Enhancing early depression detection with AI: a comparative use of NLP models

References

• World Health Organisation. World mental health report: Transforming mental health for all. World Health Organisation; 2022.
   Google Scholar
• Bech P. Rating scales in depression: limitations and pitfalls. In: Dialogues in clinical neuroscience, 2022.
   Google Scholar
• Radez J, Reardon T, Creswell C, et al. Why do children and adolescents (not) seek and access professional help for their mental health problems? A systematic review of quantitative and qualitative studies. Eur Child Adolesc Psychiatry. 2021;30:183–211. doi: 10.1007/s00787-019-01469-4
   PubMed Web of Science ®Google Scholar
• Smith-East M, Neff DF. Mental health care access using geographic information systems: an integrative review. Issues Ment Health Nurs. 2020;41(2):113–121. doi: 10.1080/01612840.2019.1646363
   PubMed Web of Science ®Google Scholar
• Cummins N, Scherer S, Krajewski J, et al. A review of depression and suicide risk assessment using speech analysis. Speech Commun. 2015;71:10–49. doi: 10.1016/j.specom.2015.03.004
   Web of Science ®Google Scholar
• Danner M, Hadzic B, Gerhardt S, et al. Advancing mental health diagnostics: Gpt-based method for depression detection. In: Proceedings Title; 62nd Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE); Tsu City, Japan; 2023; p. 1290–1296.
   Google Scholar
• Calvo R, D'Mello S, Gratch J, et al. Cyberpsychology and affective computing. In: The Oxford handbook of affective computing. Oxford University Press, Jan. 2015.
   Google Scholar
• Scherer KR. What are emotions? and how can they be measured?. Soc Sci Inf. 2005 Dec;44(4):695–729. doi: 10.1177/0539018405058216
   Web of Science ®Google Scholar
• Alghowinem S, Goecke R, Epps J, et al. Cross-cultural depression recognition from vocal biomarkers. In: Interspeech 2016; Sep. ISCA; 2016.
   Google Scholar
• Park J, Moon N. Design and implementation of attention depression detection model based on multimodal analysis. Sustainability. 2022 Mar;14(6):3569. doi: 10.3390/su14063569
   Web of Science ®Google Scholar
• Uslu I. Deep Learning im Mental Health Kontext [master's thesis]. Reutlingen University, 2023.
   Google Scholar
• Raffel C, Shazeer N, Roberts A, et al. Exploring the limits of transfer learning with a unified text-to-text transformer. In: 21.1, 2020.
   Google Scholar
• Cheng JC, Chen ALP. Multimodal time-aware attention networks for depression detection. J Intell Inf Syst. 2022 Apr;59(2):319–339. doi: 10.1007/s10844-022-00704-w
   Web of Science ®Google Scholar
• Toto E, Tlachac M, Rundensteiner EA. AudiBERT. In: Proceedings of the 30th ACM International Conference on Information & Knowledge Management; Oct. ACM; 2021.
   Google Scholar
• Sharma A, Sharma K, Kumar A. Real-time emotional health detection using fine-tuned transfer networks with multimodal fusion. Neural Comput Appl. 2023 Jan;35(31):22935–22948.
   Web of Science ®Google Scholar
• Aloshban N, Esposito A, Vinciarelli A. What you say or how you say it? Depression detection through joint modeling of linguistic and acoustic aspects of speech. Cognit Comput. 2022;14(5):1585–1598. doi: 10.1007/s12559-020-09808-3
   Web of Science ®Google Scholar
• Davis S, Mermelstein P. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans Acoust. 1980;28(4):357–366. doi: 10.1109/TASSP.1980.1163420
   Google Scholar
• Huang Z, Epps J, Joachim D. Investigation of speech landmark patterns for depression detection. IEEE Trans Affect Comput. 2022;13(2):666–679. doi: 10.1109/TAFFC.2019.2944380
   Web of Science ®Google Scholar
• McGinnis EW, Anderau SP, Hruschak J, et al. Giving voice to vulnerable children: machine learning analysis of speech detects anxiety and depression in early childhood. IEEE J Biomed Health Inform. 2019;23(6):2294–2301. doi: 10.1109/JBHI.6221020
   PubMed Web of Science ®Google Scholar
• Bailey A, Plumbley MD. Gender bias in depression detection using audio features. In: 29th European Signal Processing Conference, EUSIPCO 2021, Dublin, Ireland, August 23-27, 2021. IEEE; 2021. p. 596–600.
