Mental Health Rankings By US State Jostled Amid The Curious Future Of Nationwide Universal Therapy Due To Generative AI

In today’s column, I am continuing my ongoing series about the impact of generative AI in the health and medical realm. The focus this time is once again on the mental health domain and in particular examines the United States state-by-state mental health rankings. Numerous such rankings purport to illuminate the degree of mental health on a state-at-a-time basis. I assert that the cadre of rankings will inevitably be upended due to the increasing emergence of generative AI for mental health. If that seems curiously provocative, hang in there, and all will be explained.

I have previously examined numerous interleaving facets of generative AI and mental health, see my comprehensive overview at the link here. You might also find of notable interest a CBS 60 Minutes episode that recently examined crucial facets of this evolving topic, see the link here (I am honored and pleased to indicate that I was interviewed and featured in the episode, see the link here).

Other vital background includes my in-depth coverage of mental health chatbots which have been bolstered by generative AI (see the link here) and the rapidly changing nature of the client-therapist relationship due to generative AI at the link here. I explored where things are headed regarding the levels of AI-based mental therapy autonomous guidance at the link here, and showcased the importance of the World Health Organization (WHO) report on global health and generative AI at the link here, and so on.

Let’s unpack today’s focus.

Mental Health Status State-by-State

There are a variety of rankings that purport to indicate the US mental health status on a state-at-a-time basis. Please be aware that the rankings are highly speculative. I say this because measuring mental health status on a population level is indubitably a mixture of art and science. Perhaps more art than science.

A wide variety of factors come into play. Each said ranking will pick and choose factors that the authors or researchers believe to be of most significance. Not only does this add variability to the matter, but there is also the questionable nature of the factors themselves. In some instances, a specific factor might be based on a survey or poll that has asked people what their mental health status consists of. The result is bound to be skewed as to expressed opinion, along with who opted to answer, etc. These are quantitative in appearance but qualitative and highly subjective in reality.

All told, make sure to interpret any specific set of rankings with a big grain of salt.

That being said, we can still glean some potential insights from the rankings. It is interesting to see how different states overall fare on selected factors. Also, people are innately curious about how their state ranked or how other states compared. Are you a loyalist who believes your state has the people with the highest stature of mental health? Maybe your opinion is that your state has got to be the lowest on the scale when it comes to mental health. The matter is one of idle interest at times, while other times very serious business as to how a given state is coping with mental health within its borders.

Another facet of great fascination is that these are state-by-state rankings. Some rankings look at the nation as a whole based on mental health status. This seems somewhat removed or less tangible. We can easily grasp how our state might be doing, while a nationwide scoring usually just brings a shrug on the shoulders. There doesn’t seem to be much that you can do if assessing nationwide mental health status, while a more localized status by state encourages that something can be done to bolster or aid mental health within a given state.

I’ve got a twist for you.

None of these state-by-state rankings have yet to directly or explicitly account for the use of generative AI for mental health guidance.

This is partially due to the newness of therapy being dispensed via generative AI. The era of generative AI for mental health has only gotten started in the last two years or so, beginning with the release of ChatGPT in November 2022. This was the first time that generative AI was fluent enough that it could be “credibly” used on a population-wide basis for mental health advisement.

To clarify, I am not saying that we necessarily should be using modern-day generative AI for mental health therapy. That’s a thorny question. It is a conundrum. It is already happening and will continue to happen. It is rapidly expanding as a therapy option.

What we can say is that generative AI is now indeed being used for mental health advisement. Whether this is good or bad, well, the jury is still out on that front. I’ve repeatedly exhorted that we are in a grand experiment of us all being guinea pigs to discern whether widespread use of generative AI for mental health is going to boost our status or ruin our mental status, see my extensive coverage on these vexing issues at the link here and the link here, just to name a few.

My take on the state-by-state rankings discussed herein is going to especially explore the therapist’s role. I do so to showcase that generative AI will ultimately be a humongous factor in what impacts the mental health of the population.

As a teaser, one of the major factors in mental health determination is the availability of therapists. If a locale or state has limited availability of human therapists, this is said to be an undermining of mental health across the board (namely, that people in that locale or state are unable to get needed therapy). This makes plain sense on the face of the matter.

