Development and Validation of HealthImpact: An Incident Diabetes Prediction Model Based on Administrative Data

Rozalina McCoy, Vijay S. Nori, Steven A. Smith, Christopher A. Hane

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Objective: To develop and validate a model of incident type 2 diabetes based solely on administrative data. Data Sources/Study Setting: Optum Labs Data Warehouse (OLDW), a national commercial administrative dataset. Study Design: HealthImpact model was developed and internally validated using nested case-control study design; n = 473,049 in training cohort and n = 303,025 in internal validation cohort. HealthImpact was externally validated in 2,000,000 adults followed prospectively for 3 years. Only adults ≥18 years were included. Data Collection/Extraction Methods: Patients with incident diabetes were identified using HEDIS rules. Control subjects were sampled from patients without diabetes. Medical and pharmacy claims data collected over 3 years prior to index date were used to build the model variables. Principal Findings: HealthImpact, scored 0-100, has 48 variables with c-statistic 0.80815. We identified HealthImpact threshold of 90 as identifying patients at high risk of incident diabetes. HealthImpact had excellent discrimination in external validation cohort (c-statistic 0.8171). The sensitivity, specificity, positive predictive value, and negative predictive value of HealthImpact >90 for new diagnosis of diabetes within 3 years were 32.35, 94.92, 22.25, and 96.90 percent, respectively. Conclusions: HealthImpact is an efficient and effective method of risk stratification for incident diabetes that is not predicated on patient-provided information or laboratory tests.

Original languageEnglish (US)
JournalHealth Services Research
DOIs
StateAccepted/In press - 2016

Fingerprint

Information Storage and Retrieval
Type 2 Diabetes Mellitus
Case-Control Studies
Sensitivity and Specificity
Datasets

Keywords

  • Decision support techniques
  • Diabetes mellitus type 2
  • Risk assessment/methods
  • Theoretical models

ASJC Scopus subject areas

  • Health Policy

Cite this

Development and Validation of HealthImpact : An Incident Diabetes Prediction Model Based on Administrative Data. / McCoy, Rozalina; Nori, Vijay S.; Smith, Steven A.; Hane, Christopher A.

In: Health Services Research, 2016.

Research output: Contribution to journalArticle

@article{554b03566982422b9d01d9cc496c7c58,
title = "Development and Validation of HealthImpact: An Incident Diabetes Prediction Model Based on Administrative Data",
abstract = "Objective: To develop and validate a model of incident type 2 diabetes based solely on administrative data. Data Sources/Study Setting: Optum Labs Data Warehouse (OLDW), a national commercial administrative dataset. Study Design: HealthImpact model was developed and internally validated using nested case-control study design; n = 473,049 in training cohort and n = 303,025 in internal validation cohort. HealthImpact was externally validated in 2,000,000 adults followed prospectively for 3 years. Only adults ≥18 years were included. Data Collection/Extraction Methods: Patients with incident diabetes were identified using HEDIS rules. Control subjects were sampled from patients without diabetes. Medical and pharmacy claims data collected over 3 years prior to index date were used to build the model variables. Principal Findings: HealthImpact, scored 0-100, has 48 variables with c-statistic 0.80815. We identified HealthImpact threshold of 90 as identifying patients at high risk of incident diabetes. HealthImpact had excellent discrimination in external validation cohort (c-statistic 0.8171). The sensitivity, specificity, positive predictive value, and negative predictive value of HealthImpact >90 for new diagnosis of diabetes within 3 years were 32.35, 94.92, 22.25, and 96.90 percent, respectively. Conclusions: HealthImpact is an efficient and effective method of risk stratification for incident diabetes that is not predicated on patient-provided information or laboratory tests.",
keywords = "Decision support techniques, Diabetes mellitus type 2, Risk assessment/methods, Theoretical models",
author = "Rozalina McCoy and Nori, {Vijay S.} and Smith, {Steven A.} and Hane, {Christopher A.}",
year = "2016",
doi = "10.1111/1475-6773.12461",
language = "English (US)",
journal = "Health Services Research",
issn = "0017-9124",
publisher = "Wiley-Blackwell",

}

TY - JOUR

T1 - Development and Validation of HealthImpact

T2 - An Incident Diabetes Prediction Model Based on Administrative Data

AU - McCoy, Rozalina

AU - Nori, Vijay S.

AU - Smith, Steven A.

AU - Hane, Christopher A.

PY - 2016

Y1 - 2016

N2 - Objective: To develop and validate a model of incident type 2 diabetes based solely on administrative data. Data Sources/Study Setting: Optum Labs Data Warehouse (OLDW), a national commercial administrative dataset. Study Design: HealthImpact model was developed and internally validated using nested case-control study design; n = 473,049 in training cohort and n = 303,025 in internal validation cohort. HealthImpact was externally validated in 2,000,000 adults followed prospectively for 3 years. Only adults ≥18 years were included. Data Collection/Extraction Methods: Patients with incident diabetes were identified using HEDIS rules. Control subjects were sampled from patients without diabetes. Medical and pharmacy claims data collected over 3 years prior to index date were used to build the model variables. Principal Findings: HealthImpact, scored 0-100, has 48 variables with c-statistic 0.80815. We identified HealthImpact threshold of 90 as identifying patients at high risk of incident diabetes. HealthImpact had excellent discrimination in external validation cohort (c-statistic 0.8171). The sensitivity, specificity, positive predictive value, and negative predictive value of HealthImpact >90 for new diagnosis of diabetes within 3 years were 32.35, 94.92, 22.25, and 96.90 percent, respectively. Conclusions: HealthImpact is an efficient and effective method of risk stratification for incident diabetes that is not predicated on patient-provided information or laboratory tests.

AB - Objective: To develop and validate a model of incident type 2 diabetes based solely on administrative data. Data Sources/Study Setting: Optum Labs Data Warehouse (OLDW), a national commercial administrative dataset. Study Design: HealthImpact model was developed and internally validated using nested case-control study design; n = 473,049 in training cohort and n = 303,025 in internal validation cohort. HealthImpact was externally validated in 2,000,000 adults followed prospectively for 3 years. Only adults ≥18 years were included. Data Collection/Extraction Methods: Patients with incident diabetes were identified using HEDIS rules. Control subjects were sampled from patients without diabetes. Medical and pharmacy claims data collected over 3 years prior to index date were used to build the model variables. Principal Findings: HealthImpact, scored 0-100, has 48 variables with c-statistic 0.80815. We identified HealthImpact threshold of 90 as identifying patients at high risk of incident diabetes. HealthImpact had excellent discrimination in external validation cohort (c-statistic 0.8171). The sensitivity, specificity, positive predictive value, and negative predictive value of HealthImpact >90 for new diagnosis of diabetes within 3 years were 32.35, 94.92, 22.25, and 96.90 percent, respectively. Conclusions: HealthImpact is an efficient and effective method of risk stratification for incident diabetes that is not predicated on patient-provided information or laboratory tests.

KW - Decision support techniques

KW - Diabetes mellitus type 2

KW - Risk assessment/methods

KW - Theoretical models

UR - http://www.scopus.com/inward/record.url?scp=84961786640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961786640&partnerID=8YFLogxK

U2 - 10.1111/1475-6773.12461

DO - 10.1111/1475-6773.12461

M3 - Article

C2 - 26898782

AN - SCOPUS:84961786640

JO - Health Services Research

JF - Health Services Research

SN - 0017-9124

ER -