Detection and Estimation of Schizophrenia Severity from Acoustic Features with Inclusion of K-means as Voice Activity Detection Function

Sheriff Alimi, Afolashade Oluwakemi Kuyoro, Monday Okpoto Eze, Oyebola Akande

Abstract


Schizophrenia symptom severity estimation provides quantitative information that is useful at both the detection and treatment stages of the mental disorder, as the information helps in decision-making and improves the management of the illness. Very limited studies have been recorded for estimating the symptom severity as a regression task with machine learning, especially from speech recordings, which is the aim of this study coupled with detection. Acoustic features, which comprise frequency-domain and time-domain features, were extracted from 60 schizophrenia subjects and 59 healthy controls enrolled in this research. The acoustic features were used to train GridSearchCV-optimized XGBoost as a classifier. Three Multi-Layer Perceptron (MLP) networks, hyper-parameter-tuned by Bayesian Optimizer, were trained to predict the sub-type symptom severity from acoustic extracted features from the schizophrenia groups. The XGBoost classification model that discriminates between schizophrenia and healthy groups achieved a classification accuracy of 98.6%. The three MLP regression models yielded Mean Absolute Errors of 1.975, 2.856, and 1.555, as well as correlation coefficients of 0.888, 0.806, and 0.786 for predicting positive, negative, and cognitive symptom scores, respectively. Solution architecture for the deployment of the models for practical use was suggested

Keywords


Acoustic features; Enhanced K-means; Multi-layer Perceptron; Severity Estimation; Schizophrenia

References


A. Barbato, “Schizophrenia and public health,” WHO Nations Ment. Heal. Initiat. World Heal. Organ. Div. Ment. Heal. Prev. Subst. Abus., 1998, doi: 10.1016/s0924-9338(99)80120-5.

S. Grot et al., “Converting scores between the PANSS and SAPS/SANS beyond the positive/negative dichotomy,” Psychiatry Res., vol. 305, 2021, doi: 10.1016/j.psychres.2021.114199.

C. A. T. Naira and C. J. L. Del Alamo, “Classification of people who suffer schizophrenia and healthy people by EEG signals using deep learning,” Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 10, pp. 511–516, 2019, doi: 10.14569/ijacsa.2019.0101067.

Y. Yang et al., “Automatic classification of first-episode, drug-naive schizophrenia with multi-modal magnetic resonance imaging,” Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, vol. 34, no. 5, 2017, doi: 10.7507/1001-5515.201607084.

Z. Aslan and M. Akin, “Automatic detection of schizophrenia by applying deep learning over spectrogram images of EEG signals,” Trait. du Signal, vol. 37, no. 2, pp. 235–244, 2020, doi: 10.18280/ts.370209.

J. Fu et al., “Sch-net: a deep learning architecture for automatic detection of schizophrenia,” Biomed. Eng. Online, vol. 20, no. 1, 2021, doi: 10.1186/s12938-021-00915-2.

L. Shen, Q. Wang, and J. Shi, “Single-modal neuroimaging computer aided diagnosis for schizophrenia based on ensemble learning using privileged information,” Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, vol. 37, no. 3, 2020, doi: 10.7507/1001-5515.201905029.

J. Oh, B. L. Oh, K. U. Lee, J. H. Chae, and K. Yun, “Identifying Schizophrenia Using Structural MRI With a Deep Learning Algorithm,” Front. Psychiatry, vol. 11, Feb. 2020, doi: 10.3389/FPSYT.2020.00016.

S. Alimi, A. O. Kuyoro, M. O. Eze, and O. Akande, “Utilizing Deep Learning and SVM Models for Schizophrenia Detection and Symptom Severity Estimation Through Structural MRI,” Ingénierie des systèmes d Inf., vol. 28, no. 4, pp. 993–1002, Aug. 2023, doi: 10.18280/isi.280419.

J. Liu, X. Wang, X. Zhang, Y. Pan, X. Wang, and J. Wang, “MMM: classification of schizophrenia using multi-modality multi-atlas feature representation and multi-kernel learning,” Multimed. Tools Appl., vol. 77, no. 22, 2018, doi: 10.1007/s11042-017-5470-7.

D. W. Kim, S. H. Lee, M. Shim, and C. H. Im, “Estimation of symptom severity scores for patients with schizophrenia using ERP source activations during a facial affect discrimination task,” Front. Neurosci., vol. 11, no. AUG, pp. 1–6, 2017, doi: 10.3389/fnins.2017.00436.

J. N. de Boer et al., “Acoustic speech markers for schizophrenia-spectrum disorders: A diagnostic and symptom-recognition tool,” Psychol. Med., 2021, doi: 10.1017/S0033291721002804.

F. He, J. Fu, L. He, Y. Li, and X. Xiong, “Automatic Detection of Negative Symptoms in Schizophrenia via Acoustically Measured Features Associated with Affective Flattening,” IEEE Trans. Autom. Sci. Eng., vol. 18, no. 2, pp. 586–602, 2021, doi: 10.1109/TASE.2020.3022037.

J. de Boer, A. Voppel, F. Wijnen, and I. Sommer, “ACOUSTIC SPEECH MARKERS FOR SCHIZOPHRENIA...Schizophrenia International Research Society (SIRS) 2020 Congress.,” Schizophr. Bull., vol. 46, 2020.

D. Chakraborty et al., “Prediction of Negative Symptoms of Schizophrenia from Emotion Related Low-Level Speech Signals,” ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc., vol. 2018-April, pp. 6024–6028, 2018, doi: 10.1109/ICASSP.2018.8462102.

