Issue Navigator

Volume 15 No. 01
Earn CME
Accepted Papers

Scientific Investigations

A Conditional Inference Tree Model for Predicting Sleep-Related Breathing Disorders in Patients With Chiari Malformation Type 1: Description and External Validation

Álex Ferré, MD1,2,3; María A. Poca, MD, PhD3,4; María Dolores de la Calzada, MD, PhD3; Dulce Moncho, MD, PhD1,3; Aintzane Urbizu, PhD5; Odile Romero, MD1,2,6; Gabriel Sampol, MD, PhD2,6,7; Juan Sahuquillo, MD, PhD3,4
1Clinical Neurophysiology Department, Vall d′Hebron University Hospital, Universitat Autónoma de Barcelona, Barcelona, Spain; 2Multidisciplinary Sleep Unit, Vall d′Hebron University Hospital, Universitat Autónoma de Barcelona, Barcelona, Spain; 3Neurotraumatology and Neurosurgery Research Unit (UNINN), Vall d′Hebron University Hospital, Barcelona, Spain; 4Neurosurgery Department, Vall d′Hebron University Hospital, Universitat Autónoma de Barcelona, Barcelona, Spain; 5Conquer Chiari Research Center, Department of Mechanical Engineering, The University of Akron, Ohio; 6Centro de Investigación Biomédica en Red Enfermedades Respiratorias (CIBERES), Instituto de la Salud Carlos III (ISCIIII), Madrid, Spain; 7Pneumology Department, Vall d′Hebron Research institute, Vall d′Hebron University Hospital, Universitat Autónoma de Barcelona, Barcelona, Spain

Study Objectives:

The aim of this study is to generate and validate supervised machine learning algorithms to detect patients with Chiari malformation (CM) 1 or 1.5 at high risk of the development of sleep-related breathing disorders (SRBD) using clinical and neuroradiological parameters.


We prospectively included two independent datasets. A training dataset (n = 90) was used to obtain the best model, whereas a second dataset was used to validate it (n = 74). In both cohorts, the same clinical, neuroradiological, and sleep studies were carried out. We used two supervised machine learning approaches, multiple logistic regression (MLR) and the unbiased recursive partitioning technique conditional inference tree (URP-CTREE), to detect patients at high risk of SRBD. We then compared the accuracy, sensitivity, and specificity of the two prediction models.


Age (odds ratio [OR] 1.1 95% confidence interval [CI] 1.05–1.17), sex (OR 0.19 95% CI 0.05–0.67), CM type (OR 4.36 95% CI 1.14–18.5), and clivus length (OR 1.14 95% CI 1.01–1.31) were the significant predictor variables for a respiratory disturbance index (RDI) cutoff that was ≥ 10 events/h using MLR. The URP-CTREE model predicted that patients with CM-1 who were age 52 years or older and males with CM-1 who were older than 29 years had a high risk of SRBD. The accuracy of predicting patients with an RDI ≥ 10 events/h was similar in the two cohorts but in the URP-CTREE model, specificity was significantly greater when compared to MLR in both study groups.


Both MLR and URP-CTREE predictive models are useful for the diagnosis of SRBD in patients with CM. However, URP-CTREE is easier to apply and interpret in clinical practice.


Ferré Á, Poca MA, de la Calzada MD, Moncho D, Urbizu A, Romero O, Sampol G, Sahuquillo J. A conditional inference tree model for predicting sleep-related breathing disorders in patients with chiari malformation type 1: description and external validation. J Clin Sleep Med. 2019;15(1):89–99.

Supplemental Material

Login to view supplemental material

Please login to continue reading the full article

Subscribers to JCSM get full access to current and past issues of the JCSM.

Login to JCSM

Not a subscriber?

Join the American Academy of Sleep Medicine and receive a subscription to JCSM with your membership

Subscribe to JCSM:  $75/volume year for individuals or $140/volume year for institutions to access all current articles and archives published in JCSM.

Download this article*:   $20 to access a PDF version of a specific article from the current issue of JCSM.

*Purchase of an electronic download of JCSM provides permission to access and print the issue/article for personal scholarly, research and educational use. Please note: access to the article is from the computer on which the article is purchased ONLY. Purchase of the article does not permit distribution, electronic or otherwise, of the article without the written permission of the AASM. Further, purchase does not permit the posting of article text on an online forum or website.