A predictive model to identify Parkinson disease from administrative claims data
Citation Manager Formats
Make Comment
See Comments

This article requires a subscription to view the full text. If you have a subscription you may use the login form below to view the article. Access to this article can also be purchased.
Abstract
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.
GLOSSARY
- AUC=
- area under the receiver operator characteristic curve;
- BASF=
- beneficiary annual summary file;
- CPT=
- Current Procedural Terminology;
- ICD-9=
- International Classification of Diseases–9;
- PD=
- Parkinson disease;
- RBD=
- REM sleep behavior disorder
Footnotes
Go to Neurology.org for full disclosures. Funding information and disclosures deemed relevant by the authors, if any, are provided at the end of the article.
Supplemental data at Neurology.org
- Received November 19, 2016.
- Accepted in final form July 11, 2017.
- © 2017 American Academy of Neurology
AAN Members
We have changed the login procedure to improve access between AAN.com and the Neurology journals. If you are experiencing issues, please log out of AAN.com and clear history and cookies. (For instructions by browser, please click the instruction pages below). After clearing, choose preferred Journal and select login for AAN Members. You will be redirected to a login page where you can log in with your AAN ID number and password. When you are returned to the Journal, your name should appear at the top right of the page.
AAN Non-Member Subscribers
Purchase access
For assistance, please contact:
AAN Members (800) 879-1960 or (612) 928-6000 (International)
Non-AAN Member subscribers (800) 638-3030 or (301) 223-2300 option 3, select 1 (international)
Sign Up
Information on how to subscribe to Neurology and Neurology: Clinical Practice can be found here
Purchase
Individual access to articles is available through the Add to Cart option on the article page. Access for 1 day (from the computer you are currently using) is US$ 39.00. Pay-per-view content is for the use of the payee only, and content may not be further distributed by print or electronic means. The payee may view, download, and/or print the article for his/her personal, scholarly, research, and educational use. Distributing copies (electronic or otherwise) of the article is not allowed.
Letters: Rapid online correspondence
- Author response: A predictive model to identify PD from administrative claims data
- Susan Searles Nielsen, Assistant Professor, Washington University in St. Louis, Department of Neurology
- Brad A. Racette, Professor, Washington University in St. Louis, Department of Neurology
Submitted March 10, 2018 - RE: A predictive model to identify PD from administrative claims data
- Tomoyuki Kawada, Professor, Nippon Medical School
Submitted December 24, 2017
REQUIREMENTS
You must ensure that your Disclosures have been updated within the previous six months. Please go to our Submission Site to add or update your Disclosure information.
Your co-authors must send a completed Publishing Agreement Form to Neurology Staff (not necessary for the lead/corresponding author as the form below will suffice) before you upload your comment.
If you are responding to a comment that was written about an article you originally authored:
You (and co-authors) do not need to fill out forms or check disclosures as author forms are still valid
and apply to letter.
Submission specifications:
- Submissions must be < 200 words with < 5 references. Reference 1 must be the article on which you are commenting.
- Submissions should not have more than 5 authors. (Exception: original author replies can include all original authors of the article)
- Submit only on articles published within 6 months of issue date.
- Do not be redundant. Read any comments already posted on the article prior to submission.
- Submitted comments are subject to editing and editor review prior to posting.
You May Also be Interested in
Dr. David E. Vaillancourt and Dr. Shannon Y. Chiu
► Watch
Topics Discussed
Alert Me
Recommended articles
-
Article
Fractures in the prodromal period of Parkinson diseaseAlejandra Camacho-Soto, Anat Gross, Susan Searles Nielsen et al.Neurology, April 28, 2020 -
Article
Use of medical care biases associations between Parkinson disease and other medical conditionsAnat Gross, Brad A. Racette, Alejandra Camacho-Soto et al.Neurology, May 09, 2018 -
Article
Neurologist ambulatory care, health care utilization, and costs in a large commercial datasetJohn P. Ney, Barbara Johnson, Tom Knabel et al.Neurology, December 23, 2015 -
Article
Validation of an algorithm for identifying MS cases in administrative health claims datasetsWilliam J. Culpepper, Ruth Ann Marrie, Annette Langer-Gould et al.Neurology, February 15, 2019