Risk Adjusting Health Care Provider Collaboration Networks

Ariel E. Chandler*, R Kannan Mutharasan, Lia Amelia, Matthew B. Carson, Denise M Scholtens, Nicholas Dean Soulakis

*Corresponding author for this work

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Objectives The quality of hospital discharge care and patient factors (health and sociodemographic) impact the rates of unplanned readmissions. This study aims to measure the effects of controlling for the patient factors when using readmission rates to quantify the weighted edges between health care providers in a collaboration network. This improved understanding may inform strategies to reduce hospital readmissions, and facilitate quality-improvement initiatives. Methods We extracted 4 years of patient, provider, and activity data related to cardiology discharge workflow. A Weibull model was developed to predict the risk of unplanned 30-day readmission. A provider-patient bipartite network was used to connect providers by shared patient encounters. We built collaboration networks and calculated the Shared Positive Outcome Ratio (SPOR) to quantify the relationship between providers by the relative rate of patient outcomes, using both risk-adjusted readmission rates and unadjusted readmission rates. The effect of risk adjustment on the calculation of the SPOR metric was quantified using a permutation test and descriptive statistics. Results Comparing the collaboration networks consisting of 2,359 provider pairs, we found that SPOR values with risk-adjusted outcomes are significantly different than unadjusted readmission as an outcome measure (p -value = 0.025). The two networks classified the same provider pairs as high-scoring 51.5% of the time, and the same low scoring provider pairs 85.6% of the time. The observed differences in patient demographics and disease characteristics between high-scoring and low-scoring provider pairs were reduced by applying the risk-adjusted model. The risk-adjusted model reduced the average variation across each individual's SPOR scored provider connections. Conclusions Risk adjusting unplanned readmission in a collaboration network has an effect on SPOR-weighted edges, especially on classifying high-scoring SPOR provider pairs. The risk-adjusted model reduces the variance of providers' connections and balances shared patient characteristics between low- and high-scoring provider pairs. This indicates that the risk-adjusted SPOR edges better measure the impact of collaboration on readmissions by accounting for patients' risk of readmission.

Original languageEnglish (US)
Pages (from-to)71-78
Number of pages8
JournalMethods of Information in Medicine
Volume58
Issue number2-3
DOIs
StatePublished - Jan 1 2019

Fingerprint

Health Personnel
Patient Readmission
Risk Adjustment
Workflow
Patient Discharge
Quality Improvement
Cardiology
Patient Care
Demography
Outcome Assessment (Health Care)
Health

Keywords

  • electronic health records
  • hospital readmission
  • network analysis
  • risk-adjustment

ASJC Scopus subject areas

  • Health Informatics
  • Advanced and Specialized Nursing
  • Health Information Management

Cite this

@article{eac69b436e1e4e0b9410cd1b5736bd42,
title = "Risk Adjusting Health Care Provider Collaboration Networks",
abstract = "Objectives The quality of hospital discharge care and patient factors (health and sociodemographic) impact the rates of unplanned readmissions. This study aims to measure the effects of controlling for the patient factors when using readmission rates to quantify the weighted edges between health care providers in a collaboration network. This improved understanding may inform strategies to reduce hospital readmissions, and facilitate quality-improvement initiatives. Methods We extracted 4 years of patient, provider, and activity data related to cardiology discharge workflow. A Weibull model was developed to predict the risk of unplanned 30-day readmission. A provider-patient bipartite network was used to connect providers by shared patient encounters. We built collaboration networks and calculated the Shared Positive Outcome Ratio (SPOR) to quantify the relationship between providers by the relative rate of patient outcomes, using both risk-adjusted readmission rates and unadjusted readmission rates. The effect of risk adjustment on the calculation of the SPOR metric was quantified using a permutation test and descriptive statistics. Results Comparing the collaboration networks consisting of 2,359 provider pairs, we found that SPOR values with risk-adjusted outcomes are significantly different than unadjusted readmission as an outcome measure (p -value = 0.025). The two networks classified the same provider pairs as high-scoring 51.5{\%} of the time, and the same low scoring provider pairs 85.6{\%} of the time. The observed differences in patient demographics and disease characteristics between high-scoring and low-scoring provider pairs were reduced by applying the risk-adjusted model. The risk-adjusted model reduced the average variation across each individual's SPOR scored provider connections. Conclusions Risk adjusting unplanned readmission in a collaboration network has an effect on SPOR-weighted edges, especially on classifying high-scoring SPOR provider pairs. The risk-adjusted model reduces the variance of providers' connections and balances shared patient characteristics between low- and high-scoring provider pairs. This indicates that the risk-adjusted SPOR edges better measure the impact of collaboration on readmissions by accounting for patients' risk of readmission.",
keywords = "electronic health records, hospital readmission, network analysis, risk-adjustment",
author = "Chandler, {Ariel E.} and Mutharasan, {R Kannan} and Lia Amelia and Carson, {Matthew B.} and Scholtens, {Denise M} and Soulakis, {Nicholas Dean}",
year = "2019",
month = "1",
day = "1",
doi = "10.1055/s-0039-1694990",
language = "English (US)",
volume = "58",
pages = "71--78",
journal = "Methods of Information in Medicine",
issn = "0026-1270",
publisher = "Schattauer GmbH",
number = "2-3",

}

Risk Adjusting Health Care Provider Collaboration Networks. / Chandler, Ariel E.; Mutharasan, R Kannan; Amelia, Lia; Carson, Matthew B.; Scholtens, Denise M; Soulakis, Nicholas Dean.

