Automated extraction of speech and turn-taking parameters in autism allows for diagnostic classification using a multivariable prediction model
Autism spectrum disorder (ASD) is diagnosed on the basis of speech and communication differences, amongst other symptoms. Since conversations are essential for building connections with others, it is important to understand the exact nature of differences between autistic and non-autistic verbal beh...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-11-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1257569/full |
| _version_ | 1797635567284912128 |
|---|---|
| author | I. S. Plank J. C. Koehler A. M. Nelson N. Koutsouleris N. Koutsouleris N. Koutsouleris C. M. Falter-Wagner |
| author_facet | I. S. Plank J. C. Koehler A. M. Nelson N. Koutsouleris N. Koutsouleris N. Koutsouleris C. M. Falter-Wagner |
| author_sort | I. S. Plank |
| collection | DOAJ |
| description | Autism spectrum disorder (ASD) is diagnosed on the basis of speech and communication differences, amongst other symptoms. Since conversations are essential for building connections with others, it is important to understand the exact nature of differences between autistic and non-autistic verbal behaviour and evaluate the potential of these differences for diagnostics. In this study, we recorded dyadic conversations and used automated extraction of speech and interactional turn-taking features of 54 non-autistic and 26 autistic participants. The extracted speech and turn-taking parameters showed high potential as a diagnostic marker. A linear support vector machine was able to predict the dyad type with 76.2% balanced accuracy (sensitivity: 73.8%, specificity: 78.6%), suggesting that digitally assisted diagnostics could significantly enhance the current clinical diagnostic process due to their objectivity and scalability. In group comparisons on the individual and dyadic level, we found that autistic interaction partners talked slower and in a more monotonous manner than non-autistic interaction partners and that mixed dyads consisting of an autistic and a non-autistic participant had increased periods of silence, and the intensity, i.e. loudness, of their speech was more synchronous. |
| first_indexed | 2024-03-11T12:23:38Z |
| format | Article |
| id | doaj.art-45acf71158914a6c94260a9556ab1ba7 |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-03-11T12:23:38Z |
| publishDate | 2023-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-45acf71158914a6c94260a9556ab1ba72023-11-06T16:06:42ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402023-11-011410.3389/fpsyt.2023.12575691257569Automated extraction of speech and turn-taking parameters in autism allows for diagnostic classification using a multivariable prediction modelI. S. Plank0J. C. Koehler1A. M. Nelson2N. Koutsouleris3N. Koutsouleris4N. Koutsouleris5C. M. Falter-Wagner6Department of Psychiatry and Psychotherapy, LMU University Hospital, LMU Munich, Munich, GermanyDepartment of Psychiatry and Psychotherapy, LMU University Hospital, LMU Munich, Munich, GermanyDepartment of Psychiatry and Psychotherapy, LMU University Hospital, LMU Munich, Munich, GermanyDepartment of Psychiatry and Psychotherapy, LMU University Hospital, LMU Munich, Munich, GermanyMax Planck Institute of Psychiatry, Munich, GermanyInstitute of Psychiatry, Psychology and Neuroscience, King’s College, London, United KingdomDepartment of Psychiatry and Psychotherapy, LMU University Hospital, LMU Munich, Munich, GermanyAutism spectrum disorder (ASD) is diagnosed on the basis of speech and communication differences, amongst other symptoms. Since conversations are essential for building connections with others, it is important to understand the exact nature of differences between autistic and non-autistic verbal behaviour and evaluate the potential of these differences for diagnostics. In this study, we recorded dyadic conversations and used automated extraction of speech and interactional turn-taking features of 54 non-autistic and 26 autistic participants. The extracted speech and turn-taking parameters showed high potential as a diagnostic marker. A linear support vector machine was able to predict the dyad type with 76.2% balanced accuracy (sensitivity: 73.8%, specificity: 78.6%), suggesting that digitally assisted diagnostics could significantly enhance the current clinical diagnostic process due to their objectivity and scalability. In group comparisons on the individual and dyadic level, we found that autistic interaction partners talked slower and in a more monotonous manner than non-autistic interaction partners and that mixed dyads consisting of an autistic and a non-autistic participant had increased periods of silence, and the intensity, i.e. loudness, of their speech was more synchronous.https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1257569/fullspeechturn-takingdiagnostic classificationautismprediction modelconversation |
| spellingShingle | I. S. Plank J. C. Koehler A. M. Nelson N. Koutsouleris N. Koutsouleris N. Koutsouleris C. M. Falter-Wagner Automated extraction of speech and turn-taking parameters in autism allows for diagnostic classification using a multivariable prediction model Frontiers in Psychiatry speech turn-taking diagnostic classification autism prediction model conversation |
| title | Automated extraction of speech and turn-taking parameters in autism allows for diagnostic classification using a multivariable prediction model |
| title_full | Automated extraction of speech and turn-taking parameters in autism allows for diagnostic classification using a multivariable prediction model |
| title_fullStr | Automated extraction of speech and turn-taking parameters in autism allows for diagnostic classification using a multivariable prediction model |
| title_full_unstemmed | Automated extraction of speech and turn-taking parameters in autism allows for diagnostic classification using a multivariable prediction model |
| title_short | Automated extraction of speech and turn-taking parameters in autism allows for diagnostic classification using a multivariable prediction model |
| title_sort | automated extraction of speech and turn taking parameters in autism allows for diagnostic classification using a multivariable prediction model |
| topic | speech turn-taking diagnostic classification autism prediction model conversation |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1257569/full |
| work_keys_str_mv | AT isplank automatedextractionofspeechandturntakingparametersinautismallowsfordiagnosticclassificationusingamultivariablepredictionmodel AT jckoehler automatedextractionofspeechandturntakingparametersinautismallowsfordiagnosticclassificationusingamultivariablepredictionmodel AT amnelson automatedextractionofspeechandturntakingparametersinautismallowsfordiagnosticclassificationusingamultivariablepredictionmodel AT nkoutsouleris automatedextractionofspeechandturntakingparametersinautismallowsfordiagnosticclassificationusingamultivariablepredictionmodel AT nkoutsouleris automatedextractionofspeechandturntakingparametersinautismallowsfordiagnosticclassificationusingamultivariablepredictionmodel AT nkoutsouleris automatedextractionofspeechandturntakingparametersinautismallowsfordiagnosticclassificationusingamultivariablepredictionmodel AT cmfalterwagner automatedextractionofspeechandturntakingparametersinautismallowsfordiagnosticclassificationusingamultivariablepredictionmodel |