Jorne Laton1, Jeroen Van Schependom2, Jeroen Gielen3, Jeroen Decoster4, Tim Moons5, Jacques De Keyser6, Marc De Hert7, Guy Nagels8. 1. Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Laarbeeklaan 101, 1090 Brussel, Belgium. Electronic address: Jorne.Laton@vub.ac.be. 2. Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Laarbeeklaan 101, 1090 Brussel, Belgium; Faculté de Psychologie et des Sciences de l'Education, Université de Mons, Place du Parc 20, 7000 Mons, Belgium. Electronic address: Jeroen.Van.Schependom@vub.ac.be. 3. Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Laarbeeklaan 101, 1090 Brussel, Belgium. Electronic address: Jeroen.Gielen@vub.ac.be. 4. UPC KU Leuven - Campus Kortenberg, Department of Neurosciences, KU Leuven, Leuvensesteenweg 517, 3070 Kortenberg, Belgium. Electronic address: Jeroen.Decoster@uzleuven.be. 5. UPC KU Leuven - Campus Kortenberg, Department of Neurosciences, KU Leuven, Leuvensesteenweg 517, 3070 Kortenberg, Belgium. Electronic address: Tim.Moons@opzgeel.be. 6. Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Laarbeeklaan 101, 1090 Brussel, Belgium. Electronic address: Jacques.DeKeyser@uzbrussel.be. 7. UPC KU Leuven - Campus Kortenberg, Department of Neurosciences, KU Leuven, Leuvensesteenweg 517, 3070 Kortenberg, Belgium. Electronic address: Marc.De.Hert@uc-kortenberg.be. 8. Center for Neurosciences, UZ Brussel, Vrije Universiteit Brussel, Laarbeeklaan 101, 1090 Brussel, Belgium; Faculté de Psychologie et des Sciences de l'Education, Université de Mons, Place du Parc 20, 7000 Mons, Belgium; UPC KU Leuven - Campus Kortenberg, Department of Neurosciences, KU Leuven, Leuvensesteenweg 517, 3070 Kortenberg, Belgium; National MS Center Melsbroek, Vanheylenstraat 16, 1820 Melsbroek, Belgium. Electronic address: Guy.Nagels@vub.ac.be.
Abstract
OBJECTIVE: The diagnostic process for schizophrenia is mainly clinical and has to be performed by an experienced psychiatrist, relying primarily on clinical signs and symptoms. Current neurophysiological measurements can distinguish groups of healthy controls and groups of schizophrenia patients. Individual classification based on neurophysiological measurements mostly shows moderate accuracy. We wanted to examine whether it is possible to distinguish controls and patients individually with a good accuracy. To this end we used a combination of features extracted from the auditory and visual P300 paradigms and the mismatch negativity paradigm. METHODS: We selected 54 patients and 54 controls, matched for age and gender, from the data available at the UPC Kortenberg. The EEG-data were high- and low-pass filtered, epoched and averaged. Features (latencies and amplitudes of component peaks) were extracted from the averaged signals. The resulting dataset was used to train and test classification algorithms. First on separate paradigms and then on all combinations, we applied Naïve Bayes, Support Vector Machine and Decision Tree, with two of its improvements: Adaboost and Random Forest. RESULTS: For at least two classifiers the performance increased significantly by combining paradigms compared to single paradigms. The classification accuracy increased from at best 79.8% when trained on features from single paradigms, to 84.7% when trained on features from all three paradigms. CONCLUSION: A combination of features originating from three evoked potential paradigms allowed us to accurately classify individual subjects as either control or patient. Classification accuracy was mostly above 80% for the machine learners evaluated in this study and close to 85% at best.
OBJECTIVE: The diagnostic process for schizophrenia is mainly clinical and has to be performed by an experienced psychiatrist, relying primarily on clinical signs and symptoms. Current neurophysiological measurements can distinguish groups of healthy controls and groups of schizophreniapatients. Individual classification based on neurophysiological measurements mostly shows moderate accuracy. We wanted to examine whether it is possible to distinguish controls and patients individually with a good accuracy. To this end we used a combination of features extracted from the auditory and visual P300 paradigms and the mismatch negativity paradigm. METHODS: We selected 54 patients and 54 controls, matched for age and gender, from the data available at the UPC Kortenberg. The EEG-data were high- and low-pass filtered, epoched and averaged. Features (latencies and amplitudes of component peaks) were extracted from the averaged signals. The resulting dataset was used to train and test classification algorithms. First on separate paradigms and then on all combinations, we applied Naïve Bayes, Support Vector Machine and Decision Tree, with two of its improvements: Adaboost and Random Forest. RESULTS: For at least two classifiers the performance increased significantly by combining paradigms compared to single paradigms. The classification accuracy increased from at best 79.8% when trained on features from single paradigms, to 84.7% when trained on features from all three paradigms. CONCLUSION: A combination of features originating from three evoked potential paradigms allowed us to accurately classify individual subjects as either control or patient. Classification accuracy was mostly above 80% for the machine learners evaluated in this study and close to 85% at best.
Authors: Michael Avissar; Shanghong Xie; Blair Vail; Javier Lopez-Calderon; Yuanjia Wang; Daniel C Javitt Journal: Schizophr Res Date: 2017-07-11 Impact factor: 4.939
Authors: Delphine Van Laethem; Frederik Van de Steen; Daphne Kos; Maarten Naeyaert; Peter Van Schuerbeek; Miguel D'Haeseleer; Marie B D'Hooghe; Jeroen Van Schependom; Guy Nagels Journal: Trials Date: 2022-09-14 Impact factor: 2.728
Authors: Joel Weijia Lai; Candice Ke En Ang; U Rajendra Acharya; Kang Hao Cheong Journal: Int J Environ Res Public Health Date: 2021-06-05 Impact factor: 3.390