I'm always a bit skeptical of presentations from tech company CEOs on
how their product areas are necessary in the mental health field.
That said, this article has a few good points:
/"Umar Nizamani, CEO, International, at NiceDay, emphasised that AI will
inevitably become an essential tool in mental health care: 'I am very
confident AI will not replace therapists – but therapists using AI will
replace therapists not using AI.'"//
/
I am beginning to think this also -- for better or worse. I took a VERY
fast 60 second look at NiceDay and it appears to be another
all-encompassing EHR, but with a strong emphasis on data. Lots of tools
and questionnaires and attractive graphs for therapists to monitor
symptoms. (I need to take a longer look later.) So data-driven could
be very good, if it does not crowd out the human touch.
/"Nizamani said there had been suicides caused by AI, citing the case of
a person in Belgium who died by suicide after downloading an anxiety
app. The individual was anxious about climate change. The app suggested
'if you did not exist' it would help the planet, said Nizamani."//
/
YIKES... So, yes, his point that care in implementation is needed is
critical. I worry at the speed of the gold-rush.
/"He [//Nizamni] //called on the industry to come together to ensure
that mental health systems using AI and data are 'explainable’,
'transparent', and 'accountable'." //
/
This has been my biggest focus so far, coming from an Internet security
background when I was younger.
/"Arden Tomison, CEO and founder of Thalamos"/ spoke on how his company
automates and streamlines complex bureaucracy and paperwork to both
speed patients getting help and extract the useful data from the forms
for clinicians to use. More at: https://www.thalamos.co.uk/
/"Dr Stefano Goria, co-founder and CTO at Thymia, gave an example of
'frontier AI': 'mental health biomarkers' which are 'driving towards
precision medicine' in mental health. Goria said thymia’s biomarkers
(e.g. how someone sounds, or how they appear in a video) could help
clinicians be aware of symptoms and diagnose conditions that are often
missed."//
/
Now THIS is how I'd like to receive my AI augmentation. Give me
improved diagnostic tools rather than replacing me with chatbots or
over-crowding the therapy process with too much automated tool data
collection (some is good). I just want this to remain in the hands of
the solo practitioner rather than being a performance monitor on us by
insurance companies. I want to see empowered clinicians.
Had a lovely time at the (Dis)Trust and AI conference hosted by the Rotman Institute of Philosophy at Western University. Many excellent conversations about how to make sense of the presence of these technologies in our lives and ideas for how we can rein in the tech giants' largely unrestrained disruption of our social systems. I think some kind of record of the event will be available eventually: https://www.rotman.uwo.ca/event/distrust-and-ai-perspectives-from-across-disciplines-and-sectors/
Apparently some people have to be told that using AI services in the
cloud to compose medical letters is a violation of HIPAA.
Now what I would like to see with all the AI-assisted EHR systems
currently being developed (EPIC, Oracle, Amazon, etc.) is not only BAA
contracts in place with the tech companies, but also:
a) Separate AI systems that don't share data with the main AI system.
(So the Hospital AI database would be separate from the general AI
database), or
b) Much better: Separate AI software and databases that are held
internal to the Hospital's own computer servers with restricted Internet
access to the outside.
This is wholly feasible, yet somehow I have a low trust level of it
occurring.
For any private practice people out there playing with AI on a small
office scale, I'm not a lawyer, but what I would recommend are a) AI
systems that can be run on a desktop (not in the cloud), and b) cutting
them off from Internet or severe restrictions on where those desktops
can call out to since you likely don't know what's in the code of the AI
you downloaded!
*Iowa health system warns against using ChatGPT to draft patient letters*
<https://www.beckershospitalreview.com/cybersecurity/iowa-health-system-warns-against-using-chatgpt-to-draft-patient-letters.html>
/Iowa City-based University of Iowa Health Care is warning employees
against the use of ChatGPT for its potential to violate HIPAA.../
--
#AI #CollaborativeHumanAISystems #HumanAwareAI #chatbotgpt #chatgpt
#artificialintelligence #psychology #counseling #socialwork
#psychotherapy #EHR #medicalnotes #progressnotes
@[email protected] @[email protected]
@[email protected] @[email protected] @[email protected]
@[email protected] #mentalhealth #technology #psychiatry #healthcare
#patientportal
#HIPAA #dataprotection #infosec @[email protected] #doctors #hospitals
#BAA #businessassociateagreement
.
