Devin L Brown1, Kevin He2, Sehee Kim2, Chia-Wei Hsu3, Erin Case4, Ronald D Chervin5, Lynda D Lisabeth4. 1. Stroke Program, University of Michigan, United States. Electronic address: devinb@umich.edu. 2. Department of Biostatistics, School of Public Health, University of Michigan, United States. 3. Department of Epidemiology, School of Public Health, University of Michigan, United States. 4. Stroke Program, University of Michigan, United States; Department of Epidemiology, School of Public Health, University of Michigan, United States. 5. Sleep Disorders Center and Department of Neurology, University of Michigan, United States.
Abstract
OBJECTIVE/ BACKGROUND: Sleep-disordered breathing (SDB) is highly prevalent after stroke and is associated with poor outcomes. Currently, after stroke, objective testing must be used to differentiate patients with and without SDB. Within a large, population-based study, we evaluated the usefulness of a flexible statistical model based on baseline characteristics to predict post-stroke SDB. PATIENTS/ METHODS: Within a population-based study, participants (2010-2018) underwent SDB screening, shortly after ischemic stroke, with a home sleep apnea test. The respiratory event index (REI) was calculated as the number of apneas and hypopneas per hour of recording; values ≥10 defined SDB. The distributed random forest classifier (a machine learning technique) was applied to predict SDB with the following as predictors: demographics, stroke risk factors, stroke severity (NIHSS), neck and waist circumference, palate position, and pre-stroke symptoms of snoring, apneas, and sleepiness. RESULTS: Within the total sample (n = 1330), median age was 65 years; 47% were women; 32% non-Hispanic white, 62% Mexican American, and 6% African American. SDB was found in 891 (67%). The area under the receiver operating characteristic curve, a measure of predictive ability, applied to the validation sample was 0.75 for the random forest model. Random forest correctly classified 72.5% of validation samples. CONCLUSIONS: In this large, ethnically diverse, population-based sample of ischemic stroke patients, prediction models based on baseline characteristics and clinical measures showed fair rather than clinically reliable performance, even with use of advanced machine learning techniques. Results suggest that objective tests are still needed to differentiate ischemic stroke patients with and without SDB.
OBJECTIVE/ BACKGROUND:Sleep-disordered breathing (SDB) is highly prevalent after stroke and is associated with poor outcomes. Currently, after stroke, objective testing must be used to differentiate patients with and without SDB. Within a large, population-based study, we evaluated the usefulness of a flexible statistical model based on baseline characteristics to predict post-stroke SDB. PATIENTS/ METHODS: Within a population-based study, participants (2010-2018) underwent SDB screening, shortly after ischemic stroke, with a home sleep apnea test. The respiratory event index (REI) was calculated as the number of apneas and hypopneas per hour of recording; values ≥10 defined SDB. The distributed random forest classifier (a machine learning technique) was applied to predict SDB with the following as predictors: demographics, stroke risk factors, stroke severity (NIHSS), neck and waist circumference, palate position, and pre-stroke symptoms of snoring, apneas, and sleepiness. RESULTS: Within the total sample (n = 1330), median age was 65 years; 47% were women; 32% non-Hispanic white, 62% Mexican American, and 6% African American. SDB was found in 891 (67%). The area under the receiver operating characteristic curve, a measure of predictive ability, applied to the validation sample was 0.75 for the random forest model. Random forest correctly classified 72.5% of validation samples. CONCLUSIONS: In this large, ethnically diverse, population-based sample of ischemic strokepatients, prediction models based on baseline characteristics and clinical measures showed fair rather than clinically reliable performance, even with use of advanced machine learning techniques. Results suggest that objective tests are still needed to differentiate ischemic strokepatients with and without SDB.
Authors: Michael T Saletu; Stefan T Kotzian; Angela Schwarzinger; Sandra Haider; Josef Spatt; Bernd Saletu Journal: J Clin Sleep Med Date: 2018-09-15 Impact factor: 4.062
Authors: O Parra; A Arboix; S Bechich; L García-Eroles; J M Montserrat; J A López; E Ballester; J M Guerra; J J Sopeña Journal: Am J Respir Crit Care Med Date: 2000-02 Impact factor: 21.405
Authors: Jason J Sico; H Klar Yaggi; Susan Ofner; John Concato; Charles Austin; Jared Ferguson; Li Qin; Lauren Tobias; Stanley Taylor; Carlos A Vaz Fragoso; Vincent McLain; Linda S Williams; Dawn M Bravata Journal: J Stroke Cerebrovasc Dis Date: 2017-04-14 Impact factor: 2.136
Authors: Seong Hwan Ahn; Jin Ho Kim; Dong Uk Kim; In Seong Choo; Hyun Jin Lee; Hoo Won Kim Journal: J Clin Neurol Date: 2013-01-03 Impact factor: 3.077
Authors: Oleg Y Chernyshev; David E McCarty; Douglas E Moul; Cesar Liendo; Gloria C Caldito; Sai K Munjampalli; Roger E Kelley; Andrew L Chesson Journal: Nat Sci Sleep Date: 2015-10-20