Early Warning Sign Detection App

Hi All,

I suffer from Schizophrenia, having had 4 psychoses during my adulthood.

I’ve recently been involved in an entrepreneurship programme, where a couple of founders were working on a startup to deliver prescription-based digital therapeutics.

Which got me thinking… Both myself and my wife have noticed early warning signs in the language that I use and my emails, texts, etc. What if there were an app that people suffering from this condition could install on their phones. That analyses speech patterns in calls, and language patterns in text and emails being sent. And should it identify abnormal patterns, it sends an alert to the partner or family member of the person who is suffering from this condition. So that they can intervene by seeing a professional and adjusting medication or by intervening through therapy, etc.

I believe that with the recent advances in natural language processing and semantic analysis that this is technically feasible.

Would any of you who are suffering from this condition voluntarily install this app on your phone if it existed?

I totally understand that it wouldn’t work as an involuntary intervention - as it could further paranoia. But if it were voluntary…

What do you all think? Would you use such an app?

Only one percent of the population is affected. I don’t think anyone would plan against and when you first get sick the paranoia is overwhelming.

Maybe if it ran in your family.

Its a good idea but how precise is it? Can it accurately detect sz? What if it gives false positives? Sometimes someone drunk can write or talk like a schizophrenic. Anyways, its sounds too hard to make such an app.

Thanks for the feedback.


  1. 1% of the population is ~200,000 people. Each of those people have friends, family, employers and colleagues who are also impacted by their illness. That is likely to be millions of people and a huge proportion of the Australian population.
  2. You’re right that when you first get sick the paranoia is overwhelming. Which is why I’m trying to figure out whether someone in a psychosis would just delete the app in fear that it’s spying on them. I think the idea though - is to catch it pre-psychosis. So ideally - before the paranoia becomes overwhelming.


  1. It’s just an idea at the moment. Prior to developing it we would need to conduct a proper assessment and research. Ie; I don’t know how precise it could be just yet, or whether it would be able to accurately detect sz, psychoses or whether it would give false positives
  2. You’re right that sometimes drunk people can talk in a similar way to someone with sz. Just as normal sober people can. No-one is immune from delusion (jumping to conclusions). It happens to every one, as well as on a higher order to groups of people such as populations of countries or the world.
  3. We cannot jump to the conclusion that such an app would be too hard to make without the proper upfront research required to assess its viability. In order to influence those who could develop such an app, and to receive funding - I would need to ascertain the likelihood that those afflicted would actually use it. This is what I’m currently trying to do.

Thanks again for your respective replies.

1 Like

The target audience might be informed recovered schizophrenics, minus the % of them that have delusions related to surveillance or are concerned with their privacy. If you could do most of the processing in the way that no person sees the user’s data, and convince the user that you’re doing it (such as by letting an independent/reputable party audit the app), it might increase willingness to install such an application.
I’m wondering how you’d get enough communication data (both “sane” and “insane”) required to develop this app, though.

But such research should cost tons of money, no?

I think it’s a cool idea. I also think a lot of people with sz would just delete the app. But it’s worth looking into.

Thanks, all.


  1. Good points. I like your suggestion about ensuring no person sees the data and getting a reputable third-party to audit it.
  2. Haven’t put a lot of thought in to how we’d gather the data. Could possibly begin through a series of online surveys to try and discover common themes between the experiences of those suffering from sz. And supplement it with data mining posts from forums like this one to basically harvest written language by those who have this illness and then attempt to identify how “dellusional” each post is (if at all).


  1. A preliminary assessment should be pretty straight forward and inexpensive that will allow us to quantify the expected cost of the actual research + build cost.
  2. When it comes to funding to cover cost of the actual research and build - I have contacts in the venture capital industry and am connected to a couple of founders who are launching a digital therapeutics startup - so I’m not approaching this with zero idea of where I could get funding from.


  1. Thanks for your feedback. What do you think about an alternative take on this idea - basically an “Early Warning Sign Detection App”. Doesn’t explain how it detects the early warning signs to users. However the way it would work is as a kind of “dead man’s switch”. Ie; if the user gets paranoid and deletes the app - their family member is sent an alert. Ie; the early warning sign we use is the process of deleting the app.

This topic was automatically closed 95 days after the last reply. New replies are no longer allowed.