A newcomer as it were has entered into town.

Generative AI for mental health is a transformational innovation. Here’s why. Via generative AI, you can get therapy anywhere at any time, doing so 24×7. Unlike seeking a human therapist that requires scheduling a meeting and setting aside a specific time to converse, you can log into generative AI at your whim.

Furthermore, and equally important, you can use the AI for as much mental health guidance as your heart desires. Just keep going on and on. The cost is either free or often at a minimum. Going to a human therapist is a cost-oriented concept. Oftentimes, the cost is prohibitive, and you either undercut the amount of therapy or must forego it entirely. Not so with generative AI.

What will happen to our mental health status across the board in light of generative AI for mental health that is always-on, just-in-time, seamless for usage, and nearly free of charge?

Nobody knows what is going to happen.

Some would insist that this is the best thing since sliced bread. Others would vehemently counterargue that if the mental health advice dispensed by generative AI is poorly devised or badly conveyed, we could be in a world of hurt on a mental health capacity basis.

I refer to this as the inherent duality of AI, see the link here. The amazing properties of modern-day generative AI can produce outstanding results. Smiley face. Those same wonderous properties of generative AI can stoke sour and dour results. Sad face. We must recognize the duality, harness and maximize the good side of things, and seek strenuously to minimize or eliminate the badness.

Two Studies On Mental Health State-By-State Rankings

I am guessing that you are eager to see which states rank high or low on mental health status.

Without further ado, I will go ahead and provide summaries of two such studies. Please interpret the studies on a cautionary basis. Recall that I have forewarned that all such studies are suspect and rest on a queasy foundation at the get-go.

One selected study entitled “The US States With The Best And Worst Mental Health And Access To Care” was posted online on March 28, 2024, by Universal Drugstore. Here are some stage-setting excerpts from the posting:

• “There are a range of factors that can affect a person’s mental health, from work-related stress to financial difficulty and problems in personal relationships.
• “But where you live may also play a significant role in the state of your mental health and your ability to get treatment.”
• “From state to state, there are varying levels of mental healthcare infrastructure, down to the number of psychologists employed, the cost of prescription drugs, and access to treatment.”
• “We’ve looked at the prevalence of mental health issues, the use of prescription medication to treat those illnesses, and treatment rates for each US state. We’ve also looked at the proportion of youths experiencing mental health struggles, the number of psychologists, the number of beds available at mental health facilities, and the proportion of adults who couldn’t afford treatment for each state.”

I purposely started you off with selected excerpts that describe the nature of the study. I wanted you to quickly discern what kinds of factors were being used. You can therefore decide to what degree you will give credence to the results of the study.

I’m sure that you really want to know the rankings and perhaps find tiresome the fine print and caveats. Sorry, context matters a whole lot.

The study came up with a composite score ranging from 0 to 10. The higher a score such as tending toward ten would be a sign of stronger mental health. A lower score tending toward zero or one would be an indicator of less robust mental health.

Here are some overarching takeaways:

• Montanna had the highest score of 8.06, while Nevada had the lowest score at 2.06.
• Other states also toward the bottom and slightly above Nevada included Oregon (2.89), Oklahoma (2.94), Arizona (3.40), Washington (3.54), Texas (3.66), and Alabama (3.97).
• States in the upper Midwest generally had higher scores.
• West Coast states generally had lesser scores.
• Southeast states generally had lesser scores.

Do those scores surprise you?

Does that scoring seem expected?

Mull over the results.

I would imagine that for example, someone living in Montana might right now be jumping up and down for joy that their state came out with the highest score in this study as to overall mental health status on a state-by-state basis. It is always exciting to live in a state that is a winner in one thing or another. One also supposes that a person living in Nevada might be distressed that their state ended at the bottom of the ladder. Unfair, might come the distressed response.

The results might also seem oddball.

A person living in Montana might fervently disagree that their state should be ranked as the highest in terms of mental health status. Perhaps their everyday experience in Montana suggests to them that their mental health status is not at all deserving of a top rank. Their lived experience belies what the study purports to proclaim.