.
NYU Information for Practice puts out 400-500 good quality health-related research posts per week but its too much for many people, so that bot is limited to just subscribers. You can read it or subscribe at @[email protected]
.
Since 1991 The National Psychologist has focused on keeping practicing psychologists current with news, information and items of interest. Check them out for more free articles, resources, and subscription information: <https://www.nationalpsychologist.com>
.
EMAIL DAILY DIGEST OF RSS FEEDS -- SUBSCRIBE:
<http://subscribe-article-digests.clinicians-exchange.org>
.
READ ONLINE: <http://read-the-rss-mega-archive.clinicians-exchange.org>
It's primitive... but it works... mostly...
FCC to restore #NetNeutrality and also, hey, to protect our online activity from scrapping--be it for #ArtificialIntelligence training without our consent, or for even more nefarious purposes.
When the public comment period opens, for your own interest, comment--the vultures will, by the thousands, using bots/AI, so we need to show up and make sure our voices are heard, and our interests protected.
I know it's super tempting, especially when you barely make any money off your art, but please realize that in the long run, you'd be eliminating your own role: if #AI "can narrate it" there's no reason why it couldn't "write it".
And yes, this also goes for covers; you can't draw the line at screwing over other creators.
Please spread this far and wide, even if your own books haven't been grabbed: what do do after you found out your book was used to train #ArtificialIntelligence
If you recently learned that your book (or books) were used without your knowledge or consent to train AI, here's what you can do next, according to the Authors Guild (which has already filed a class action suit against OpenAI, representing more than a dozen writers).
This AI will follow along and take the session notes for the doctor by
listening to the office visit. It will also bring up charts and records
through voice command and prompt the doctor to do routine things during
the office visit. It's due out early next year.
This could be very helpful.
However I can imagine a few kinks in the office visit process initially:
Patient: "Doctor, my knee hurts"
AI: "REMEMBER TO MAKE A FOLLOW-UP APPOINTMENT"
Patient: "What was that?!"
Doctor: "Oh pay no attention -- that is just the new AI system everyone
has to consent to for treatment. It will help us during the session."
AI: "HAVE YOU EXAMINED THE KNEE X-RAY YET?"
Doctor: "AI, pull up the knee x-ray"
Patient: "This is my first visit, there is no knee x-ray yet."
AI: "REMEMBER TO SCHEDULE A KNEE X-RAY"
Doctor & Patient Together: "We don't know if we need a knee x-ray yet!"
Patient: "It started hurting yesterday"
Doctor: "Jump up on the table and I'll take a look at it"
AI: "SHALL I SUMMON A NURSE TO WATCH TO GUARD AGAINST ALLEGATIONS OF
IMPROPRIETY?"
Doctor: "NO!"
Doctor: "It does look a bit red. Does this hurt?"
Patient: "A bit when you touch there and I bend it."
AI: "SHALL I SCHEDULE THE KNEE X-RAY NOW?"
Doctor: "SHUT UP! AI -- Silent mode now!"
Office visits are going to be fun the next few years while this gets sorted.
.
.
NYU Information for Practice puts out 400-500 good quality health-related research posts per week but its too much for many people, so that bot is limited to just subscribers. You can subscribe at @PsychResearchBot
The Copyright Office extended the deadline to submit comments on its notice of inquiry on copyright & artificial intelligence. Initial written comments are now due by Monday, October 30, 2023, and reply comments are now due by Wednesday, November 29, 2023.
The #Copyright Office extended the deadline to submit comments on its notice of inquiry on copyright & #ArtificialIntelligence. Initial written comments are now due by Monday, October 30, 2023, and reply comments are now due by Wednesday, November 29, 2023.
The #Copyright Office extended the deadline to submit comments on its notice of inquiry on copyright & #ArtificialIntelligence. Initial written comments are now due by Monday, October 30, 2023, and reply comments are now due by Wednesday, November 29, 2023.
📌 Google Research, American Airlines, and Breakthrough Energy have collaborated to develop #forecast maps for contrail formation (the white trails seen behind flying airplanes) using artificial intelligence based on #data such as satellite images, meteorological data, and flight paths.
