Comment by kgarten | Hacker News Reader

Comment by kgarten | Hacker News Reader

Parent Full thread

Such studies, papers and news always makes me cringe. It seems overly engineered with limited usefulness.

Superpower glass … really?

As background I work in public research and have no background in Autism research. Yet, due to a mutual friend, I was lucky to meet Kelly Hunter, and attend one of her workshops (together with several other researchers working on helping autistic children). I knew the Stanford project, mentioned it and got just strange looks: “This does not really solve any of the problems we are facing” It seems detecting facial emotions are not the main problems of the autistic children they are dealing with ...

https://flutetheatre.co.uk/changing-lives-of-people-with-aut...

Here’s work from a friend on the topic: https://www.ucl.ac.uk/grand-challenges/sites/grand-challenge...

The system itself can just help children with very mild symptoms. One colleague who works on wearable sensing for them mentioned that even head bands and wrist watches cannot be used as children commonly take them off and throw them around.

Kelly also runs a fundraiser right now in case somebody wants to help out. In my personal opinion much more useful than the solution described in the ieee article: https://www.facebook.com/donate/574661226469627/101582037614...

Autism is a spectrum disorder, which means there is a wide range of afflictions, and the afflictions range from very, very mild to debilitating.

Conducting research for something that is spectrum based is frustrating because researchers can only target one small area. The approach is necessary in order to tackle the problem because the problem is so large, we'll need a lot of researchers working on a lot of very focused areas in order to move forward in a broad fashion.

Completely agree, yet I think this should be reflected in the article.

From the limited exposure I had with children on the spectrum, I didn’t see many that could actually wear a google glass to use it as described in the article. I also don’t understand the benefit of the device itself. It’s not designed for autism, the interventions seem simplicstic ,battery life is highly limited, it‘s very fragile ... if it’s for short interactions and games (like they describe in the papers) I wonder what the advantage of the head mounted display is compared to other setups. they don’t do any comparisons.

It turns out that people with autism do have difficulty detecting emotions. A classic task in the lab is the "reading the mind in the eyes" task (http://socialintelligence.labinthewild.org/mite/), whereby individuals need to identify the emotion someone is expressing by looking at a picture of their eyes. People with autism consistently show lower scores than healthy controls.

Will improving the ability to detect emotions improve clinical outcomes? We don't know, but their initial evidence looks promising: take a look at the JAMA Pediatrics paper (https://jamanetwork.com/journals/jamapediatrics/fullarticle/...) and the Nature Digital Medicine paper (https://www.nature.com/articles/s41746-018-0035-3), which are both linked to in the article:

Would a therapy like the one you described be better than a technology like this? Maybe. But therapy also very expensive, time consuming, and prohibitive for people who don't have time to take their kid to it every week. We are always looking for new approaches. Even if technology like this doesn't work out, learning why it doesn't work will be helpful for developing future treatments which are better. Remember that this is active research, not an established methodology. (Don't be put off by the "breakthrough therapy" designation mentioned in the article, which is a bureaucratic technical term used by the FDA.)

The paper you linked to is about monitoring, and is not useful by itself without a therapist to interpret it and evaluate it. There is not yet established methodology on how to use this kind of data.

On a related note, there has been a lot of interest recently in real-time feedback for enhanced therapy and treatment. There is a growing literature on neurofeedback in particular, such as reducing depression symptoms by training someone to control their neural activity (e.g. see https://www.youtube.com/watch?v=Xb7bgNo3sUs). Exciting stuff!

Therapists that worked 10 -20 years in the field are maybe better than some tech that's not even thoroughly evaluated? Sorry that made me chuckle. Check some of the videos. The children I saw in the workshops (who played Shakespeare at the end), would have just taken the Google glass and threw it to the ground as soon as they would have been angry. There were a lot of dangerous situations in the workshops, that therapists could just avert due to their training ... The article and the research paper oversimplify the problem. This is just useful for a very small minority of autistic children. Autism is a spectrum and it is very complicated.

here some videos so you can judge: https://vimeo.com/user42939049

What's the point of knowing someone is angry if you do not know why he is angry? Detecting emotions doesn't strike me as particularly useful. Manipulating emotions of others on the other hand,...

Knowing someone is angry allows you to act accordingly.

If you don't know someone is sad how do you console them?

There's a great comedy on Netflix called Atypical, one of the things the main character deals with in this show is his inability to read peoples emotions.

That you think a sad person needs consoling reveals your lack of understanding of the problem. It wouldn't occur to an autistic person to console someone who is sad. The ability to read emotion isn't useful on its own. You also need to know how to react to this emotion. Knowing someone is angry won't help you if you have no idea how to defuse this anger. Social interactions do not make sense for autistic people and need to be learned like a foreign language. It's like writing a computer program. You have to be very precise when telling a computer what to do and the same goes for autistic people. You can't just tell them someone is angry and expect them to know what to do. Or when someone is sad, even if you tell them that they have to console such a person, they'd have no idea what consoling even is and how to do it.

See this is the problem a lot of children on the spectrum don't know how to react (or will react in an atypical fashion) ... You need to train interactions (and changes in emotions during communication).

There might be something useful coming out of it, yet it might also do more harm than good.

It's a start. You're unlikely to learn why somebody is angry unless you know that somebody is angry. And humans are very good correlators. If me doing X repeatedly leads to immediate anger, I'll learn not to do it even if I don't understand why.

Reply on news.ycombinator.com