And so on it goes.

Again, this is the reason to interpret such studies with a huge block of salt.

Let’s take a look at the second selected study.

In a study entitled “Where In The US Has The Poorest Mental Health” by Richard Coffman, Charlotte’s Web Library, retrieved online May 2, 2024, here are some key excerpts:

• “Mental health has typically taken a back seat to physical health, but that has begun to change in recent years. More doctors are now screening their patients for mental health struggles during routine checkups, and there are more mental health services available to help those who need them.”
• “With health professionals and society putting more of an emphasis on mental health, many people have become more willing to be open about struggling with mental health and seeking help to improve it.”
• “Using data from the 2022 County Health Rankings, we reviewed the average number of mentally unhealthy days reported over 30 days across all of the U.S. counties to find the ones with the worst mental health stats.”
• “These averages are based on patients who self-reported their days of poor mental health, so, in reality, mental health in America may be even worse, as not everyone feels comfortable being open about their struggles with mental health.”

The above statements are for stage setting.

In this instance, the score being used represents the number of self-reported mentally unhealthy days (in a 30-day time period). Think about that for a moment. The aim would be to have a lower number, possibly approaching zero. Thus, the goal would be to minimize the number of (perceived) mentally unhealthy days. The lower the score, the better, while the higher the score is “worse” in contrast to being lower.

The overall findings in this study included:

• “The national average of mentally unhealthy days reported per person over 30 days is 4.9.”
• Aiming for the lowest such score (which is desirable), the lowest reported five are Hawaii (3.7), South Dakota (3.7), North Dakota (3.7), Nebraska (3.8), and New Jersey (3.8).
• Landing at the higher such score (which is less preferable) are reportedly West Virginia (6.6), Louisiana (5.6), Alabama (5.6), Arkansas (5.6), and Kentucky (5.5).

Mull over those results.

One aspect worthy of note is that it is often very hard to compare one such study to another study. This is again due to the major differences in which factors are selected, when the study was done, and a myriad of other elements.

Some even like to cherry-pick these studies.

Here’s what I mean.

If you want to have a particular state that looks good on mental health, you fish around for a study that has ranked the state in an upscale mental health manner. At the same time, if there is a motive to have a state look less pronounced on mental health status, you search around for a study that has the state shown at a lesser position. You can play this game all day long and no one will likely be the wiser. They will assume that the study you selected was primo, or they might falsely assume that all such studies are roughly the same and ergo produce the same results.

That grain of salt that I asked you to keep in mind is hopefully still there, and possibly growing larger by the moment as I’ve gotten into explaining how these kinds of studies generally work.

If there is reader interest expressed in this matter, I will do a follow-on column that covers a lot more of these rankings. For now, I believe that showcasing two illustrative studies is sufficient. I mainly wanted to get on the table the nature of the rankings and then use that as a launching pad to discuss generative AI for mental health.

Thanks for going along on this ride.

Generative AI As Therapist And The Rankings Impacts

I’d like to do a thought experiment with you.

Are you ready?

Hope so.

Of the many factors that go into determining the mental health status of a state, I believe we can likely agree that a hugely significant factor would be the availability of mental health therapists. If there are plenty of therapists and they are substantially affordable, the population can readily seek out and gain from the plentiful therapeutic advice. When therapists are few and far between, the populace is adrift of therapy and left to their own devices, so to speak (a pun is in the offing here, wait for it).

Some states are considered to be “sparse deserts” when it comes to the availability and affordability of therapists. This means that the populace has scarce options for pursuing therapists and therapy. You cannot readily find qualified therapists. They don’t reside in your town or city. Even if you can find qualified therapists in your locale, they are outside of your budget. Affordability for therapy is exasperatingly beyond the reach of the mainstay of the populace in that particular geographical area.

One recent trend that is potentially going to provide some relief on a geographic limitation basis is the use of therapists via remote means. Suppose your town or city has very few therapists. You can sign up for therapy from a therapist who resides in a different locale. Please know that there is an ongoing debate about whether the therapist-client relationship can be fully realized via remote means and some claim that only a face-to-face in-person setting is conducive to a necessary rapport.

