As a Geneia blog reader, you likely are familiar with the Geneia Data Intelligence Lab (GDI Lab). In short, the GDI Lab is led by our chief data scientist Fred Rahmanian and staffed with Ph.D. and masters’ level data scientists who are driven to use leading-edge data science to drive lower healthcare costs and improve health outcomes.
The GDI Lab has created a series of models to help health plans, hospitals and physicians to identify, stratify and predict high-cost patients and conditions, including:
- Hypertension Complications Model*, which helps healthcare organizations:
- Predict hypertensive patients/members most likely to experience complications in the next 12 months.
- Predict each person's risk for three stages of hypertension.
- Refine individual risk within each stage.
- Onset of Type 2 Diabetes Model*, which predicts the members likely to become diabetic in the next 12 months;
- Type 2 Diabetes Complications Model* and the Heart Failure Complications Model*, which forecasts which patients are likely to experience a complication related to the chronic disease in the coming 12 months.
- Opioid Abuse and/or Overdose Model*, which predicts the patients who are likely to have an opioid abuse diagnosis or an overdose event in the next six months.
- High Cost Claimants Model, which predicts future cost using demographics information (e.g., age and gender) and as few as only two data elements from claims (e.g., cost and date of service.)
- Hypertension: Challenge to Treat Model, which predicts who will be challenging to treat for hypertension in the next 12 months.
Over the years, many have asked to know more about how the GDI Lab creates its model. Some of the questions I’ve heard are:
- What’s the difference between artificial intelligence (AI) and machine learning?
- What are neural networks?
- How does Geneia construct the data sets it uses in model development?
- What are the characteristics of a good data set and a good model?
I’m pleased to share that many of the frequently asked questions about the GDI Lab and much more are addressed in the video, By Looking Forward You Can Avoid the Distractions in the Rear-view Mirror, a conversation with Barry Chaiken, MD, clinical lead of Tableau and author of the book, Navigating the Code: How Revolutionary Technology Transforms the Patient-Physician Journey, Geneia’s chief data scientist Fred Rahmanian and our president and CEO, Heather Lavoie.
To view the video, click here.
*Patent pending for the Opioid Abuse and/or Overdose Model, Onset of Type 2 Diabetes Model, Type 2 Complications Model, Heart Failure Complications Model and Hypertension Complications Model. Predictive models, by their very nature, contain certain assumptions. This is not an attempt to practice medicine or provide specific medical advice, and it should not be used to make a diagnosis or to replace or overrule a qualified healthcare provider’s judgment. Certain data used in these studies were supplied by International Business Machines Corporation. Any analysis, interpretation, or conclusion based on these data is solely that of the authors and not International Business Machines Corporation. Click here to review Geneia’s full legal notice and disclaimer.