Bharati Prasad1,2, Chirag Agarwal3, Elan Schonfeld3, Dan Schonfeld3, Babak Mokhlesi4. 1. Department of Medicine, University of Illinois at Chicago, Chicago, Illinois. 2. Jesse Brown VA Medical Center, Chicago, Illinois. 3. Department of Electrical and Computer Engineering, University of Illinois at Chicago, Chicago, Illinois. 4. Section of Pulmonary and Critical Care, Sleep Disorders Center, University of Chicago, Chicago, Illinois.
Abstract
STUDY OBJECTIVES: Nocturnal blood pressure (BP) profile shows characteristic abnormalities in OSA, namely acute postapnea BP surges and nondipping BP. These abnormal BP profiles provide prognostic clues indicating increased cardiovascular disease risk. We developed a deep neural network model to perform computerized analysis of polysomnography data and predict nocturnal BP profile. METHODS: We analyzed concurrently performed polysomnography and noninvasive beat-to-beat BP measurement with a deep neural network model to predict nocturnal BP profiles from polysomnography data in 13 patients with severe OSA. RESULTS: A good correlation was noted between measured and predicted postapnea systolic and diastolic BP (Pearson r ≥ .75). Moreover, Bland-Altman analyses showed good agreement between the 2 values. Continuous systolic and diastolic BP prediction by the deep neural network model was also well correlated with measured BP values (Pearson r ≥ .83). CONCLUSIONS: We developed a deep neural network model to predict nocturnal BP profile from clinical polysomnography signals and provide a potential prognostic tool in OSA. Validation of the model in larger samples and examination of its utility in predicting CVD risk in future studies is warranted.
STUDY OBJECTIVES: Nocturnal blood pressure (BP) profile shows characteristic abnormalities in OSA, namely acute postapnea BP surges and nondipping BP. These abnormal BP profiles provide prognostic clues indicating increased cardiovascular disease risk. We developed a deep neural network model to perform computerized analysis of polysomnography data and predict nocturnal BP profile. METHODS: We analyzed concurrently performed polysomnography and noninvasive beat-to-beat BP measurement with a deep neural network model to predict nocturnal BP profiles from polysomnography data in 13 patients with severe OSA. RESULTS: A good correlation was noted between measured and predicted postapnea systolic and diastolic BP (Pearson r ≥ .75). Moreover, Bland-Altman analyses showed good agreement between the 2 values. Continuous systolic and diastolic BP prediction by the deep neural network model was also well correlated with measured BP values (Pearson r ≥ .83). CONCLUSIONS: We developed a deep neural network model to predict nocturnal BP profile from clinical polysomnography signals and provide a potential prognostic tool in OSA. Validation of the model in larger samples and examination of its utility in predicting CVD risk in future studies is warranted.
Authors: Fadi Seif; Sanjay R Patel; Harneet K Walia; Michael Rueschman; Deepak L Bhatt; Roger S Blumenthal; Stuart F Quan; Daniel J Gottlieb; Eldrin F Lewis; Susheel P Patil; Naresh M Punjabi; Denise C Babineau; Susan Redline; Reena Mehra Journal: J Hypertens Date: 2014-02 Impact factor: 4.844
Authors: Miguel-Angel Martínez-García; Francisco Capote; Francisco Campos-Rodríguez; Patricia Lloberes; María Josefa Díaz de Atauri; María Somoza; Juan F Masa; Mónica González; Lirios Sacristán; Ferrán Barbé; Joaquín Durán-Cantolla; Felipe Aizpuru; Eva Mañas; Bienvenido Barreiro; Mar Mosteiro; Juan J Cebrián; Mónica de la Peña; Francisco García-Río; Andrés Maimó; Jordi Zapater; Concepción Hernández; Nuria Grau SanMarti; Josep María Montserrat Journal: JAMA Date: 2013-12-11 Impact factor: 56.272
Authors: R Doug McEvoy; Nick A Antic; Emma Heeley; Yuanming Luo; Qiong Ou; Xilong Zhang; Olga Mediano; Rui Chen; Luciano F Drager; Zhihong Liu; Guofang Chen; Baoliang Du; Nigel McArdle; Sutapa Mukherjee; Manjari Tripathi; Laurent Billot; Qiang Li; Geraldo Lorenzi-Filho; Ferran Barbe; Susan Redline; Jiguang Wang; Hisatomi Arima; Bruce Neal; David P White; Ron R Grunstein; Nanshan Zhong; Craig S Anderson Journal: N Engl J Med Date: 2016-08-28 Impact factor: 91.245
Authors: Babak Mokhlesi; Erika W Hagen; Laurel A Finn; Khin Mae Hla; Jason R Carter; Paul E Peppard Journal: Thorax Date: 2015-08-25 Impact factor: 9.139
Authors: Jason R Carter; Ida T Fonkoue; Daniela Grimaldi; Leila Emami; David Gozal; Colin E Sullivan; Babak Mokhlesi Journal: Am J Physiol Regul Integr Comp Physiol Date: 2016-01-27 Impact factor: 3.619