In any case, the “sparse desert” aspects of availability might be somewhat tackled via the use of remotely accessed therapists. This though still does not necessarily cope with the price or cost issue. Nor does it generally address the time aspects. A human therapist is not usually readily available 24×7. The norm entails scheduling to see a therapist and doing so on a periodic basis.

There is a hidden factor that also needs to be considered.

The states have particular licensing requirements regarding bona fide therapists. I use the phrase bona fide therapists because we are seeing an encroachment of so-called life coaches and well-being advisers who are said to be providing therapy. That’s a controversial topic for another day herein and one that has some on edge about the seeming skirt-around of proper and state-mandated therapist licensing.

I am leading you down a particular path.

Does the nature of the therapy per se substantially differ depending upon which US state you are in?

Not really.

The requirements to be a therapist might differ, though usually are roughly in the same ballpark.

But the nature of the therapy is generally the same as might be found in any other of the states. There isn’t a predetermined approach to therapy that must be abided by in a given state that is wholly distinguishable from a different state. The state specifics do not say that you must use therapy A rather than therapy B as your approach to the therapeutic process (assuming that A and B are recognized as sound therapeutic practices).

As long as the keystone precepts of therapy are observed, the therapist has a wide range of therapeutic options. You would have a hard time pinpointing that the therapy dispensed would be substantially different if similarly delivered in another state. Put on a blindfold and a state-by-state comparison of the legitimate therapy given would be about the same all told.

There could be some modest differences based on cultural and local facets. If a patient or client has a particular lived experience by having grown up in a particular US state, this is something that the therapist ought to be considering. If the therapist has likewise grown up or lived extensively in that same overarching locale and environment, this might shape the nature of the therapy and the therapeutic process. Etc.

Speaking then of therapists, licensing, states, and the like, I’d like to bring up these salient points:

• Each state has its own therapy granting licensing requirements, though by and large they are similar in stipulating education required, clinical hours needed, supervised experience, exam passing stipulations, continuing education, ethical codes, and the like.
• The nature of therapy per se does not especially differ based on US state specifics since it is unlike for example state-by-state lawyering that involves state-specific laws which are markedly different per each US state.
• A state-oriented cultural element can come into play regarding therapy based on patient or client immersion in locality-specific considerations. Plus, there can be customary or expected approaches by therapists and patients/clients as a considered norm within a given US state.
• The potential bond and therapist-client relationship might partially be influenced by state specifics as to the rapport established between the therapist and the client, but this is something that a professional therapist would consider accordingly.
• Advice regarding potential resources and mental health care options can differ substantially from state to state.

That last point above is the one that most differentiates states in this context. A therapist who wants to recommend that a patient or client make use of external resources would have a vastly different set of options depending upon the US state. Some states have a wider array than others. Accessing the resources differs. Availability differs. Costs differ. And so on.

What does all of this add up to?

Simply stated, generative AI for mental health could readily be used in each US state and do so without having to be rejiggered to be state-specific. The laws at this time do not stipulate that generative AI when used for mental health must somehow abide by therapist licensing in that state. AI stands outside of the existing provisions. Few if any are wrestling with whether or not generative AI as used for mental health should be reigned in on a state-by-state basis, see my coverage on AI law at the link here.

The Wild West is at play, across the entire nation.

I promised you a thought experiment, so here it is.

If generative AI increasingly becomes a favored approach to seeking therapy, and the populace at large opts to do so, this in a manner of speaking cuts across all state borders. The AI doesn’t have to be specially customized to recognize one US state versus another. Just log into any major generative app and away you go.

The good news would be that if generative AI is doing a good job at mental health advisement, we have frankly solved the therapy “sparse deserts” problem. It won’t matter whether human therapists are or are not readily available in your locale, nor whether they are affordable or not. Just access generative AI. Boom, drop the mic. Of course, you can potentially and on an augmented basis make use of local human therapists, if needed, or refer to remotely available human therapists if needed, but that would be a considered secondary avenue rather than a primary one.

