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

Scarlett O' Hara Diagnosed

By Ragini Chatterjee   (Overall Grade Remedial) A case study on Scarlett O' Hara from ‘Gone with The Wind’   Scarlett O' Hara has to be one of the most vivacious character, on print. With her southern Belle ‘ Fiddle de dees ’, bright green eyes and sharp tongue, she is hard to forget. After having seen the movie multiple times from age 13, I was fascinated by her personality. Her antics, at times cruel, bought the story to life. Her obsession with Ashley, her multiple marriages, her cunning mind and relentless spirt were always entertaining from the perspective of the viewer. However, years later as I look back, I can’t help but recognize patterns of behavior that may resonate with some personality disorder. From the beginning of the movie, Scarlett has to be the centre of attention . At the Wilkes Party, in her attempts to drive Ashley jealous, she flirts with every man in sight- Starting with Charles Hamilton, Frank Kennedy, the Tarleton twins, she promis...
Post a Comment
Read more

PTSD and its portrayal in Peaky Blinders

AARYAN SANWAL The award-winning TV series, Peaky Blinders is set in Birmingham, England at the end of the First World War and gives an account of the Peaky Blinders that is headed by the Shelby family. Thomas Shelby was a tunneller in World War I and for his actions, received two medals of honour after the war.   This blog post shall look at the representation of war trauma, its accuracy in depictions and its effects on the lives of the characters. The two main characters that this blog post will be focusing on are Thomas Shelby and Daniel Owen (a.k.a. Danny Whiz-Bang). The two of them were tunnellers in the War and were going through a routine tunnel expedition when the Germans broke through the end of their tunnel and attacked the men in the tunnel and brutally injured Thomas and Daniel. They were able to kill the enemies and leave the tunnels, alive but severely injured. During various instances throughout the show, Thomas Shelby has recurring nightmares of his time i...
Post a Comment
Read more

PTSD and its relationship with defense mechanisms and empathy: Character analysis of Levi Ackerman (SnK)

|Indira Bulhan Blog post: 1 “Manga is for kids” (My ignorant friend, 2018). Manga is often treated by people as something which is not so serious. However, it holds within itself some dark aspects of humanity. One such example is Shingeki no Kyojin (Attack on Titan). In it, the character of Levi Ackerman has been through a series of events which sets him apart from the people around him. Through this blog post, I will look upon the nature of post-traumatic stress disorder (PTSD) and its relationship with defense mechanisms and empathy.     Levi’s past is filled with events which can act as strong stressors for the development of trauma: the death of his mother at an early age, abandonment by father, raised by his uncle in the underworld in a highly unhygienic and malnourished state (who later abandons him again), death of his two closest friends and lover. Post-traumatic stress disorder or PTSD can be defined as a mental disorder which can happen to peopl...
Post a Comment
Read more