   Google Scholar
• OpenAI. GPT-4 technical report. In: CoRR abs/2303.08774; 2023.
   Google Scholar
• Thoppilan R, Freitas DD, Hall J, et al. Lamda: Language models for dialog applications. In: CoRR abs/2201.08239; 2022.
   Google Scholar
• Sun Y, Wang S, Feng S, et al. ERNIE 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation. In: CoRR abs/2107.02137; 2021.
   Google Scholar
• Touvron H, Lavril T, Izacard G, et al. Llama: Open and efficient foundation language models. In: CoRR abs/2302.13971; 2023.
   Google Scholar
• DeVault D, Artstein R, Benn G, et al. Simsensei kiosk: A virtual human interviewer for healthcare decision support. In: Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems; 2014; p. 1061–1068.
   Google Scholar
• Gratch J, Artstein R, Lucas G, et al. The distress analysis interview corpus of human and computer interviews. Tech. rep. University of Southern California Los Angeles, 2014.
   Google Scholar
• Scherer S, Stratou G, Lucas G, et al. Automatic audiovisual behavior descriptors for psychological disorder analysis. Image Vis Comput. 2014;32(10):648–658. doi: 10.1016/j.imavis.2014.06.001
   Web of Science ®Google Scholar
• Lopez-Otero P, Docio-Fernandez L. Analysis of gender and identity issues in depression detection on de-identified speech. Comput Speech Lang. 2021;65:101118. doi: 10.1016/j.csl.2020.101118
   Web of Science ®Google Scholar
• Qureshi SA, Saha S, Hasanuzzaman M, et al. Multitask representation learning for multimodal estimation of depression level. IEEE Intell Syst. 2019;34(5):45–52. doi: 10.1109/MIS.2019.2925204
   Web of Science ®Google Scholar
• Chicco D, Jurman G. The advantages of the Matthews correlation coefficient (MCC) over f1 score and accuracy in binary classification evaluation. BMC Genomics. 2020;21(1):1–13. doi: 10.1186/s12864-019-6413-7
   Web of Science ®Google Scholar
• Yacouby R, Axman D. Probabilistic extension of precision, recall, and f1 score for more thorough evaluation of classification models. In: Proceedings of the first workshop on evaluation and comparison of NLP systems; 2020; p. 79–91.
   Google Scholar
• Kroenke K, Strine TW, Spitzer RL, et al. The PHQ-8 as a measure of current depression in the general population. J Affect Disord. 2009;114(1-3):163–173. doi: 10.1016/j.jad.2008.06.026
   PubMed Web of Science ®Google Scholar
• Radford A, Kim JW, Xu T, et al. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning; 2023; p. 28492–28518. PMLR.
   Google Scholar
• Hamilton M. A rating scale for depression. J Neurol Neurosurg Psychiatr. 1960;23(1):56–62. doi: 10.1136/jnnp.23.1.56
   PubMed Web of Science ®Google Scholar
• Itai A, Papadimitriou CH, Szwarcfiter JL. Hamilton paths in grid graphs. SIAM J Comput. 1982;11(4):676–686. doi: 10.1137/0211056
   Web of Science ®Google Scholar
• Devlin J, Chang MW, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding; 2018.
   Google Scholar
• El Anigri S, Himmi MM, Mahmoudi A. How bert's dropout fine-tuning affects text classification?. In: Business Intelligence; 2021; p. 130–139.
   Google Scholar
• Katz DM, Bommarito MJ, Gao S, et al. Gpt-4 passes the bar exam. 2023 March 15.
   Google Scholar
• Villatoro-Tello E, Ramirez-de-la Rosa G, Gática-Pérez D, et al. Approximating the mental lexicon from clinical interviews as a support tool for depression detection. In: Proceedings of the 2021 International Conference on Multimodal Interaction; 2021; p. 557–566.
   Google Scholar
• Senn S, Tlachac M, Flores R, et al. Ensembles of bert for depression classification. In: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC); 2022; p. 4691–4694.
   Google Scholar