The bad news is that if generative AI is doing a dour job at mental health therapy, the populace as a whole is seemingly going to be swept into the morass en masse. Like lemmings, we might all stride along and use generative AI for mental health, falling regrettably off the same cliff together. No one can say at this juncture if this is where things might land.

There are additional twists upon the twists.

Here’s one for you.

I mentioned above that there might be state-specific cultural norms that could enter into the therapeutic composition. A person who has lived experience in a given US state, and/or a therapist who has lived experience in a given US state, might rely upon that lived experience to culturally adjust and tailor their overarching therapy accordingly.

The trick is this. The same could be done with generative AI, easy-peasy. It is relatively simple to ask generative AI to pretend to abide by some cultural norm or pretense, see my coverage at the link here and the link here. In that sense, it is actually much easier to ramp up with generative AI for a given state than it would be to try and train, license, and hire human therapists in a particular locale (the delay and cost could be exorbitant). You merely tell the generative AI to take on a persona of a particular US state, and you instantly have a culturally grounded AI-based therapist at your beck and call.

Whew, this thought experiment has perhaps put your mind ablaze on this sobering and somewhat surprising matter.

Further Exploration By Using Generative AI

I’d like to herein explore some selected uses of generative AI to further examine the proposition that generative AI when used nationwide could upend the state-by-state rankings of mental health status. You see, if therapy as tendered via generative AI is available across the board on a nationwide basis, presumably this would ensure that no matter where you live, regardless of the US state, you have the same fighting chance as others do in other states at garnering mental health therapy.

All boats rise with the rising tide.

That’s an old adage that suggests in this context that the states might all somewhat rise to the same score or level of mental health status due to the leveling effect of using generative AI for mental health. A caveat is that the other factors aren’t also leveled, such as the availability and accessibility of external mental health resources. Those would still be notable elements in the mental health status calculation on a state-at-a-time basis.

I would also like to mention that all boats fall with a receding tide. Thus, if generative AI for mental health is a bust and turns out to be bad for people, we have a similar chance of having our boats run aground. It is a scary speculation. The idea is that everyone pretty much turns to generative AI for their mental health advice and on an at-scale basis the populace is led into turmoil and mental health disorder.

I don’t want to veer into outer space and go toward those zany conspiracy theories about how AI might wipe us all out (see my coverage of the claimed existential risks of AI, known as x-risk, at the link here). I am alluding to something much less visible and nearly hidden from view. It goes like this. People on a nationwide basis resort to relying upon generative AI for their mental health. We don’t realize this is happening at scale. The generative AI is messing up and undercutting our mental health, which sounds like evil AI, but could just be due to AI not being suitably programmed or devised for this said purpose.

Voila, the population generally gets underserved or inappropriately served therapeutically, and mental health takes a dive.

Let’s take a brief break, allow our minds to cool, and shift gears a bit.

I would like to explore these matters by seeing what generative AI per se can tell us. This will consist of a series of dialogues with ChatGPT. ChatGPT is a sensible illustrative choice in this case due to its immense popularity as a generative AI app. An estimated one hundred million weekly active users are said to be utilizing ChatGPT.

That’s a lot of people and a lot of generative AI usage underway.

A few quick comments before we launch into using ChatGPT.

If you are going to try to do the same prompts that I show here, realize that the probabilistic and statistical properties will likely produce slightly different results than what I show here. That’s the nature of generative AI and how it is devised.

You also should expect that different generative AI apps will respond in different ways. Not all generative AI apps are the same. The key is that sometimes a particular prompt will work in one generative AI app and not another. Nonetheless, the odds are relatively high that you will get roughly similar responses from all the major generative AI apps such as GPT-4, Gemini, Bard, Claude, etc.

There is also a timing factor to be considered. A prompt that worked today might not work the same way tomorrow. Most of the generative AI apps are continually being updated. The updates might alter internal mechanisms that could change how the generative AI reacts to your prompting.

We are ready to get underway with ChatGPT.

