A Machine Learning Approach Involving Functional Connectivity Features to Classify Rest-EEG Psychogenic Non-Epileptic Seizures from Healthy Controls
Until now, clinicians are not able to evaluate the Psychogenic Non-Epileptic Seizures (PNES) from the rest-electroencephalography (EEG) readout. No EEG marker can help differentiate PNES cases from healthy subjects. In this paper, we have investigated the power spectrum density (PSD), in resting-sta...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/1/129 |
| _version_ | 1827667652844191744 |
|---|---|
| author | Giuseppe Varone Wadii Boulila Michele Lo Giudice Bilel Benjdira Nadia Mammone Cosimo Ieracitano Kia Dashtipour Sabrina Neri Sara Gasparini Francesco Carlo Morabito Amir Hussain Umberto Aguglia |
| author_facet | Giuseppe Varone Wadii Boulila Michele Lo Giudice Bilel Benjdira Nadia Mammone Cosimo Ieracitano Kia Dashtipour Sabrina Neri Sara Gasparini Francesco Carlo Morabito Amir Hussain Umberto Aguglia |
| author_sort | Giuseppe Varone |
| collection | DOAJ |
| description | Until now, clinicians are not able to evaluate the Psychogenic Non-Epileptic Seizures (PNES) from the rest-electroencephalography (EEG) readout. No EEG marker can help differentiate PNES cases from healthy subjects. In this paper, we have investigated the power spectrum density (PSD), in resting-state EEGs, to evaluate the abnormalities in PNES affected brains. Additionally, we have used functional connectivity tools, such as phase lag index (PLI), and graph-derived metrics to better observe the integration of distributed information of regular and synchronized multi-scale communication within and across inter-regional brain areas. We proved the utility of our method after enrolling a cohort study of 20 age- and gender-matched PNES and 19 healthy control (HC) subjects. In this work, three classification models, namely support vector machine (SVM), linear discriminant analysis (LDA), and Multilayer perceptron (MLP), have been employed to model the relationship between the functional connectivity features (rest-HC versus rest-PNES). The best performance for the discrimination of participants was obtained using the MLP classifier, reporting a precision of 85.73%, a recall of 86.57%, an F1-score of 78.98%, and, finally, an accuracy of 91.02%. In conclusion, our results hypothesized two main aspects. The first is an intrinsic organization of functional brain networks that reflects a dysfunctional level of integration across brain regions, which can provide new insights into the pathophysiological mechanisms of PNES. The second is that functional connectivity features and MLP could be a promising method to classify rest-EEG data of PNES form healthy controls subjects. |
| first_indexed | 2024-03-10T03:22:18Z |
| format | Article |
| id | doaj.art-9e05250a80ef4a33860e227c649e8d32 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:22:18Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9e05250a80ef4a33860e227c649e8d322023-11-23T12:17:23ZengMDPI AGSensors1424-82202021-12-0122112910.3390/s22010129A Machine Learning Approach Involving Functional Connectivity Features to Classify Rest-EEG Psychogenic Non-Epileptic Seizures from Healthy ControlsGiuseppe Varone0Wadii Boulila1Michele Lo Giudice2Bilel Benjdira3Nadia Mammone4Cosimo Ieracitano5Kia Dashtipour6Sabrina Neri7Sara Gasparini8Francesco Carlo Morabito9Amir Hussain10Umberto Aguglia11Department of Neuroscience and Imaging, University G. d’Annunzio Chieti e Pescara, 66100 Chieti, ItalyRobotics and Internet-of-Things Laboratory, Prince Sultan University, Riyadh 12435, Saudi ArabiaDepartment of Science Medical and Surgery, University of Catanzaro, 88100 Catanzaro, ItalyRobotics and Internet-of-Things Laboratory, Prince Sultan University, Riyadh 12435, Saudi ArabiaDICEAM Department, University “Mediterranea” of Reggio Calabria, 89100 Reggio Calabria, ItalyDICEAM Department, University “Mediterranea” of Reggio Calabria, 89100 Reggio Calabria, ItalySchool of Computing, Edinburgh Napier University, Edinburgh EH11 4BN, UKDepartment of Science Medical and Surgery, University of Catanzaro, 88100 Catanzaro, ItalyDepartment of Science Medical and Surgery, University of Catanzaro, 88100 Catanzaro, ItalyDICEAM Department, University “Mediterranea” of Reggio Calabria, 89100 Reggio Calabria, ItalySchool of Computing, Edinburgh Napier University, Edinburgh EH11 4BN, UKDepartment of Science Medical and Surgery, University of Catanzaro, 88100 Catanzaro, ItalyUntil now, clinicians are not able to evaluate the Psychogenic Non-Epileptic Seizures (PNES) from the rest-electroencephalography (EEG) readout. No EEG marker can help differentiate PNES cases from healthy subjects. In this paper, we have investigated the power spectrum density (PSD), in resting-state EEGs, to evaluate the abnormalities in PNES affected brains. Additionally, we have used functional connectivity tools, such as phase lag index (PLI), and graph-derived metrics to better observe the