Using multiple data features improved the validity of osteoporosis case ascertainment from administrative databases

Lisa M. Lix, Marina S. Yogendran, William D. Leslie, Souradet Y. Shaw, Richard Baumgartner, Christopher Bowman, Colleen Metge, Abba Gumel, Janet Hux, Robert C. James

Research output: Contribution to journalArticle

56 Citations (Scopus)

Abstract

Objectives: The aim was to construct and validate algorithms for osteoporosis case ascertainment from administrative databases and to estimate the population prevalence of osteoporosis for these algorithms. Study Design and Setting: Artificial neural networks, classification trees, and logistic regression were applied to hospital, physician, and pharmacy data from Manitoba, Canada. Discriminative performance and calibration (i.e., error) were compared for algorithms defined from different sets of diagnosis, prescription drug, comorbidity, and demographic variables. Algorithms were validated against a regional bone mineral density testing program. Results: Discriminative performance and calibration were poorer and sensitivity was generally lower for algorithms based on diagnosis codes alone than for algorithms based on an expanded set of data features that included osteoporosis prescriptions and age. Validation measures were similar for neural networks and classification trees, but prevalence estimates were lower for the former model. Conclusion: Multiple features of administrative data generally resulted in improved sensitivity of osteoporosis case-detection algorithm without loss of specificity. However, prevalence estimates using an expanded set of features were still slightly lower than estimates from a population-based study with primary data collection. The classification methods developed in this study can be extended to other chronic diseases for which there may be multiple markers in administrative data.

Original languageEnglish (US)
Pages (from-to)1250-1260
Number of pages11
JournalJournal of Clinical Epidemiology
Volume61
Issue number12
DOIs
StatePublished - Dec 2008
Externally publishedYes

Fingerprint

Osteoporosis
Databases
Calibration
Manitoba
Prescription Drugs
Bone Density
Population
Canada
Prescriptions
Comorbidity
Chronic Disease
Logistic Models
Demography
Physicians

Keywords

  • Classification trees
  • Logistic regression
  • Neural networks
  • Osteoporosis
  • Prevalence
  • Sensitivity
  • Specificity

ASJC Scopus subject areas

  • Epidemiology

Cite this

Lix, L. M., Yogendran, M. S., Leslie, W. D., Shaw, S. Y., Baumgartner, R., Bowman, C., ... James, R. C. (2008). Using multiple data features improved the validity of osteoporosis case ascertainment from administrative databases. Journal of Clinical Epidemiology, 61(12), 1250-1260. https://doi.org/10.1016/j.jclinepi.2008.02.002

Using multiple data features improved the validity of osteoporosis case ascertainment from administrative databases. / Lix, Lisa M.; Yogendran, Marina S.; Leslie, William D.; Shaw, Souradet Y.; Baumgartner, Richard; Bowman, Christopher; Metge, Colleen; Gumel, Abba; Hux, Janet; James, Robert C.

In: Journal of Clinical Epidemiology, Vol. 61, No. 12, 12.2008, p. 1250-1260.

Research output: Contribution to journalArticle

Lix, LM, Yogendran, MS, Leslie, WD, Shaw, SY, Baumgartner, R, Bowman, C, Metge, C, Gumel, A, Hux, J & James, RC 2008, 'Using multiple data features improved the validity of osteoporosis case ascertainment from administrative databases', Journal of Clinical Epidemiology, vol. 61, no. 12, pp. 1250-1260. https://doi.org/10.1016/j.jclinepi.2008.02.002
Lix, Lisa M. ; Yogendran, Marina S. ; Leslie, William D. ; Shaw, Souradet Y. ; Baumgartner, Richard ; Bowman, Christopher ; Metge, Colleen ; Gumel, Abba ; Hux, Janet ; James, Robert C. / Using multiple data features improved the validity of osteoporosis case ascertainment from administrative databases. In: Journal of Clinical Epidemiology. 2008 ; Vol. 61, No. 12. pp. 1250-1260.
@article{7056b7498e184e63b8c6adcf5d3a5717,
title = "Using multiple data features improved the validity of osteoporosis case ascertainment from administrative databases",
abstract = "Objectives: The aim was to construct and validate algorithms for osteoporosis case ascertainment from administrative databases and to estimate the population prevalence of osteoporosis for these algorithms. Study Design and Setting: Artificial neural networks, classification trees, and logistic regression were applied to hospital, physician, and pharmacy data from Manitoba, Canada. Discriminative performance and calibration (i.e., error) were compared for algorithms defined from different sets of diagnosis, prescription drug, comorbidity, and demographic variables. Algorithms were validated against a regional bone mineral density testing program. Results: Discriminative performance and calibration were poorer and sensitivity was generally lower for algorithms based on diagnosis codes alone than for algorithms based on an expanded set of data features that included osteoporosis prescriptions and age. Validation measures were similar for neural networks and classification trees, but prevalence estimates were lower for the former model. Conclusion: Multiple features of administrative data generally resulted in improved sensitivity of osteoporosis case-detection algorithm without loss of specificity. However, prevalence estimates using an expanded set of features were still slightly lower than estimates from a population-based study with primary data collection. The classification methods developed in this study can be extended to other chronic diseases for which there may be multiple markers in administrative data.",
keywords = "Classification trees, Logistic regression, Neural networks, Osteoporosis, Prevalence, Sensitivity, Specificity",
author = "Lix, {Lisa M.} and Yogendran, {Marina S.} and Leslie, {William D.} and Shaw, {Souradet Y.} and Richard Baumgartner and Christopher Bowman and Colleen Metge and Abba Gumel and Janet Hux and James, {Robert C.}",
year = "2008",
month = "12",
doi = "10.1016/j.jclinepi.2008.02.002",
language = "English (US)",
volume = "61",
pages = "1250--1260",
journal = "Journal of Clinical Epidemiology",
issn = "0895-4356",
publisher = "Elsevier USA",
number = "12",