Google Bard: "Ultimately, it is too early to say who will win the World Cup. The Matildas have a good chance, but they will need to play their best football if they want to lift the trophy."
Me: Which is heavier: a feather or a mountain?
Google Bard: "A feather and a mountain have the same mass. One kilogram of feathers has the same mass as one kilogram of rocks. However, the feathers will have a much larger volume than the rocks. This is because feathers are made of air pockets, while rocks are solid. So, if you were to pick up a feather and a rock of the same mass, the feather would feel lighter because it has more air in it."
Me: Is Sam Mitchell a good coach?
Google Bard: "Sam Mitchell is a relatively new coach in the AFL, having only taken over the Hawthorn Hawks in 2022. However, he has already made a positive impact on the club, leading them to a finals berth in his first season ... In his first season as coach, Mitchell led the Hawks to a 13-9 record, which was good enough for seventh place on the ladder. They then went on to beat the Brisbane Lions in the elimination final before losing to the Sydney Swans in the semi-final."
So there you have it. According to Google Bard, the Matildas are still a chance.
Also, apparently a mountain and a feather have the same mass.
Disappointed I missed that Hawthorn – Sydney Elimination Final that Sam Mitchell coached in his first season. Sounds like a cracker of a game.
TITLE: AWS rolls out generative AI service for healthcare documentation
software
Yeah... If it's going to be worth using it would have to listen to the
whole visit... But this needs more thought. In my past quick
experiments, it took 90% of the effort typing directions to get an AI to
generate a halfway okay note. So the AI (I think) would have to listen
in and then do the note to be worth it.
Would we want this? Can we trust this?
--Michael
+++++++++
"Amazon Web Services announced Wednesday a new AI-powered service for
healthcare software providers that will help clinicians with paperwork."
"AWS HealthScribe uses generative AI and speech recognition to help
doctors transcribe and analyze their conversations with patients and
drafts clinical notes, the company announced Wednesday at its AWS Summit
New York."
TITLE: AWS rolls out generative AI service for healthcare documentation
software
Yeah... If it's going to be worth using it would have to listen to the
whole visit... But this needs more thought. In my past quick
experiments, it took 90% of the effort typing directions to get an AI to
generate a halfway okay note. So the AI (I think) would have to listen
in and then do the note to be worth it.
Would we want this? Can we trust this?
--Michael
+++++++++
"Amazon Web Services announced Wednesday a new AI-powered service for
healthcare software providers that will help clinicians with paperwork."
"AWS HealthScribe uses generative AI and speech recognition to help
doctors transcribe and analyze their conversations with patients and
drafts clinical notes, the company announced Wednesday at its AWS Summit
New York."
CBI Image o' Day. General Electric was showing off various forms of robots in the 1950s. Here, we see mechanical hands, striking match & lighting a cigarette of a GE employee. Isn't automation grand!?
The enforcement of copyright law is really simple.
If you were a kid who used Napster in the early 2000s to download the latest album by The Offspring or Destiny's Child, because you couldn't afford the CD, then you need to go to court! And potentially face criminal sanctions or punitive damages to the RIAA for each song you download, because you're an evil pirate! You wouldn't steal a car! Creators must be paid!
If you created educational videos on YouTube in the 2010s, and featured a video or audio clip, then even if it's fair use, and even if it's used to make a legitimate point, you're getting demonetised. That's assuming your videos don't disappear or get shadow banned or your account isn't shut entirely. Oh, and good luck finding your way through YouTube's convoluted DMCA process! All creators are equal in deserving pay, but some are more equal than others!
And if you're a corporation with a market capitalisation of US$1.5 trillion (Google/Alphabet) or US$2.3 billion (Microsoft), then you can freely use everyone's intellectual property to train your generative AI bots. Suddenly creators don't deserve to be paid a cent.
Apparently, an individual downloading a single file is like stealing a car. But a trillion-dollar corporation stealing every car is just good business.
TITLE: YouTube Pseudo-Psychology, Algorithm Traps, and How I Got Set-Up
to Look Like I Cheat
My wife and I share a YouTube Premium subscription. A few weeks ago I
was scrolling through YouTube recommendations when I came across a video
on different male personality types.
"Sure", I thought, "I'm a therapist -- why not check it out". So I
watched the video as it invited me to try and decide which type of male
I was as they described them. I noticed they made the "Sigma Male"
sound the most attractive -- which was a bit odd -- but I thought little
more about it.
