. That's why it was such a delight to meet Hayden Mortimer, who challenges this very closed mindset! Hayden and I met a couple of weeks ago, and we discovered we share the same philosophy: when we share and join data, the entire community moves forward and we can aim higher together! We're excited to announce that many of the mimilabs tables containing addresses will now be indexed with Placekey, a universal address key that you can use to join various location data and much more! To start, we've made Placekey available in NPIDATA, and we'll be releasing several more tables with Placekey integration. This is incredibly exciting! Special thanks to Jarred Parrett for making this happen! If you want to join open healthcare data with other datasets, come join us and use all the available data! Sign up Link: https://lnkd.in/eYrMrgYX
-
-
Six thousand variables! That's how many we found in the Centers for Medicare & Medicaid Services Research Files (via ResDAC). We've combed through all available tables, variables, and their dictionaries - and now you can navigate them all in mimilabs! Check out the resdac catalog. Ever wondered what those mysterious "00" or "11" codes mean in specific columns? Mystery solved! All those definitions are now in mimilabs, so you can say goodbye to hard-coding values. Join tables and automate processes with ease! 🎉 https://lnkd.in/egUA_K2Y
Data Catalog - mimilabs
mimilabs.ai
-
HCC in FHIR! Join our cool project!
CEO at mimilabs | LinkedIn Top Voice | Ph.D., Machine Learning and Health Data
HCC in Fire? No FHIR! 🔥 I'm finally embarking on a project to rewrite hccpy. The new version, called `hccinfhir` (HCC in FHIR), will be managed under mimilabs. I've admittedly been slacking on maintaining the hccpy package, primarily because I felt it needed a complete rewrite for several reasons: - HCC is more than just diagnosis mapping. While diagnosis-to-CC mapping is critical, the complex filtering logic was overlooked in the previous implementation - Reference data is constantly evolving. From diagnosis-to-CC mappings to model versions and their variations, new models have been introduced over the years with frequently changing reference data - Our data interface with CMS is transitioning from flatfile to FHIR. Whether you're a FHIR enthusiast or not, we'll increasingly interact with it, especially in the Medicare space. Since FHIR will be our source of truth for CMS data, working with minimal data loss is crucial. When FHIR transforms to relational tables, many nested relationships and graph structures are either lost or become difficult to identify, creating reconciliation challenges After much consideration and time spent collecting various reference data in mimilabs and studying different logics and BCDA, I've finally taken the first step. Here's the draft of the package (see the link). I'm approaching the problem in three phases: 1. Extract: ingests raw FHIR data and extracts minimal data elements for risk adjustment 2. Filter: applies various claim filtering logic across Inpatient/Outpatient/Professional claims 3. Calculate: leverages reference data to compute risk scores and other relevant outputs So far, I've completed the Extract phase and will soon implement the other two components. My goal is to create an HCC engine that achieves reconcilable-grade accuracy. Want to run HCC directly from your BCDA data feed with accuracy that closely matches CMS numbers? Share your thoughts and feedback – I'll work to incorporate as many suggestions as possible! https://lnkd.in/ecN9xrk6
GitHub - mimilabs/hccinfhir: HCC Algorithm that works with FHIR
github.com
-
🎉 Milestone achieved: 1000+ amazing followers! What started as curiosity has grown into became a journey of exploring and analyzing thousands of public datasets with all of you. Together, we've been uncovering fascinating insights about Medicare Advantage, SDoH, and nitty-gritty details of Medicare billing and operation. Want to join our growing community of data enthusiasts? Hit that follow button to get fresh data insights and observations in your feed! Thank you to everyone who's been part of this data exploration journey so far. 💡 #DataAnalysis #DataScience #DataCommunity #Milestone #workmilestone
This content isn’t available here
Access this content and more in the LinkedIn app
-
Many new datasets are updated in our mimilabs data catalog! - PalmettoGBA; various EDPS/RAPS/FERAS valuesets! - NYU: Avoidable ED visit algorithms - Bid Pricing Data for Medicare Advantage plans - Risk Adjustment Models value sets!! https://lnkd.in/eX8wJp-t Check out our data catalog to learn more! Or even better, sign up and become our members: https://lnkd.in/eYrMrgYX
Centers for Medicare & Medicaid Services Data
data.cms.gov
-
Linking various datasets can sometimes provide you an interesting perspective!
CEO at mimilabs | LinkedIn Top Voice | Ph.D., Machine Learning and Health Data
If It's Avoidable, It's Not Risk Adjustable If you've taken Vishnu Rachakonda's claims analytics course or used the Tuva Health data mart (yay Aaron Neiderhiser!), you're likely familiar with the NYU Avoidable ED Visit algorithm - a standard approach for identifying potential savings opportunities in claims analytics. Recently, I had an interesting thought: what if we connected the NYU algorithm with CMS-HCC? In other words, is there a relationship between avoidable ED visits and risk adjustment factors? The chart above reveals the answer. Using the 2017 NYU patched algorithm [1] and the V28 HCC diagnosis set, I analyzed diagnosis codes with Non-Emergent Scores above 0 (noner > 0) - essentially, visits that "could have been" avoided with some probability. The x-axis shows the Non-Emergent Score quartiles, while the y-axis displays diagnosis code counts, with eligible codes in blue and ineligible codes in yellow. What stands out? As visits become more definitively non-emergent, we see increasingly tall yellow bars, indicating they're not eligible for Risk Adjustment. The correlation between Non-Emergent Scores and non-RA eligibility is striking. It's almost like a rule: if it's not emergent, it's not risk adjustable. This insight offers interesting perspectives. These non-emergent visits represent pure cost - they don't even contribute to risk adjustment. You could reduce them significantly without affecting your benchmark at all. The question becomes: what are the best strategies to reduce avoidable ED visits? It seems like such a clear-cut goal. Sometimes, combining seemingly unrelated datasets can provide surprisingly valuable insights. [1] https://lnkd.in/dgyKRFEE
-
-
The final part of our mimilabs quickstart series is here – meet your new favorite research companion! In this video, we showcase mimi-bot, our AI-powered assistant that helps you: - Find relevant healthcare datasets instantly - Generate SQL queries for complex analyses - Get research guidance and support - Navigate our extensive data catalog efficiently Ready to start exploring healthcare data? Join our community today and transform healthcare through data-driven insights! #HealthcareInnovation #AI #DataAnalysis #HealthTech https://lnkd.in/eDmhfN_F
mimilabs onboarding part3
https://www.youtube.com/