}

TY - JOUR

T1 - Using multiple data features improved the validity of osteoporosis case ascertainment from administrative databases

AU - Lix, Lisa M.

AU - Yogendran, Marina S.

AU - Leslie, William D.

AU - Shaw, Souradet Y.

AU - Baumgartner, Richard

AU - Bowman, Christopher

AU - Metge, Colleen

AU - Gumel, Abba

AU - Hux, Janet

AU - James, Robert C.

PY - 2008/12

Y1 - 2008/12

N2 - Objectives: The aim was to construct and validate algorithms for osteoporosis case ascertainment from administrative databases and to estimate the population prevalence of osteoporosis for these algorithms. Study Design and Setting: Artificial neural networks, classification trees, and logistic regression were applied to hospital, physician, and pharmacy data from Manitoba, Canada. Discriminative performance and calibration (i.e., error) were compared for algorithms defined from different sets of diagnosis, prescription drug, comorbidity, and demographic variables. Algorithms were validated against a regional bone mineral density testing program. Results: Discriminative performance and calibration were poorer and sensitivity was generally lower for algorithms based on diagnosis codes alone than for algorithms based on an expanded set of data features that included osteoporosis prescriptions and age. Validation measures were similar for neural networks and classification trees, but prevalence estimates were lower for the former model. Conclusion: Multiple features of administrative data generally resulted in improved sensitivity of osteoporosis case-detection algorithm without loss of specificity. However, prevalence estimates using an expanded set of features were still slightly lower than estimates from a population-based study with primary data collection. The classification methods developed in this study can be extended to other chronic diseases for which there may be multiple markers in administrative data.

AB - Objectives: The aim was to construct and validate algorithms for osteoporosis case ascertainment from administrative databases and to estimate the population prevalence of osteoporosis for these algorithms. Study Design and Setting: Artificial neural networks, classification trees, and logistic regression were applied to hospital, physician, and pharmacy data from Manitoba, Canada. Discriminative performance and calibration (i.e., error) were compared for algorithms defined from different sets of diagnosis, prescription drug, comorbidity, and demographic variables. Algorithms were validated against a regional bone mineral density testing program. Results: Discriminative performance and calibration were poorer and sensitivity was generally lower for algorithms based on diagnosis codes alone than for algorithms based on an expanded set of data features that included osteoporosis prescriptions and age. Validation measures were similar for neural networks and classification trees, but prevalence estimates were lower for the former model. Conclusion: Multiple features of administrative data generally resulted in improved sensitivity of osteoporosis case-detection algorithm without loss of specificity. However, prevalence estimates using an expanded set of features were still slightly lower than estimates from a population-based study with primary data collection. The classification methods developed in this study can be extended to other chronic diseases for which there may be multiple markers in administrative data.

KW - Classification trees

KW - Logistic regression

KW - Neural networks

KW - Osteoporosis

KW - Prevalence

KW - Sensitivity

KW - Specificity

UR - http://www.scopus.com/inward/record.url?scp=55249113158&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55249113158&partnerID=8YFLogxK

U2 - 10.1016/j.jclinepi.2008.02.002

DO - 10.1016/j.jclinepi.2008.02.002

M3 - Article

C2 - 18619800

AN - SCOPUS:55249113158

VL - 61

SP - 1250

EP - 1260

JO - Journal of Clinical Epidemiology

JF - Journal of Clinical Epidemiology

SN - 0895-4356

IS - 12

ER -