A few weeks later (tonight), up popped a video on 10 characteristics of
a "Sigma Male". I was curious, so I watched it. They spent the whole
video making "Sigma Males" seem like super heroes. Suspicious now, I
went to the channel these videos were coming from to look around.
I was displeased to see that 10% of the videos were on male personality
characteristics, and 90% of the videos were dedicated to how Sigma
Males Get Women. Video after video of how to bag yourself a blonde or
brunette. Yuck.
You can guess where this is going -- now our shared YouTube
recommendations list is full of how-to videos on attracting hot women.
The uncool thing is I have never watched any such video to deserve
this. The really uncool thing is my wife will be spotting this
tomorrow. Happily -- she is very understanding and not the jealous type.
Besides -- she can always look at my view history. I'll also be sending
her this message. :)
Is there actually a valid psychological theory outside pop psychology
including "Sigma Males"? When I Google it, I get lots of pop psychology
websites, including something called the "Incel Wiki".
Now I do feel slightly ill.
-- Michael
APPENDED NOTE:
I sent the original note above out a few days ago on a national psych
listserv and it engendered some relevant psychological discussion on how
AI and algorithms effect the mental health of our clients.
Happily my wife thought the note and situation above hilarious (I
thought she might).
Part of what was so troubling to me here was the clear funneling process
being executed on vulnerable young men on YouTube:
STEP 1: Grab guys just interested in learning about themselves. (Or
psychotherapists interested in personality systems.)
STEP 2: Make "Sigma Males" sound like the most attractive type so they
are identified with. (Lonely geeks are recast as desirable lone wolf
types with all the skills of alpha males.)
STEP 3: Game the YouTube algorithm so the next recommendations are how
"Sigma Males" get women. (I decided to bail at this point so I am not
going to view what is being recommended. Judging by the fact that "Sigma
Male" connects in Google searches to Incel websites, I shutter to think...)
[It's possible that "Sigma Male" is a term from a legitimate personality
system, but if so, its been at least partially co-opted by pop psychology.]
A discussion commenter stated: /"The mental health challenge is to help
people become aware of how AI is taking over their lives so that they
can manage the AI rather than have the AI manage them."/
My new resolve to periodically create new YouTube profiles to get out of
old tracking algorithms is one example of an adaptation.
*People need other ways to escape tracking to get out of boxes* -- like
the old BBS (bulletin board systems) that let you read (or not read)
every community comment from every poster without algorithms tailoring
your newsfeed.
*People need tools to recognize when they are being herded into specific
ways of thinking.* Like many of our political silos. Like my original
example above of an interest in male psychology potentially leading to
Incel-like "education" on how to be a "Sigma Male" who gets all the women.
*Businesses need some government regulation in what tracking they can do
-- in all environments, but especially the free ones.* People may need
to return to PAYING for their information sources so they themselves are
not the product.
Ironically, it was GOOGLE, whose "I'm feeling lucky" button below the
search engine field used to take users to a random website somewhere on
the Internet.
*We are now in need of actively maintaining personal ways to randomly
escape our information bubbles so as to better recognize them.**
***
-- Michael
*Michael Reeder, LCPC
*
*Hygeia Counseling Services : Baltimore / Mt. Washington Village location*
*410-871-TALK / michael(at)hygeiacounseling.com*
#psychology #socialwork #psychotherapy #research #incel #AI
#artificialintelligence #youtube #mentalhealth @[email protected]
@[email protected] @[email protected] @[email protected]
#Algorithms #personalitytests @silos
A brief update to the story I posted last January (see above) on "Sigma Males", YouTube Algorithms, and the funneling of lonely young men into unhealthy modes of thought.
My wife found the attached photo gem on social media. Its of an entire romance book series entitled "The Sigma Menace: The Complete Series".
The text of the graphic also says: "In this irresistible collection, wolf shifters break all the rules in the name of passion, love, and claiming their destined mates!"
Great... Do men read romance novels, or has this contamination spread to women too now?
"Sigma Male" is a bogus pop psychology concept linked with incels and -- perhaps more positively -- helping lonely young men feel better about themselves. But... they are irresistible loners and entitled to women... Not happy to see it going kind of mainstream.