Aetna Inc.

DEFY AUGURY?

Henry Wei, M.D. November 2014

Aetna Inc.

Not a whit. We defy augury. There’s a  special providence in the fall of a sparrow.

If it be now, ’tis not to come. If it be not to  come, it will be now. If it be not now, yet it  will come—the readiness is all. Since no 

man of aught he leaves knows, what is ’t to  leave betimes? Let be. 

‐

Hamlet, Act 5, Scene 2

2

ICD-10 : W61: Contact with birds (domestic) (wild) W61.99XA Other contact with other birds, initial encounter

Aetna Inc.

Whither Accuracy?

3

Aetna Inc.

“City vs

Highway Mileage”

Aetna Inc.

We all love this pyramid

5

Conventional Application 

doesn’t require precision at 

boundaries:1.Use fancy models to find the 

highest‐risk populations2.Nurses line them up for calls 

from outer space3.“Engagement”

levels 

modest

“Truncated model”

note 

in footnotes of tech 

documentation

Pond full of Black Swans:Invisible to claims‐driven 

models, yet full of risk.

Aetna Inc.

Clinically‐Derived  Inputs

6

Medical Conditions

Acuity vs. Chronicity

Complexity of Care

Psychosocial

Groupers

Consumer Behavior

e.g. ACG, ERG, DxCG, CDPS, 3M

How sick is this population? Who are the sickest?

Aetna Inc.

Clinically‐Derived  Inputs

7

Medical Conditions

Acuity vs. Chronicity

Complexity of Care

Psychosocial

Groupers

Consumer Behavior

e.g. ACG, ERG, DxCG, CDPS, 3M

How sick is this population? Who are the sickest?

“Actionable Insight”

= 

Prioritized lists? That’s it?

Typical “dashboard”

graph from 

100s of startups and well‐

established analytics companies

Aetna Inc. 8

Physician Decision‐Making (Provider Contracting)

Aetna Inc.

Clinically‐Derived  Inputs

9

Medical Conditions

Acuity vs. Chronicity

Complexity of Care

Psychosocial

Groupers

Consumer Behavior

Add a drug

Add a test

Stop a drug

Do a diagnostic workup

Ask for more data

How sick is this population? Who are the sickest?

How well‐managed are they?What intervention are needed?

What will be the change in 

utilization that results?Physician Decision‐Making

Aetna Inc.

Example: Stroke Prevention

Aetna Inc.

STROKE434.11

AVOIDEDSTROKE

ATRIAL 

FIBRILLATION

427.31

Aetna Inc.12

Example of Clinically‐Derived Inputs Feature Extraction for Diabetes

Diagnose & Evaluate

Prevent & Monitor for Complications

Manage Disease & Complications Medication Safety

BMI>25 & Age >40, need diabetes test

High random blood sugar, need test

Gestational diabetes, need diabetes test

Metabolic syndrome, need treatment

Need Vaccines for Influenza, Pneumonia

Need Eye Exam

Need Foot Exam

Need Peripheral Artery Disease Test

Need A1c blood test

Need LDL cholesterol blood test

Need kidney damage urine protein test

Need kidney function blood test

>40, need aspirin

LDL >100, no meds, need statin therapy

LDL still high, on meds, need intensify

High A1c, no meds, need metformin

High A1c, on meds, need to intensify

Very high A1c, need insulin

Hypertension, need ACE inhibitor/ARB

Statins – liver, muscle damage warning

Aspirin & ulcer risk, need ulcer protection

Oral contraceptives – danger with diabetes

Hyperglycemia - Atypical Antipsychotics

Metformin danger conditions, need tests

Glitazones, liver danger, tests needed

Drugs that worsen blood sugar levels

ACE inhibitor/ARB side effects (e.g. potassium)

Kidney damage, need ACE inhibitor / ARB

Atypical Antipsychotics – Glucose Monitoring

Systemic steroids – Hyperglycemia screen

Autoimmune disorders – Diabetes screen

Aetna Inc.

EBM Gaps in Care: Cousins of Quality Measures

Patient Data

CareEngine Logic

Message• Relevant data• Applicable literature and

guideline(s)

• What data was found (claims for diabetes, labs for micro-albuminuria, no claims for ACE inhibitor or ARB)

• Literature and guidelines (American Diabetes Association recommendation)

Alert generation

Excluded• Already on medication

or equivalent• Contraindications to

medication• Similar CC sent

• Current ACE Inhibitor/ARB • Angioedema • Pregnancy• Hyperkalemia• Renovascular disease

Exception screening

Validated• Diabetes • Diabetic nephropathy• Age 18+

• ICD-9 claims for Diabetes• Diabetes medications or supplies or DME• Micro-albuminuria >=30 mL/day(Also with specific timeframe criteria)

Clinical confirmation

Aetna Inc.

Note on ICD code specificity & clinical data

ICD‐9

↓ICD‐10

↑ ↓HL7 + SNOMED

↓Mood Codes

14

Sensitivity vs.  Specificity

EHR

Aetna Inc.

Clinically‐Relevant Outputs

15

Groupers Total Cost

Unit Volumes Unit Costsx

Aetna Inc.

Clinically‐Relevant Outputs

16

Groupers Total Cost

Inpatient

OP Procedures

ER

Specialty Visits

PCP Visits

Imaging

Lab Tests

Rx

Rates

Rates

Rates

Rates

Rates

Rates

Rates

Rates

Unit volume Unit cost

Aetna Inc. 17

InpatientAcute

InpatientNon‐Acute

OP 

Procedures 

& FacilityER

ROC (C‐stat) 0.82 0.84 0.79 0.84

PPV 53% 48% 59% 63%

Sensitivity 28% 23% 35% 60%

Specificity 96% 99% 95% 95%

% of overall spend ~39% 8.4% 3.8%

Aetna Inc. 18

Aetna Inc.

Shouldn’t our predictive models keep  breaking down if we’re doing our job?

•

If Risk Adjustment models change 

only modestly year‐over‐year…

are 

we actually making progress?

•

Do we inadvertently remove the 

most important predictor features / 

variables because they’re so good 

at reducing costs?

In other words, if we don’t believe 

there are modifiable

risk factors…

then all of this healthcare business 

is just an academic exercise.

Aetna Inc.

Real‐World Outcomes & High‐Dimensional Propensity  Scoring: A Wish to the Predictive Modeling Community

20

Predict 

assignment to 

intervention 

(e.g. logistic 

regression)

Compare 

intervention 

group vs. 

matched 

“control”

Use PS as 

adjustment 

covariate, 

stratification 

tool, or identify 

matches

How might we bring the strength of the predictive modeling community to 

bear, with opportunity for massive automation & ways to solve for hidden 

bias?

Aetna Inc.

A Final Note: Patient‐Centered Predictive Modeling

21