Screening Tools for Early Autism Detection using Voice and Gesture Analysis

Riffat Farrukh; Ahmad Bilal Ashraf; Akash Kumar; Shizma Junejo; Asma Mushtaq; Laiba Mushtaq

doi:10.70749/ijbr.v3i7.2649

Authors

Riffat Farrukh Department of Pediatrics, Abbasi Shaheed Hospital, Karachi, Sindh, Pakistan.
Ahmad Bilal Ashraf Allama Iqbal Medical College/Jinnah Hospital, Lahore, Punjab, Pakistan.
Akash Kumar Department of Surgery, Sandeman Provincial Hospital, Quetta, Balochistan, Pakistan.
Shizma Junejo Department of Pharmacology, Bahria University Health Sciences Campus Karachi, Sindh, Pakistan.
Asma Mushtaq Department of Gynae & Obs, St Richards Hospital, Chichester, England.
Laiba Mushtaq Sheikh Khalifa bin Zayed Al Nahyan Medical and Dental College, Lahore, Punjab, Pakistan.

DOI:

https://doi.org/10.70749/ijbr.v3i7.2649

Keywords:

Autism Spectrum Disorder (ASD), Early Detection, Voice Analysis, Gesture Analysis, Screening Tool, Machine Learning, Non-verbal Communication, Acoustic Biomarkers.

Abstract

Background: For maximizing outcomes of treatment, timely and precise condition analysis, and screening, are necessary. For example, using ASD Screening combines clinical and observational assessments. The objective of the study assessed the aim of Voice Automated Technology, and an objective multi- modality detection tool integrates gesture to analyze the phenomena of children. Methods: Eighty-two young children referred for developmental evaluation were included in this observational study and were separated into two groups, ASD (n=41) and non-ASD (n=41), according to the Modified Checklist for Autism in Toddlers (M-CHAT). Samples of the participants' voices were examined to measure dimensions of atypicality (total fundamental frequency, jitter, speech rate), while the processed, structured video recordings were analyzed with motion-tracking software to measure the frequencies of gesture expression, duration of mutual visual attention, and eye fixation, thus resulting in an overall score for gesture atypicality. Sensitivity, specificity, accuracy, and area under the curve (AUC) were employed in examining both the separate and the combined models. Results: Variations between the ASD and non-ASD populations were apparent regarding all parameters in the other acoustic and gesture parameters combined. The Combined Voice + Gesture Model achieved significantly higher performance (p<0.001) on its own than either modality and achieved an Accuracy of almost 85%, a Sensitivity of 87.8%, and an AUC of 0.91. On the other hand, the Voice Only and Gesture Only models reported an accuracy of 72.0% and 75.0%, respectively. Conclusion: An integrated investigation on voice and gesture features presents a valid and high-accuracy method for ASD (autism spectrum disorder) screening in preschoolers. Combining these two objective types of data greatly improves predicative capability, showing the ability of the technological model to offer a scalable and non-invasive approach to early detection of autism in clinical settings.

Downloads

Download data is not yet available.

References

1. Choi, B., Shah, P., Rowe, M. L., Nelson, C. A., & Tager-Flusberg, H. (2019). Gesture development, caregiver responsiveness, and language and diagnostic outcomes in infants at high and low risk for autism. Journal of Autism and Developmental Disorders, 50(7), 2556-2572.

https://doi.org/10.1007/s10803-019-03980-8

2. Zhang, M., Chen, Y., Lin, Y., Ding, H., & Zhang, Y. (2022). Multichannel perception of emotion in speech, voice, facial expression, and gesture in individuals with autism: A scoping review. Journal of Speech, Language, and Hearing Research, 65(4), 1435-1449.

https://doi.org/10.1044/2022_jslhr-21-00438

3. Sharma, A., & Tanwar, P. (2020). Deep analysis of autism spectrum disorder detection techniques. 2020 International Conference on Intelligent Engineering and Management (ICIEM), 455-459.

https://doi.org/10.1109/iciem48762.2020.9160123

4. Bloch, C., Tepest, R., Jording, M., Vogeley, K., & Falter-Wagner, C. M. (2022). Intrapersonal synchrony analysis reveals a weaker temporal coherence between gaze and gestures in adults with autism spectrum disorder. Scientific Reports, 12(1).

https://doi.org/10.1038/s41598-022-24605-8

5. Kojovic, N., Natraj, S., Mohanty, S. P., Maillart, T., & Schaer, M. (2021). Using 2D video-based pose estimation for automated prediction of autism spectrum disorders in preschoolers.

https://doi.org/10.1101/2021.04.01.21254463

6. Tang, C., Zheng, W., Zong, Y., Qiu, N., Lu, C., Zhang, X., Ke, X., & Guan, C. (2020). Automatic identification of high-risk autism spectrum disorder: A feasibility study using video and audio data under the still-face paradigm. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28(11), 2401-2410.