integration of distributed information of regular and synchronized multi-scale communication within and across inter-regional brain areas. We proved the utility of our method after enrolling a cohort study of 20 age- and gender-matched PNES and 19 healthy control (HC) subjects. In this work, three classification models, namely support vector machine (SVM), linear discriminant analysis (LDA), and Multilayer perceptron (MLP), have been employed to model the relationship between the functional connectivity features (rest-HC versus rest-PNES). The best performance for the discrimination of participants was obtained using the MLP classifier, reporting a precision of 85.73%, a recall of 86.57%, an F1-score of 78.98%, and, finally, an accuracy of 91.02%. In conclusion, our results hypothesized two main aspects. The first is an intrinsic organization of functional brain networks that reflects a dysfunctional level of integration across brain regions, which can provide new insights into the pathophysiological mechanisms of PNES. The second is that functional connectivity features and MLP could be a promising method to classify rest-EEG data of PNES form healthy controls subjects.https://www.mdpi.com/1424-8220/22/1/129psychogenic non-epileptic seizurespower spectral densityphase lag indexrest-machine learning-based diagnosisEEG-based machine learning techniques for PNES |
| spellingShingle | Giuseppe Varone Wadii Boulila Michele Lo Giudice Bilel Benjdira Nadia Mammone Cosimo Ieracitano Kia Dashtipour Sabrina Neri Sara Gasparini Francesco Carlo Morabito Amir Hussain Umberto Aguglia A Machine Learning Approach Involving Functional Connectivity Features to Classify Rest-EEG Psychogenic Non-Epileptic Seizures from Healthy Controls Sensors psychogenic non-epileptic seizures power spectral density phase lag index rest-machine learning-based diagnosis EEG-based machine learning techniques for PNES |
| title | A Machine Learning Approach Involving Functional Connectivity Features to Classify Rest-EEG Psychogenic Non-Epileptic Seizures from Healthy Controls |
| title_full | A Machine Learning Approach Involving Functional Connectivity Features to Classify Rest-EEG Psychogenic Non-Epileptic Seizures from Healthy Controls |
| title_fullStr | A Machine Learning Approach Involving Functional Connectivity Features to Classify Rest-EEG Psychogenic Non-Epileptic Seizures from Healthy Controls |
| title_full_unstemmed | A Machine Learning Approach Involving Functional Connectivity Features to Classify Rest-EEG Psychogenic Non-Epileptic Seizures from Healthy Controls |
| title_short | A Machine Learning Approach Involving Functional Connectivity Features to Classify Rest-EEG Psychogenic Non-Epileptic Seizures from Healthy Controls |
| title_sort | machine learning approach involving functional connectivity features to classify rest eeg psychogenic non epileptic seizures from healthy controls |
| topic | psychogenic non-epileptic seizures power spectral density phase lag index rest-machine learning-based diagnosis EEG-based machine learning techniques for PNES |
| url | https://www.mdpi.com/1424-8220/22/1/129 |
| work_keys_str_mv | AT giuseppevarone amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT wadiiboulila amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT michelelogiudice amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT bilelbenjdira amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT nadiamammone amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT cosimoieracitano amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT kiadashtipour amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT sabrinaneri amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT saragasparini amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT francescocarlomorabito amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT amirhussain amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT umbertoaguglia amachinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT giuseppevarone machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT wadiiboulila machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT michelelogiudice machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT bilelbenjdira machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT nadiamammone machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT cosimoieracitano machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT kiadashtipour machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT sabrinaneri machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT saragasparini machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT francescocarlomorabito machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT amirhussain machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols AT umbertoaguglia machinelearningapproachinvolvingfunctionalconnectivityfeaturestoclassifyresteegpsychogenicnonepilepticseizuresfromhealthycontrols |