Ken Monahan1, Yanna Song2, Ken Loparo3, Reena Mehra4, Frank E Harrell2, Susan Redline5. 1. Division of Cardiovascular Medicine, Vanderbilt Medical Center, 1215 21st Avenue-5th Floor-Medical Center East, Nashville, TN, 37232, USA. ken.monahan@vanderbilt.edu. 2. Department of Biostatistics, Vanderbilt Medical Center, Nashville, TN, USA. 3. Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, OH, USA. 4. Division of Sleep Medicine, Cleveland Clinic Foundation, Cleveland, OH, USA. 5. Division of Sleep Medicine, Brigham and Women's Hospital, Boston, MA, USA.
Abstract
PURPOSE: Accurate identification of atrial fibrillation episodes from polysomnograms is important for research purposes but requires manual review of a large number of long electrocardiographic tracings. As automated assessment of these tracings for atrial fibrillation may improve efficiency, this study aimed to evaluate this approach in polysomnogram-derived electrocardiographic data. METHODS: A previously described algorithm to detect atrial fibrillation from single-lead electrocardiograms was applied to polysomnograms from a large epidemiologic study of obstructive sleep apnea in older men (Osteoporotic Fractures in Men [MrOS] Sleep Study). Atrial fibrillation status during each participant's PSG was determined by independent manual review. Models to predict atrial fibrillation status from a combination of algorithm output and clinical/polysomnographic characteristics were developed, and their accuracy was evaluated using standard statistical techniques. RESULTS: Derivation and validation cohorts each consisted of 1395 individuals; 5 % of each group had atrial fibrillation. Model parameters were optimized for the derivation cohort using the Akaike information criterion. Application to the validation cohort of these optimized models revealed high sensitivity (85-90 %) and specificity (90-95 %) as well as good predictive ability, as assessed by the C statistic (>0.9) and generalized R (2) values (∼0.6). Addition of cardiovascular or polysomnogram data to the models did not improve their performance. CONCLUSIONS: In a research setting, automated detection of atrial fibrillation from polysomnogram-derived electrocardiographic signals appears feasible and agrees well with manual identification. Future studies can evaluate the utility of this technique as applied to clinical polysomnograms and ambulatory electrocardiographic monitoring.
PURPOSE: Accurate identification of atrial fibrillation episodes from polysomnograms is important for research purposes but requires manual review of a large number of long electrocardiographic tracings. As automated assessment of these tracings for atrial fibrillation may improve efficiency, this study aimed to evaluate this approach in polysomnogram-derived electrocardiographic data. METHODS: A previously described algorithm to detect atrial fibrillation from single-lead electrocardiograms was applied to polysomnograms from a large epidemiologic study of obstructive sleep apnea in older men (Osteoporotic Fractures in Men [MrOS] Sleep Study). Atrial fibrillation status during each participant's PSG was determined by independent manual review. Models to predict atrial fibrillation status from a combination of algorithm output and clinical/polysomnographic characteristics were developed, and their accuracy was evaluated using standard statistical techniques. RESULTS: Derivation and validation cohorts each consisted of 1395 individuals; 5 % of each group had atrial fibrillation. Model parameters were optimized for the derivation cohort using the Akaike information criterion. Application to the validation cohort of these optimized models revealed high sensitivity (85-90 %) and specificity (90-95 %) as well as good predictive ability, as assessed by the C statistic (>0.9) and generalized R (2) values (∼0.6). Addition of cardiovascular or polysomnogram data to the models did not improve their performance. CONCLUSIONS: In a research setting, automated detection of atrial fibrillation from polysomnogram-derived electrocardiographic signals appears feasible and agrees well with manual identification. Future studies can evaluate the utility of this technique as applied to clinical polysomnograms and ambulatory electrocardiographic monitoring.
Authors: Virend K Somers; David P White; Raouf Amin; William T Abraham; Fernando Costa; Antonio Culebras; Stephen Daniels; John S Floras; Carl E Hunt; Lyle J Olson; Thomas G Pickering; Richard Russell; Mary Woo; Terry Young Journal: J Am Coll Cardiol Date: 2008-08-19 Impact factor: 24.094
Authors: Eric Orwoll; Janet Babich Blank; Elizabeth Barrett-Connor; Jane Cauley; Steven Cummings; Kristine Ensrud; Cora Lewis; Peggy M Cawthon; Robert Marcus; Lynn M Marshall; Joan McGowan; Kathy Phipps; Sherry Sherman; Marcia L Stefanick; Katie Stone Journal: Contemp Clin Trials Date: 2005-10 Impact factor: 2.226
Authors: Ken Monahan; Amy Storfer-Isser; Reena Mehra; Eyal Shahar; Murray Mittleman; Jeff Rottman; Naresh Punjabi; Mark Sanders; Stuart F Quan; Helaine Resnick; Susan Redline Journal: J Am Coll Cardiol Date: 2009-11-03 Impact factor: 24.094
Authors: Reena Mehra; Katie L Stone; Paul D Varosy; Andrew R Hoffman; Gregory M Marcus; Terri Blackwell; Osama A Ibrahim; Rawan Salem; Susan Redline Journal: Arch Intern Med Date: 2009-06-22