https://doi.org/10.1109/tnsre.2020.3027756

7. De Belen, R. A., Bednarz, T., Sowmya, A., & Del Favero, D. (2020). Computer vision in autism spectrum disorder research: A systematic review of published studies from 2009 to 2019. Translational Psychiatry, 10(1).

https://doi.org/10.1038/s41398-020-01015-w

8. Liu, J., Wang, Z., Xu, K., Ji, B., Zhang, G., Wang, Y., Deng, J., Xu, Q., Xu, X., & Liu, H. (2022). Early screening of autism in toddlers via response-to-Instructions protocol. IEEE Transactions on Cybernetics, 52(5), 3914-3924.

https://doi.org/10.1109/tcyb.2020.3017866

9. Tanner, A., & Dounavi, K. (2020). The emergence of autism symptoms prior to 18 months of age: A systematic literature review. Journal of Autism and Developmental Disorders, 51(3), 973-993.

https://doi.org/10.1007/s10803-020-04618-w

10. Corbett, B. A., Schwartzman, J. M., Libsack, E. J., Muscatello, R. A., Lerner, M. D., Simmons, G. L., & White, S. W. (2020). Camouflaging in autism: Examining sex‐based and compensatory models in social cognition and communication. Autism Research, 14(1), 127-142.

https://doi.org/10.1002/aur.2440

11. Welarathna, K., Kulasekara, V., Pulasinghe, K., & Piyawardana, V. (2021). Automated Sinhala speech emotions analysis tool for autism children. 2021 10th International Conference on Information and Automation for Sustainability (ICIAfS), 500-505.

https://doi.org/10.1109/iciafs52090.2021.9605841

12. Pandkar, C., Pensalwar, R., Chakravarty, A., & Bhairavkar, A. (2020). Automations in the screening of autism spectrum disorder. Technium, 2(5), 123-131.

https://doi.org/10.47577/technium.v2i5.1136

13. Desideri, L., Pérez-Fuster, P., & Herrera, G. (2021). Information and communication technologies to support early screening of autism spectrum disorder: A systematic review. Children, 8(2), 93.

https://doi.org/10.3390/children8020093

14. Cahyadi, M., Aqilah, T. S., Ediyanto, E., & Junaidi, A. R. (2022). Early detection assessment tools in children with autism spectrum disorder: A literature study. Discourse and Communication for Sustainable Education, 13(2), 13-25.

https://doi.org/10.2478/dcse-2022-0015

15. Khozaei, A., Moradi, H., Hosseini, R., Pouretemad, H., & Eskandari, B. (2020). Early screening of autism spectrum disorder using cry features. PLOS ONE, 15(12), e0241690.

https://doi.org/10.1371/journal.pone.0241690

16. Shrestha, S., Shah, A., Dhakal, P., & Dhakal, N. (2021). Head gesture and voice based learning app for children with autism of Nepal. 2021 3rd International Conference on Sustainable Technologies for Industry 4.0 (STI), 1-6.

https://doi.org/10.1109/sti53101.2021.9732539

17. Kohli, M., Kar, A. K., & Sinha, S. (2022). The role of intelligent technologies in early detection of autism spectrum disorder (ASD): A scoping review. IEEE Access, 10, 104887-104913.

https://doi.org/10.1109/access.2022.3208587

18. MacFarlane, H., Salem, A. C., Chen, L., Asgari, M., & Fombonne, E. (2022). Combining voice and language features improves automated autism detection. Autism Research, 15(7), 1288-1300.

https://doi.org/10.1002/aur.2733

19. Natarajan, J., Bajaj, U., Shahi, D., Soni, R., & Anand, T. (2022). Speech and gesture analysis: A new approach. Multimedia Tools and Applications, 81(15), 20763-20779.

https://doi.org/10.1007/s11042-022-12685-7

20. Laister, D., Stammler, M., Vivanti, G., & Holzinger, D. (2021). Social-communicative gestures at baseline predict verbal and nonverbal gains for children with autism receiving the early start Denver model. Autism, 25(6), 1640-1652.

https://doi.org/10.1177/1362361321999905

21. Wetherby, A. M., Guthrie, W., Hooker, J. L., Delehanty, A., Day, T. N., Woods, J., Pierce, K., Manwaring, S. S., Thurm, A., Ozonoff, S., Petkova, E., & Lord, C. (2021). The early screening for autism and communication disorders: Field-testing an autism-specific screening tool for children 12 to 36 months of age. Autism, 25(7), 2112-2123.

https://doi.org/10.1177/13623613211012526

22. Drimalla, H., Scheffer, T., Landwehr, N., Baskow, I., Roepke, S., Behnia, B., & Dziobek, I. (2020). Towards the automatic detection of social biomarkers in autism spectrum disorder: Introducing the simulated interaction task (SIT). npj Digital Medicine, 3(1).

https://doi.org/10.1038/s41746-020-0227-5