In: Methods of Information in Medicine, Vol. 58, No. 2-3, 01.01.2019, p. 71-78.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Risk Adjusting Health Care Provider Collaboration Networks

AU - Chandler, Ariel E.

AU - Mutharasan, R Kannan

AU - Amelia, Lia

AU - Carson, Matthew B.

AU - Scholtens, Denise M

AU - Soulakis, Nicholas Dean

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Objectives The quality of hospital discharge care and patient factors (health and sociodemographic) impact the rates of unplanned readmissions. This study aims to measure the effects of controlling for the patient factors when using readmission rates to quantify the weighted edges between health care providers in a collaboration network. This improved understanding may inform strategies to reduce hospital readmissions, and facilitate quality-improvement initiatives. Methods We extracted 4 years of patient, provider, and activity data related to cardiology discharge workflow. A Weibull model was developed to predict the risk of unplanned 30-day readmission. A provider-patient bipartite network was used to connect providers by shared patient encounters. We built collaboration networks and calculated the Shared Positive Outcome Ratio (SPOR) to quantify the relationship between providers by the relative rate of patient outcomes, using both risk-adjusted readmission rates and unadjusted readmission rates. The effect of risk adjustment on the calculation of the SPOR metric was quantified using a permutation test and descriptive statistics. Results Comparing the collaboration networks consisting of 2,359 provider pairs, we found that SPOR values with risk-adjusted outcomes are significantly different than unadjusted readmission as an outcome measure (p -value = 0.025). The two networks classified the same provider pairs as high-scoring 51.5% of the time, and the same low scoring provider pairs 85.6% of the time. The observed differences in patient demographics and disease characteristics between high-scoring and low-scoring provider pairs were reduced by applying the risk-adjusted model. The risk-adjusted model reduced the average variation across each individual's SPOR scored provider connections. Conclusions Risk adjusting unplanned readmission in a collaboration network has an effect on SPOR-weighted edges, especially on classifying high-scoring SPOR provider pairs. The risk-adjusted model reduces the variance of providers' connections and balances shared patient characteristics between low- and high-scoring provider pairs. This indicates that the risk-adjusted SPOR edges better measure the impact of collaboration on readmissions by accounting for patients' risk of readmission.

AB - Objectives The quality of hospital discharge care and patient factors (health and sociodemographic) impact the rates of unplanned readmissions. This study aims to measure the effects of controlling for the patient factors when using readmission rates to quantify the weighted edges between health care providers in a collaboration network. This improved understanding may inform strategies to reduce hospital readmissions, and facilitate quality-improvement initiatives. Methods We extracted 4 years of patient, provider, and activity data related to cardiology discharge workflow. A Weibull model was developed to predict the risk of unplanned 30-day readmission. A provider-patient bipartite network was used to connect providers by shared patient encounters. We built collaboration networks and calculated the Shared Positive Outcome Ratio (SPOR) to quantify the relationship between providers by the relative rate of patient outcomes, using both risk-adjusted readmission rates and unadjusted readmission rates. The effect of risk adjustment on the calculation of the SPOR metric was quantified using a permutation test and descriptive statistics. Results Comparing the collaboration networks consisting of 2,359 provider pairs, we found that SPOR values with risk-adjusted outcomes are significantly different than unadjusted readmission as an outcome measure (p -value = 0.025). The two networks classified the same provider pairs as high-scoring 51.5% of the time, and the same low scoring provider pairs 85.6% of the time. The observed differences in patient demographics and disease characteristics between high-scoring and low-scoring provider pairs were reduced by applying the risk-adjusted model. The risk-adjusted model reduced the average variation across each individual's SPOR scored provider connections. Conclusions Risk adjusting unplanned readmission in a collaboration network has an effect on SPOR-weighted edges, especially on classifying high-scoring SPOR provider pairs. The risk-adjusted model reduces the variance of providers' connections and balances shared patient characteristics between low- and high-scoring provider pairs. This indicates that the risk-adjusted SPOR edges better measure the impact of collaboration on readmissions by accounting for patients' risk of readmission.

KW - electronic health records

KW - hospital readmission

KW - network analysis

KW - risk-adjustment

UR - http://www.scopus.com/inward/record.url?scp=85072146412&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072146412&partnerID=8YFLogxK

U2 - 10.1055/s-0039-1694990

DO - 10.1055/s-0039-1694990

M3 - Article

C2 - 31514208

AN - SCOPUS:85072146412

VL - 58

SP - 71

EP - 78

JO - Methods of Information in Medicine

JF - Methods of Information in Medicine

SN - 0026-1270

IS - 2-3

ER -