N. B. Mota, M. Copelli, and S. Ribeiro, “ARTICLE Thought disorder measured as random speech structure classifies negative symptoms and schizophrenia diagnosis 6 months in advance,” vol. 3, p. 18, 2017, doi: 10.1038/s41537-017-0019-3.

H. H. Stassen, M. Albers, J. Püschel, C. Scharfetter, M. Tewesmeier, and B. Woggon, “Speaking behavior and voice sound characteristics associated with negative schizophrenia,” J. Psychiatr. Res., vol. 29, no. 4, pp. 277–296, 1995, doi: 10.1016/0022-3956(95)00004-O.

Y. Tahir et al., “Non-verbal speech cues as objective measures for negative symptoms in patients with schizophrenia,” PLoS One, vol. 14, no. 4, pp. 1–17, 2019, doi: 10.1371/journal.pone.0214314.

J. Piischel, H. H. Stassen, G. Bomben, C. Scharfetter, and D. Hell, “J OURNALOF PSYCHIATRIC F & EAFL ~ H Speaking behavior and speech sound characteristics in acute schizophrenia,” Control, 1997.

D. W. Kim, S. H. Lee, M. Shim, and C. H. Im, “Estimation of symptom severity scores for patients with schizophrenia using ERP source activations during a facial affect discrimination task,” Front. Neurosci., vol. 11, no. AUG, 2017, doi: 10.3389/fnins.2017.00436.

G. Fant, Acoustic Theory of Speech Production: With Calculations based on X-Ray Studies of Russian Articulations. Berlin: Gruyter Mouton, 1971. [Online]. Available: ps://doi.org/10.1515/9783110873429

K. A. Binsaeed and A. M. Hafez, “Enhancing Intrusion Detection Systems with XGBoost Feature Selection and Deep Learning Approaches,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 5, 2023, doi: 10.14569/IJACSA.2023.01405112.

Z. Jiang, J. Che, M. He, and F. Yuan, “A CGRU multi-step wind speed forecasting model based on multi-label specific XGBoost feature selection and secondary decomposition,” Renew. Energy, vol. 203, 2023, doi: 10.1016/j.renene.2022.12.124.

S. S. Dhaliwal, A. Al Nahid, and R. Abbas, “Effective intrusion detection system using XGBoost,” Inf., vol. 9, no. 7, 2018, doi: 10.3390/info9070149.

B. Karan, “Speech-Based Parkinson’s Disease Prediction Using XGBoost-Based Features Selection and the Stacked Ensemble of Classifiers,” J. Inst. Eng. Ser. B, vol. 104, no. 2, 2023, doi: 10.1007/s40031-022-00851-2.

S. Kilmen and O. Bulut, “Scale Abbreviation with Recursive Feature Elimination and Genetic Algorithms: An Illustration with the Test Emotions Questionnaire,” Inf., vol. 14, no. 2, 2023, doi: 10.3390/info14020063.

S. Yang, W. Xiao, M. Zhang, S. Guo, J. Zhao, and F. Shen, “Image Data Augmentation for Deep Learning: A Survey,” 2022, [Online]. Available: http://arxiv.org/abs/2204.08610

F. Dubost et al., “Hydranet: Data augmentation for regression neural networks,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 11767 LNCS, no. January 2020, pp. 438–446, 2019, doi: 10.1007/978-3-030-32251-9_48.

N. Network, “Effects of Data Augmentation on the Nine-Axis IMU-Based,” Sensors, vol. 23, no. 17, 2023, doi: doi.org/10.3390/s23177458.

H. Ohno, “Auto-encoder-based generative models for data augmentation on regression problems,” Soft Comput., vol. 24, no. 11, pp. 7999–8009, 2020, doi: 10.1007/s00500-019-04094-0.

Y. El Khessaimi, Y. El Hafiane, A. Smith, and M. A. Barkatou, “The Effectiveness of Data Augmentation in Compressive Strength Prediction of Calcined Clay Cements Using Linear Regression Learning,” NanoWorld J., vol. 9, no. September, pp. 1–6, 2023, doi: 10.17756/nwj.2023-s2-054.

G. Iglesias, E. Talavera, Á. González-Prieto, A. Mozo, and S. Gómez-Canaval, “Data Augmentation techniques in time series domain: a survey and taxonomy,” Neural Comput. Appl., vol. 35, no. 14, pp. 10123–10145, 2023, doi: 10.1007/s00521-023-08459-3.

C. W. Espinola, J. C. Gomes, J. M. S. Pereira, and W. P. dos Santos, “Vocal acoustic analysis and machine learning for the identification of schizophrenia,” Res. Biomed. Eng., vol. 37, no. 1, pp. 33–46, 2021, doi: 10.1007/s42600-020-00097-1.

Y. J. Huang et al., “Assessing Schizophrenia Patients Through Linguistic and Acoustic Features Using Deep Learning Techniques,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 30. pp. 947–956, 2022. doi: 10.1109/TNSRE.2022.3163777.

J. Zhang, H. Yang, W. Li, Y. Li, J. Qin, and L. He, “Automatic Schizophrenia Detection Using Multimodality Media via a Text Reading Task,” Front. Neurosci., vol. 16, no. July, pp. 1–17, 2022, doi: 10.3389/fnins.2022.933049.


Full Text: PDF

Refbacks

  • There are currently no refbacks.


 

Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
ISSN 2089-3272

Creative Commons Licence

This work is licensed under a Creative Commons Attribution 4.0 International License.

web analytics
View IJEEI Stats