Skip to main content

Diagnosing Depression in Casual Conversation? Neural Networks Lead The Way

Asiket Singh Dhillon



Neural Networking and pattern recognition are a rising force in technological sector. Once we can teach machines to ‘learn’, the avenues that machines can be used in are ever expanding. Improved neural networks could possibly yield higher efficiency rates in automatic screening of individuals who may have cognitive and behavioural abnormalities.
Earlier this year Tulka Anhanai, Mohammed Ghassemi and James Glass came together to present their paper titled Detecting Depression with Audio/Text Sequence Modeling of Interviews. It puts forward a model of detecting depression in individuals which rather than relying on traditional iterations of uses, what they call “context-free” detection. Traditional models may analyse a set of answers to predetermined questions. For example, “How often do feel low/depressed?” / “Does your family have a history of any mental diagnoses?”. The model knows what a depressed person would say and compares the individual’s answers to see where they fit.
Al Hanai’s model analyses the content as well as the manner of expression of answers. Therefore, it is not constrained to the specific conversation but can utilise patterns recognised in other individuals that may exhibit similar content and exhibition to reach its assessment. Depressed individuals may speak slower and with lower voice modulation in comparison to healthy individuals. The model recognises certain patterns which emerge and then presents its diagnosis. This is known as sequence modelling which allows it to not be constrained to a case-by-case analysis and use recognisable patterns and apply those to a variety of contexts. Sequencing allows for the analysis to not be restricted to pointed questions and direct answers but rather for entire conversations and detect the severity of depression as well.
Out of a total of 142 subjects that the system analysed it labelled 28 individuals as those with depression. In terms of precision the system scored 71%. Out of the 142 some were used as training for the model and others for development which left 47 (25%) of the subjects which the model had to assess. While this is far from ideal, it is a learning step. The implications of such a model means that it would be possible to not rely only on self-reports and manual analysis which may be hindered by the assessor’s biases. The system will be able to analyse casual conversation and provide assistance. Furthermore, individuals that cannot physically be present at the practitioner’s office will also fall under the purview of the system. Clinicians are then, no longer restricted to asking specific questions and direct answers within specific context.
What the researchers found upon poring over the results was that the system requires over 4 times more audio interactions (30) to identify patterns as compared to text (7).  I believe that this may be due to the fact that audio would require far more categorisations than text. Such as modulation, tone, pauses between words and tempo. The textual analysis is fairly constrained to the content of the text as well as arrangement. While the parameters that the system works on are understood, “How” the system reaches its conclusions as well as what patterns it recognises are hard to discern. This is due to the nature of neural networks and their functioning, i.e the individual nodes and their function in the larger network is largely unknown. So we know the input which is the audio and transcripts and the output which is the model’s assessment.  Figuring out how it reached that conclusion is the next step forward.
The researchers hope that this model paves the way for different, specialised versions which can diagnose other impairments such as Dementia. The way forward for the model is a symbiotic relation between the clinician and the model. Improving the accuracy of the model as well as increase the understanding that we have of the inner workings of the neural networks.

Matheson, Rob. (2018, August 29). Model can more naturally detect depression in conversations. MIT News. Retrieved from http://news.mit.edu/2018/neural-network-model-detect-depression-conversations-0830
Al Hanai, T., Ghassemi, M., Glass, J. (2018) Detecting Depression with Audio/Text Sequence Modeling of Interviews. Proc. Interspeech 2018, 1716-1720, DOI: 10.21437/Interspeech.2018-2522.

Labels:

Comments

Post a Comment

Popular posts from this blog

The Burari Deaths: The Psychopathology of Lalit, a Biopsychosocial Perspective

Pankhudi Narayan Blogpost 1  TW: Death, mentions of suicide.         On July 1st of 2018, eleven members of a family were found dead in their shared home in the Burari area of Delhi. The deaths seemed to be fashioned in a ritualistic manner and evidence suggested that the family members were willing participants. This was the Bhatia family, a typical middle-class Indian joint family. Bhopal Singh who had passed away and his wife Narayani Devi formed the older generations of the family and were Lalith’s parents. The most compelling evidence in the uncovering of the events that led to the death of an entire family was provided by eleven diaries found by authorities. The diaries described the events that transpired before the deaths, discussing a ritual that needed to be conducted and the diary entries were corroborated by the post mortem findings as the accounts were found to be consistent with injuries (Yadav et al., 2021). It was uncovered that Lalit, a member of the family who was the
Post a Comment
Read more

Made in Heaven: An analysis of Faiza Naqvi

Vyoma Vijai Blog Post 3 ‘Made in Heaven’ is a popular Indian web series created by Zoya Akhtar and Reema Kaagti and was launched in March 2018. The show gained a lot of attention in the first few days of it coming out. It is a bold show that focuses on marriage practices in the rich and elite class of Delhi. The show focuses on the social issues and practices that are often not spoken of or are kept closeted. These issues include homosexuality, dowry, molestation and other questionable Indian customs. The story follows the lives of multiple characters at the same time. The two most important characters are Tara and Karan who run a wedding planning agency.   Tara is married to a rich industrialist whose name is Adil and her best friend in the show is Faiza, played by Kalki Koechlin. This essay analyses Faiza’s character and her role in this web series. Faiza is a complex character to understand. Her actions make it hard for the viewers to decide whether they l
Post a Comment
Read more

Disorderly Delvian: A Deep Dive into "Anna Delvey" through the Lens of NPD

       A markedly thick accent, a mop of blonde hair, a magical array of unimaginably expensive clothing, and an air of calculated mystery mesh uncomfortably together to invent Anna Delvey, the centre of Netflix’s appropriately named documentary/drama series, “Inventing Anna”. This series tells or rather retells the fascinating story of how one woman deceived the creme de la creme of New York society as well as some prestigious financial institutions under the guise that she was a wealthy heiress from Germany. The series follows a journalist, Vivian Kent, as she tries to uncover the carefully constructed web of lies Anna spun around high society after her arrest, heavily interspersed by flashbacks, present-day court hearings, and interviews with the enigma herself (Shondaland, 2022). Anna as a character, infused with a troubling reality and a dramatised narrative, presents an interesting scope to study the symptomatology of Narcissistic Personality Disorder as presented in her behaviou
Post a Comment
Read more