Mohammad M Ghassemi1, Edilberto Amorim2,3, Tuka Alhanai1, Jong W Lee4, Susan T Herman5, Adithya Sivaraju6, Nicolas Gaspard7, Lawrence J Hirsch6, Benjamin M Scirica8, Siddharth Biswal9, Valdery Moura Junior2, Sydney S Cash2, Emery N Brown10,11, Roger G Mark1,12, M Brandon Westover2. 1. Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA. 2. Department of Neurology, Massachusetts General Hospital, Boston, MA. 3. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA. 4. Department of Neurology, Brigham and Women's Hospital, Boston, MA. 5. Department of Neurology, Beth Israel Deaconess Medical Center, Boston, MA. 6. Department of Neurology, Yale School of Medicine, New Haven, CT. 7. Department of Neurology, Universite Libre de Bruxelles, Brussels, Belgium. 8. Division of Cardiology, Department of Medicine, Brigham and Women's Hospital, Boston, MA. 9. School of Computer Science, Georgia Institute of Technology, Atlanta, GA. 10. Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, MA. 11. Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA. 12. Information Systems, Beth Israel Deaconess Medical Center, Boston, MA.
Abstract
OBJECTIVES: Electroencephalogram features predict neurologic recovery following cardiac arrest. Recent work has shown that prognostic implications of some key electroencephalogram features change over time. We explore whether time dependence exists for an expanded selection of quantitative electroencephalogram features and whether accounting for this time dependence enables better prognostic predictions. DESIGN: Retrospective. SETTING: ICUs at four academic medical centers in the United States. PATIENTS: Comatose patients with acute hypoxic-ischemic encephalopathy. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We analyzed 12,397 hours of electroencephalogram from 438 subjects. From the electroencephalogram, we extracted 52 features that quantify signal complexity, category, and connectivity. We modeled associations between dichotomized neurologic outcome (good vs poor) and quantitative electroencephalogram features in 12-hour intervals using sequential logistic regression with Elastic Net regularization. We compared a predictive model using time-varying features to a model using time-invariant features and to models based on two prior published approaches. Models were evaluated for their ability to predict binary outcomes using area under the receiver operator curve, model calibration (how closely the predicted probability of good outcomes matches the observed proportion of good outcomes), and sensitivity at several common specificity thresholds of interest. A model using time-dependent features outperformed (area under the receiver operator curve, 0.83 ± 0.08) one trained with time-invariant features (0.79 ± 0.07; p < 0.05) and a random forest approach (0.74 ± 0.13; p < 0.05). The time-sensitive model was also the best-calibrated. CONCLUSIONS: The statistical association between quantitative electroencephalogram features and neurologic outcome changed over time, and accounting for these changes improved prognostication performance.
OBJECTIVES: Electroencephalogram features predict neurologic recovery following cardiac arrest. Recent work has shown that prognostic implications of some key electroencephalogram features change over time. We explore whether time dependence exists for an expanded selection of quantitative electroencephalogram features and whether accounting for this time dependence enables better prognostic predictions. DESIGN: Retrospective. SETTING: ICUs at four academic medical centers in the United States. PATIENTS: Comatosepatients with acute hypoxic-ischemic encephalopathy. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We analyzed 12,397 hours of electroencephalogram from 438 subjects. From the electroencephalogram, we extracted 52 features that quantify signal complexity, category, and connectivity. We modeled associations between dichotomized neurologic outcome (good vs poor) and quantitative electroencephalogram features in 12-hour intervals using sequential logistic regression with Elastic Net regularization. We compared a predictive model using time-varying features to a model using time-invariant features and to models based on two prior published approaches. Models were evaluated for their ability to predict binary outcomes using area under the receiver operator curve, model calibration (how closely the predicted probability of good outcomes matches the observed proportion of good outcomes), and sensitivity at several common specificity thresholds of interest. A model using time-dependent features outperformed (area under the receiver operator curve, 0.83 ± 0.08) one trained with time-invariant features (0.79 ± 0.07; p < 0.05) and a random forest approach (0.74 ± 0.13; p < 0.05). The time-sensitive model was also the best-calibrated. CONCLUSIONS: The statistical association between quantitative electroencephalogram features and neurologic outcome changed over time, and accounting for these changes improved prognostication performance.
Authors: Miikka Ermes; Mika Särkelä; Mark van Gils; Johanna Wennervirta; Anne Vakkuri; Tapani Salmi Journal: Annu Int Conf IEEE Eng Med Biol Soc Date: 2007
Authors: Wei-Long Zheng; Edilberto Amorim; Jin Jing; Ona Wu; Mohammad Ghassemi; Jong Woo Lee; Adithya Sivaraju; Trudy Pang; Susan T Herman; Nicolas Gaspard; Barry J Ruijter; Marleen C Tjepkema-Cloostermans; Jeannette Hofmeijer; Michel J A M van Putten; M Brandon Westover Journal: IEEE Trans Biomed Eng Date: 2022-04-21 Impact factor: 4.756
Authors: Wei-Long Zheng; Edilberto Amorim; Jin Jing; Wendong Ge; Shenda Hong; Ona Wu; Mohammad Ghassemi; Jong Woo Lee; Adithya Sivaraju; Trudy Pang; Susan T Herman; Nicolas Gaspard; Barry J Ruijter; Jimeng Sun; Marleen C Tjepkema-Cloostermans; Jeannette Hofmeijer; Michel J A M van Putten; M Brandon Westover Journal: Resuscitation Date: 2021-10-24 Impact factor: 5.262
Authors: Zubeda Sheikh; Olga Selioutski; Olga Taraschenko; Emily J Gilmore; M Brandon Westover; Adam B Cohen Journal: J Clin Neurophysiol Date: 2022-01-20 Impact factor: 2.590