Reducing Healthcare Costs through Targeted Care Management: Risk - - PowerPoint PPT Presentation

Reducing Healthcare Costs through Targeted Care Management: Risk Adjustment Modeling to Predict Patients Remaining High-Cost

JONATHAN WRATHALL, PHD, INTERMOUNTAIN HEALTHCARE TOM BELNAP, MS, INTERMOUNTAIN HEALTHCARE CONCORDIUM 2016

Highest Costs Originate Among Select Few

At Intermountain Healthcare:

• Among patients in the highest cost decile in 2012:

– 20% of patients remained in the highest cost decile in 2013. – 18% of patients remained in the highest cost decile in 2014.

• From 2008-2012, top 5% high-cost patients incurred 51% of healthcare costs.
• In 2012, Top 1% of patients incurred 24% of healthcare costs
• Most of these patients have at least one chronic condition

How can we respond to these challenges?

Community Care Management

What is CCM?

– Longitudinal care management pilot – Not embedded in a clinic

Which Patients?

1. Retrospective Referrals

– Highest cost and most complex patients

2. Concurrent Referrals

– Highest risk from other care managers or clinicians

3. Additional Inclusions/Exclusions

Model Design

– Initial In-home assessment by appropriate discipline – Interdisciplinary

• Dedicated Clinical Pharmacist, Care

Conferences with PCPs, Community based Resources, other Care Managers. – Referrals to internal and community-based resources – Intensive Care Coordination to navigate complexities of healthcare – Community Integration

Core Team

– Community Care Manager (RN) – Community Care Social Worker (MSW) – Community Care Transitionist

Objectives

• Improve upon the current pre-screening ranking algorithm to

identify & prioritize patients for care managers to reach out to.

– Prioritize patients sooner – Require less data

• Proof of concept

– This process can be refined as care management teams define strategy around what services they will provide.

CCM Pre-Screening Cost-Rank Algorithm

• Living Adults
• Not enrolled in a care management program
• Not a transplant patient
• Select Health or uninsured
• Within 30 miles of a Care Management Clinic
• In Top 10% of hospital costs* in the previous year

& in Top 15% in one of the two years prior

Sample

• Hospital Costs* in the previous year
• Indigo Expected Benefit Score
• Charlson Comorbidity Index Score
• Optum Prospective Risk Score

Rank

*Hospital costs exclude chemotherapy, dialysis, IV therapy, spinal fusion, knee & hip replacement

Proposed Changes to a Predictive Logistic Model

• Living Adults
• Not enrolled in a care management program
• Not a transplant patient
• Select Health or uninsured
• Within 30 miles of a Care Management Clinic
• In Top 15% of hospital* & MG Cost in the previous year

& in Top 15% in one of two prior years

Sample

• Hospital and MG Costs* in the previous year
• Charlson Comorbidity Index Score
• Indigo Expected Benefit Score
• Optum Prospective Risk Score

Variables

• Likelihood of Pre-Screening Patients Remaining In Top 15% of

Cost For 2 of 3 Future Years

• Tested multiple models aimed at limiting regression to the

mean

• CART, Random Forests, & Logistic Regression

Predict

*Hospital costs exclude chemotherapy, dialysis, IV therapy, spinal fusion, knee & hip replacement + Additional Patient Demographics + Additional Health Information

Demographic & Health Information

Additional Comorbidities Obstructive Sleep Apnea Hyperlipidemia Morbid Obesity Coronary Artery Disease Hypertension

Persistent Top 15% ~ Demographic Factors + SocioEconomic Factors + Comorbidities + ε !"#!$

Behavioral Health Conditions Schizophrenic Disorders Depression Bipolar Affective Disorders Organic Psychotic Conditions Nonorganic Psychoses Neurotic Disorders Personality Disorders Alcohol/Drug Dependence Eating Disorders Childhood/Adolesence Disorders Intellect Disability Charlson Comorbidities Myocardial Infarction Cancer Connective Tissue Disease-Rheumatic Disease Chronic Pulmonary Disease Cerebrovascular Disease Metastatic Carcinoma Dementia Moderate or Severe Liver Disease Diabetes with complications Diabetes without complications Mild Liver Disease Periphral Vascular Disease AIDS/HIV Peptic Ulcer Disease Congestive Heart Failure Renal Disease Paraplegia and Hemiplegia

Socio-Economic Factors Average Household Income in Patient ZIP Code Singh Area Deprivation Index in Patient Census Block Demographic Factors Age Gender Marital Status

• Random Forest Classification

– variables selected based on Variable Importance Matrix

• Logistic Regression performed better than

Random Forest and outperformed CART.

Modeling Results

Measure Cost-Rank Model Logistic Model

C-statistic .536 .712 Likelihood of Pre-Screening Patients Remaining In Top 15% of Cost For 1 of 3 Future Years 63.0% 79.0% Likelihood of Pre-Screening Patients Remaining In Top 15% of Cost For 2 of 3 Future Years 31.0% 48.1% Identified Patients 1,400 1,800

• Avg. Prior Year Cost

$38,700 $44,000 % with Area Deprivation Index > 115 (Top Quintile) 16.9% 18.0%

• Avg. Number of Charlson Comorbidities

3.6 5.0

• Avg. Number of Behavioral Health Conditions

1.7 2.2

• Avg. Number of Other Comorbidities

1.4 2.3 Diagnosed With Behavioral Health Condition 63.2% 82.8% Diagnosed With Obesity 27.8% 54.9% Diagnosed With Hypertension Patients 59.3% 80.3%

Improving Patient Intervention Targets

• Relatively simple variables can improve predictive power

– Basic prediction model includes administrative data with additional persistent comorbidities. – Did not require lengthy cost history. – Some difficulty in obtaining socioeconomic context variables.

• Populations may have specific characteristics unique to them.

– Be sensitive to sample characteristics.

Prediction vs Ranking

Questions?

Thank you