Definition:
Predictive Modeling in health care strives to use health data to predict the ultimate cost of a claim based on claimant characteristics, and injury circumstance.
It can also be used to evaluate the efficacy a treatment based on specific injury and patient characteristics. These results can help inform treatment decision and adds to the understanding of evidence based medicine.
In workers comp this means developing a model that can help predict how quickly the claimant returns to work, the chances of a claim reopening at a later date and whether surgery or physical therapy are more effective treatment of a given injury type.
Evidence Based Medicine
wikipedia: "Evidence-based medicine (EBM) or evidence-based practice (EBP) aims to apply the best available evidence gained from the scientific method to clinical decision making.[1] It seeks to assess the strength of evidence of the risks and benefits of treatments (including lack of treatment) and diagnostic tests.[2] This helps clinicians to learn whether or not any treatment will do more good than harm.[3]
Evidence quality can be assessed based on the source type (from meta-analyses and systematic reviews of double-blind, placebo-controlled clinical trials at the top end, down to conventional wisdom at the bottom), as well as other factors including statistical validity, clinical relevance, currency, and peer-review acceptance."
Key Presentations:
Workers Comp Claims Predictive Modeling - How to Reduce WC Medical Costs
PRIDIT: An Example from Hospital Quality
Helpful links:
http://www.healthcare-informatics.com/article/gains-predictive-modeling