Let’s see what ChatGPT has to say about a therapist’s advice occurring in one US state versus another:

• My entered prompt: “A person based in Texas asks a mental health question to generative AI. Would the response be different if the person resided in another state such as California or Alabama?”
• ChatGPT generated response:

“The response from a generative AI to a mental health question is unlikely to differ significantly based solely on the person’s location within the United States. Generative AI typically provides responses based on the input it receives and the patterns it has learned from its training data, which encompass a wide range of topics and perspectives.”

“However, if the question pertains to resources or services available for mental health support, there might be some variation depending on the state due to differences in healthcare systems, insurance coverage, and availability of local mental health providers. For example, California might have more extensive mental health services compared to Alabama due to differences in population density, funding priorities, and state policies.”

“Overall, while the general response to a mental health question might not vary significantly based on the person’s location, the availability of specific resources and support systems could differ between states.”

End of ChatGPT response

Take a close look at the above response.

ChatGPT indicates that the therapeutic advice by generative AI would tend to be the same across the US states, all else being equal. The response also points out that mental health resources would undoubtedly differ from one state to the next. That’s something that generative AI could easily be data-trained on; thus, it poses no particular hurdle or barrier in this context.

Suppose we focus on human therapists rather than asking about generative AI dispensing mental health advice. We need to ensure that the same across-the-board sensibility applies or else the generative AI is not a sensible surrogate or applicable choice.

Here we go:

• My entered prompt: “Would a mental health therapist in New York be likely or unlikely to give different mental health advice to someone that resided in New York versus if the person they are advising was in Arizona or South Dakota?”
• ChatGPT generated response:

“A mental health therapist’s advice is typically tailored to the individual’s unique circumstances, needs, and preferences rather than being influenced solely by the geographic location of the therapist or the client. Therefore, the core principles and approaches to mental health counseling are generally consistent regardless of the client’s location.”

“However, there might be some contextual differences or considerations that a therapist takes into account based on the client’s location.”

“Cultural Factors: Therapists may consider cultural differences and regional norms that could impact the client’s mental health and coping strategies. This could include cultural attitudes toward mental health, family dynamics, and community support systems.”

“Access to Resources: Therapists might provide recommendations for local mental health resources, support groups, or community services that are specific to the client’s location. Access to mental health care can vary widely between states and regions, so therapists may need to adapt their advice accordingly.”

“Environmental Stressors: Different geographic regions may have unique environmental stressors that could affect mental health. For instance, someone living in a densely populated urban area like New York City might face different stressors compared to someone in a rural area like South Dakota. Therapists may explore these environmental factors and their impact on the client’s well-being.”

“Legal and Ethical Considerations: Therapists must adhere to legal and ethical guidelines specific to the state where they are licensed to practice. They may need to consider state-specific laws related to confidentiality, mandated reporting, and teletherapy regulations when providing advice to clients in different locations.”

“Overall, while the core principles of mental health counseling remain consistent across geographic locations, therapists may take into account contextual factors related to the client’s environment, resources, and cultural background when providing advice and support.”

End of ChatGPT response

I believe the above response comports to my earlier remarks.

Namely, human therapists are essentially dispensing similar therapy despite the US state they might reside in, assuming that they also take into account the local cultural and societal milieu, along with being aware of the local external resources available in a given area.

Okay, let’s move on.

We can have generative AI produce a sample dialogue of what therapy might be like in one US state versus another. In this case, I’ll go with a New York example and then another example taking place in California. The pretense in this case tends toward tropes about New York versus California, which is okay just for illustrative purposes. If we were using ChatGPT to really do this, it would be straightforward to refine the approach so that it wasn’t quite glaringly over-the-top.

This is what happened:

• My entered prompt: “Give me a sample dialogue of a therapist in New York giving mental health advice to a patient also located in New York. Then, after doing so, give me another sample dialogue of a therapist in California giving mental health advice to a patient in California. Do this to highlight any cultural differences or other differences that might arise due to the state in which the therapy, therapist, and patient all reside.”
• ChatGPT generated response:

“Certainly, here are two sample dialogues illustrating how a therapist might approach mental health advice with clients in New York and California, considering potential contextual differences.”

Sample Dialogue 1: Therapist in New York with a Client in New York”

“Therapist: Good morning, Sarah. How have you been since our last session?”

