TY - JOUR
T1 - A predictive model to identify Parkinson disease from administrative claims data
AU - Nielsen, Susan Searles
AU - Warden, Mark N.
AU - Camacho-Soto, Alejandra
AU - Willis, Allison W.
AU - Wright, Brenton A.
AU - Racette, Brad A.
N1 - Funding Information:
Study funded by the Michael J. Fox Foundation, National Institute for Environmental Health Sciences (K24ES017765), and American Parkinson Disease Association. Dr. Racette takes full responsibility for the data, the analyses and interpretation, and the conduct of the research; has full access to all of the data; and has the right to publish any and all data separate and apart from any sponsor.
Funding Information:
Dr. Searles Nielsen reports government research support from the NIH (R21 ES024120 [co-I], R01ES021488 [co-I], R01 ES025991 [co-I]) and research support from the Michael J. Fox Foundation. M.N. Warden reports no disclosures relevant to the manuscript. Dr. Camacho-Soto reports government research support from NCMRR (K12HD00109719). Dr. Willis reports government research support from NINDS (K23NS081087). Dr. Wright reports research support from Teva (sub-I) and Vaccinex (sub-I). Dr. Racette reports research support from Teva (PI), US World Meds (PI), Allergan (PI), and Vaccinex (PI); government research support from the NIH (K24ES017765 [PI], R21ES17504 [PI], R01ES021488 [PI], R01ES021488-02S1 [PI], R01 ES025991 [PI], R21ES024120); research support from the Michael J. Fox Foundation; and consultation income from 86 Pillars for legal consultation. Go to Neurology.org for full disclosures.
Publisher Copyright:
© 2017 American Academy of Neurology.
PY - 2017/10/3
Y1 - 2017/10/3
N2 - Objective: To use administrative medical claims data to identify patients with incident Parkinson disease (PD) prior to diagnosis. Methods: Using a population-based case-control study of incident PD in 2009 among Medicare beneficiaries aged 66-90 years (89,790 cases, 118,095 controls) and the elastic net algorithm, we developed a cross-validated model for predicting PD using only demographic data and 2004-2009 Medicare claims data. We then compared this model to more basic models containing only demographic data and diagnosis codes for constipation, taste/smell disturbance, and REM sleep behavior disorder, using each model's receiver operator characteristic area under the curve (AUC). Results: We observed all established associations between PD and age, sex, race/ethnicity, tobacco smoking, and the above medical conditions. A model with those predictors had an AUC of only 0.670 (95% confidence interval [CI] 0.668-0.673). In contrast, the AUC for a predictive model with 536 diagnosis and procedure codes was 0.857 (95% CI 0.855-0.859). At the optimal cut point, sensitivity was 73.5% and specificity was 83.2%. Conclusions: Using only demographic data and selected diagnosis and procedure codes readily available in administrative claims data, it is possible to identify individuals with a high probability of eventually being diagnosed with PD.
AB - Objective: To use administrative medical claims data to identify patients with incident Parkinson disease (PD) prior to diagnosis. Methods: Using a population-based case-control study of incident PD in 2009 among Medicare beneficiaries aged 66-90 years (89,790 cases, 118,095 controls) and the elastic net algorithm, we developed a cross-validated model for predicting PD using only demographic data and 2004-2009 Medicare claims data. We then compared this model to more basic models containing only demographic data and diagnosis codes for constipation, taste/smell disturbance, and REM sleep behavior disorder, using each model's receiver operator characteristic area under the curve (AUC). Results: We observed all established associations between PD and age, sex, race/ethnicity, tobacco smoking, and the above medical conditions. A model with those predictors had an AUC of only 0.670 (95% confidence interval [CI] 0.668-0.673). In contrast, the AUC for a predictive model with 536 diagnosis and procedure codes was 0.857 (95% CI 0.855-0.859). At the optimal cut point, sensitivity was 73.5% and specificity was 83.2%. Conclusions: Using only demographic data and selected diagnosis and procedure codes readily available in administrative claims data, it is possible to identify individuals with a high probability of eventually being diagnosed with PD.
UR - http://www.scopus.com/inward/record.url?scp=85030776257&partnerID=8YFLogxK
U2 - 10.1212/WNL.0000000000004536
DO - 10.1212/WNL.0000000000004536
M3 - Article
C2 - 28864676
AN - SCOPUS:85030776257
SN - 0028-3878
VL - 89
SP - 1448
EP - 1456
JO - Neurology
JF - Neurology
IS - 14
ER -