In this 60-page special report, "Predictive Modeling: Improving Margins by Identifying and Targeting High-Risk Populations," a panel of experts detail ways health plans use predictive modeling to identify plan members who may need proactive care management. By identifying this at-risk population, health plans can accurately gauge future patient expenses based on prior treatments. Using a combination of technology and web-based tools, health plans can use predictive modeling to project future member and group healthcare costs and price more appropriately for risk.

Click here to hear what our customers have said about this resource:

You'll hear from Howard Brill, manager of medical informatics at Monroe Plan for Medical Care Inc.; Danielle Butin, manager, health promotion and wellness, Oxford Health Plans; Michael Cousins, Ph.D, director of informatics, Health Management Corporation; James M. Dolstad, ASA, MAAA, vice president of actuarial services, SHPS Inc.; Dr. Stanley Hochberg, medical director, provider service network; Marilyn Schlein Kramer, CEO and president, DxCG Inc.; and Jerry Osband, MD, chief medical officer, SHPS Inc., on theories, application and results of predictive modeling programs.

In this report Brill, Butin, Cousins, Dolstad, Hochberg, Kramer and Osband describe the types of predictive models, the impact of predictive modeling programs and how predictive modeling results can be improved.

You'll get details on:

• Trends in predictive modeling;
• Evidence-based medicine and predictive modeling;
• Diseases best suited to predictive modeling;
• The role of health risk assessments in predictive modeling;
• Validating the integrity of the data
• The bottom line impact of predictive modeling programs.

Here's what our customers have said about this resource:

This report affords a real-to-life perspective on challenges and benefits. The examples are palpable and easily referable making it less challenging to relate the barriers and benefits of a data analytics and predictive modeling strategy to our clients," said Shawna Koch, RN, director of healthcare innovation at Perot Systems.

Table of Contents

• Improving the Quality of Data Collection for Effective Predictive Modeling
  • Risk Groupers
  • Statistical Models
  • Artificial Intelligence
  • The Potential of Neural Networks
  • Features of Neural Networks
  • The Impact of Modeling Tools on the Healthcare Industry
  • One Predictive Model Doesn’t Necessarily Fit All
• Strategies, Trends and Forecasts
  • Incremental Cost of Chronic Disease
  • Models Address Top 10 Healthcare Issues
  • Identifying Potentially Expensive Patients
  • Adding DCGs Improves Margins
  • Medicare Drives Healthcare Trends
• The Impact of Evidence-based Medicine on Predictive Modeling
  • Pros and Cons of Health Risk Assessments
  • Diseases Best Suited to Predictive Modeling
  • HRAs Match High-Risk Patients to Interventions
  • Variables for Diabetes in Predictive Models
  • The Struggle to Manage Re-Admissions
  • Transitional Coaches Conduct Patient Assertiveness Training
  • Using Predictive Modeling to Identify High-Risk Members
  • Telephonic Training Reaches Out to Homebound COPD Patients
  • Pain Management Program Nets $142 PMPM
• Predictive Modeling’s Impact and EBM’s Role
  • Ensuring Data Integrity
  • Elements of Data Mining
  • Net Savings Forecast
  • Identifying a Member’s Willingness to Change
  • Where Predictive Modeling Has an Impact
  • Formulating an Intervention Strategy
  • Enhanced Engagement Process
• Predictive Modeling in an Integrated Delivery System
  • Predictive Modeling’s Effect on PMPM
  • Current Concerns
  • Predictive Modeling and Medicaid Care Management
  • Pareto 80/20 Rule: Monroe Asthma Patients, 2002
  • The Value of Prediction
  • Components of a Coherent Care Management Process
  • Targeted Interventions Change Predicted Outcomes
  • Challenges of Risk Adjustment Based on Predictive Modeling
• Q&A: Ask the Experts
  • Predictive Modeling in the Self-Insured Market
  • Maximizing Enrollment in Opt-In Plans
  • Software Recommendations
  • The High-Risk Patient and Bedside Tools
  • Developing Predictors for Intervenable Cases
  • The Value of Telephonic vs. Online Communications
  • Specifying Physician Incentives
  • Adjusting Forecasts for Exaggeration or Overestimation
  • Updating Predictive Models for New Treatments, Drugs
  • Drawbacks to Predictive Modeling
  • Boosting ROI