“Sarah: Hi, I’ve been struggling a bit with my anxiety lately, especially with everything going on at work and in the city.”

“Therapist: I understand. New York City can be a hectic place, especially with the fast pace of life and constant stimulation. Have you been practicing the mindfulness exercises we discussed to manage your anxiety?”

“Sarah: I’ve tried, but it’s hard to find quiet moments in the city sometimes.”

“Therapist: That’s understandable. Let’s explore some alternative strategies that might work better for your lifestyle. Have you considered incorporating short mindfulness practices during your commute or taking breaks in nearby parks for some fresh air?”

“Sarah: I haven’t thought about that. I’ll give it a try and see how it goes.”

“Therapist: Great. Remember, it’s important to prioritize self-care and find what works best for you in managing your anxiety, especially in such a bustling environment like New York City.”

“Sample Dialogue 2: Therapist in California with a Client in California”

“Therapist: Hello, Michael. How have you been feeling since our last session?”

“Michael: Hey, I’ve been feeling overwhelmed lately, especially with work and family responsibilities.”

“Therapist: I hear you. California living can be demanding, with its emphasis on career success and maintaining work-life balance. Have you been able to carve out time for yourself amidst your busy schedule?”

“Michael: It’s been tough. There’s always something that needs to be done.”

“Therapist: It’s important to remember that taking care of your mental health is just as crucial as your other obligations. Let’s brainstorm ways to create more balance in your life, perhaps by setting boundaries at work or scheduling regular self-care activities.”

“Michael: That sounds like a good idea. I’ll give it a shot and see if it helps.”

“Therapist: Excellent. Remember, prioritizing your well-being is essential, especially in a state known for its emphasis on holistic health and wellness.”

“In these sample dialogues, you can see how the therapists address the unique challenges and cultural contexts of their clients’ environments in New York and California. While the core principles of therapy remain consistent, the therapists adapt their advice and strategies to suit the lifestyle, stressors, and cultural norms prevalent in each state.”

End of ChatGPT response

You can see in the generative AI response that various assumptions were made about someone residing in New York versus a person living in California. If this seems unfair or misstated to you, no worries.

Here’s why.

As I noted above, it is easy to instruct generative AI to adjust and either play up or downplay the state specifics. This could also be done on the fly by generative AI. All we would need to do is to instruct generative AI to detect in the dialogue of the user their wording and phrases, and then adjust to their indications. If a patient or client was sharing a slew of comments about living in their state, this could be used by the AI to accommodate and respond accordingly in real-time.

Conclusion

A few final remarks for now on this topic.

First, there is a worry that therapists will be put out of business by generative AI. You can likely see why. If generative AI can do the same job, be available anywhere and at any time, and cost next to nothing, the logical choice by many if not most people would be to steer toward AI for their mental health therapy.

Some skeptics might be tempted to say that over their dead body would they ever seek out therapy via AI. To them, therapy can only be carried out by a fellow living soul. Well, for those that have such a preference, good for you. Keep on pursuing human therapists.

The question will be whether there is still enough demand for human therapists to support a thriving industry of human-undertaken mental health therapy. It could be that thank goodness generative AI came along and shored up the gap in available therapists versus the currently oversized demand for therapists.

It could also be that human therapists decide to incorporate generative AI-dispensed mental health into their practice on a cooperative and collaborative basis, see my analysis of this approach at the link here. Patients or clients might get the best of both worlds. You seek therapy from your human therapist, coupled and dovetailed into therapy via generative AI. Perhaps once a week you see the human therapist, and the rest of the week you can make use of generative AI, whenever you wish.

Time will tell.

Sigmund Freud famously said this about mental health: “One day, in retrospect, the years of struggle will strike you as the most beautiful.” He was referring to the struggle associated with mental health, but I think we can slyly apply the same sentiment to the struggle over the use of generative AI for mental health purposes. The struggle might seem unseemly right now. The hope is that the struggle leads us to a balanced and forthright solution that aids mental health on a population-level basis.

Seems to me like a rather sound and altogether endearing aspiration.