 |
|
"For smaller healthcare
organizations, leveraging predictive analytics for risk
assessment (e.g. population assessment) and risk adjustment
could be a good start (the ‘Crawl’ state). Using commercially
available predictive modeling solutions for care management
identification, stratification and triaging could be a good next
step in the predictive modeling journey (the ‘Walk’ state).
Developing custom predictive models to address specific needs
(e.g. predicting hospital-acquired conditions) could represent
the ‘Run’ state. Leveraging advanced predictive modeling
techniques such as artificial intelligence, machine learning,
deep learning, etc., to solve complex business problems (e.g.
emergency room department demand and flow) could qualify as the
‘Fly’ state.” - Soyal Momin MS MBA, Vice President, Center of Excellence for Data and Analytics, Presbyterian Health Services. |
|
"Based on our
literature review, we hypothesized that people with higher risk
of prescription opioid use would incur higher healthcare costs
and utilization than non-prescription opioid users. However, we
did not expect a considerable difference in the percentage
increase between medical and pharmacy costs; for example, among concomitant users (i.e., both opioids and benzodiazepine), the percentage increase in pharmacy costs was 41%, while this increase was only 7% in medical costs.” Excerpted from: Predictive Modeling News, Volume 11 Number 6, June 2018, Journal Scan: "JHU CPHIT Team Details Costs, Predictors of Opioid Abuse ." |
 |
A Predictive Model Use Case in the Healthcare Domain
Behavioral health (BH) conditions and their escalating severity
can often negatively impact chronic medical conditions;
proactively identifying a population in need of an appropriate
and supportive BH intervention may help to achieve optimal
health outcomes. The objective of this presentation is to
describe the development of a predictive model that estimates BH
severity for a Medicare Advantage population in the next 12
months, and identify high risk members for timely clinical
intervention. The model is currently being employed to identify
individuals that will likely have escalating BH severity in the
future and accordingly deliver appropriate interventions. |
|
- Journal Scan: JHU CPHIT Team Details Costs, Predictors of Opioid Abuse
- Duncan's PM/RA Text Now in 2nd Edition; Expert Details Changes
- Market Reports
- Movers and Shakers
- Thought Leaders' Corner: "Which predictive modeling activities are most effective for smaller healthcare organizations, those with limited budgets and few, if any, dedicated analytics staff?"
- Industry News: Kaiser Permanente, Zillion, Restore Health, Anthem, TripleTree and EarlySense
- Predictably Quotable
- Click here to subscribe to Predictive Modeling News, or find out more
Follow Health Policy Publishing:
|
||
| Subscribe to the Bulletin | Promotional Opportunities |
| Predictive
Modeling Bulletin, a publication of Health Policy Publishing LLC 1101 Standiford Avenue, Suite C-3, Modesto, CA 95350 (v) 209.577.4888 | (f) 209.577.3557 © 2018, Health Policy Publishing LLC |