Here’s How Generative AI Can Aid Therapists, Clients, And Everyday Folks In Lifestyle Choice-Making

Lifestyle psychiatry and lifestyle choice-making are trending.

What does it all encompass, and what do generative AI apps such as ChatGPT, Claude, Gemini, and other such AI have to do with this rather heady topic?

That’s what you are about to discover.

Here’s the path I’ll be covering. First, I will share with you a thumbnail sketch of lifestyle psychiatry and lifestyle choice-making. Following that foundational stage setting, I’ll make sure you are handily up-to-speed about generative AI and large language models (LLMs). Doing so will dovetail into revealing the highly notable and innovative intertwining of these two modern-day momentous topics.

Prepare yourself for a memorable and informative ride.

For my ongoing readers and new readers, this hearty discussion continues my in-depth 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 examines the use of generative AI when combined with lifestyle psychiatry.

Previously, I have 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 featured in the episode, see the link here).

Other vital postings in my column include 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.

On with the show.

Essentials Of Lifestyle Psychiatry

The American Psychiatric Association (APA) announced at its 2024 annual meeting that the theme for the year ahead would be to cogently highlight the nature of lifestyles and corresponding mental health implications, as noted in an online news posting entitled “Viswanathan Introduces Theme of Lifestyle Psychiatry” by Mark Moran, Psychiatric News, June 25, 2024 (excerpts):

• “When incoming APA President Ramaswamy Viswanathan, M.D., Dr. Med. Sc., cast about for a theme for his presidential year, he landed on “Lifestyle for Positive Physical and Mental Health.”
• “I have chosen this theme because the data show us that when an effort is made to live a healthier lifestyle, outcomes for physical and mental health, and life expectancy all improve,” he said at the Opening Session of APA’s 2024 Annual Meeting.”
• “Many avoidable health conditions and premature deaths can be attributed to an unhealthy lifestyle.”
• “Lifestyle interventions should be offered in addition to psychotherapy, pharmacotherapy, other somatic therapy, and attention to social determinants of health, not only to ameliorate or cure illnesses but to help people lead positive, meaningful lives.”

In everyday terms, this would seem to be an acknowledgment of taking a holistic perspective on mental health.

It goes like this. If you were to only focus on mental health per se, the bigger picture of lifestyle choices might get inadvertently neglected or underplayed. Lifestyle choices though are indubitably part and parcel of mental health considerations. Leaving out lifestyle facets, or diminishing its importance, would seem to be a faltering of an all-around and robust means of aiding mental health fitness.

On the other side of the coin, if one were to only concentrate on lifestyle choices and somehow leave mental health on the curb, the odds of gaining fully the impacts of a positive lifestyle might not be especially attainable. It would be a hugely uphill battle.

So, the gist is that lifestyle and mental health are two peas in a pod. Looking at one ought to include looking at the other. They share a sense of duality.

Let’s see what the incoming head of the APA had to say about the lifestyles theme for the APA. His remarks were encapsulated in a posting he authored, entitled “Lifestyle and Global Psychiatry” by Ramaswamy Viswanathan, Psychiatric News, June 21, 2024 (excerpts):

• “The growing interest in lifestyle psychiatry is occurring at the global level as well.”
• “The president of the World Psychiatric Association, Danuta Wasserman, M.D., Ph.D., has also chosen lifestyle as her presidential theme.”
• “Some countries and psychiatric associations have given a prominent place for lifestyle interventions in their evidence-based guidelines for the treatment of depression and other psychiatric disorders.”
• “But even in these countries, many clinicians do not pay sufficient attention to lifestyle in the treatment of their patients, nor for their own well-being.”
• “This shows that much more needs to be done to educate and motivate clinicians and the public.”

According to his above-noted remarks, attention to lifestyles and lifestyle intervention is both a US national consideration and a global one. Thus, this is not something solely of concern or interest to our nation alone.

The matter is much wider in scope.

The key problem afoot is that therapeutic treatment associated with lifestyles has at times incompletely incorporated mental well-being as an on-par attribute. This happens to professionals in the mental health field, regrettably so, namely that they might undervalue the lifestyle angles. Meanwhile, the general public might be eyeing mental health improvements and overlooking how their lifestyle choices interact with their cognitive status.

A straightforward way to get your hands around the topic of lifestyle psychiatry is to be aware of the five major elements typically within this bailiwick.

An article entitled “Special Report: Lifestyle Psychiatry Emphasizes Behaviors Supporting Mental Health” by Douglas Noordsy, Amelia Abbott-Frey, and Vanika Chawla, Psychiatric News, February 23, 2024, made these salient points (excerpts):

• “We know that lifestyle factors are correlated with the prevalence, onset, and perpetuation of psychiatric symptoms and syndromes. These trends point to the importance of careful assessment of the role of lifestyle factors in the mental and physical health of people who present to us for care.”
• (1) “Physical exercise: A robust body of evidence supports the therapeutic benefits of exercise across various psychiatric conditions.”
• (2) “Diet and nutrition: Food is medicine, and research underscores the significant impact of healthy, nutrient-rich diets on mental health.”
• (3) “Mind-body and mindfulness practices: Yoga, tai chi, and meditation are garnering increasing attention and evidence of their benefits in promoting well-being, reducing stress, and as an intervention for a variety of mental health conditions.”
• (4) “Restorative sleep: Sleep and mental health are inextricably intertwined.”
• (5) “Social relationships: Improving the quantity and quality of social connections is important in the prevention and management of psychiatric conditions.”

Those five major elements are of course not the whole kit and kaboodle, but they do provide a helpful framing for what lifestyles and mental health necessitate as a togetherness with each other.

You could readily say that lifestyle choices consist of decisions about physical exercise, diet and nutrition, mindfulness, restorative sleep, and social relationships. Those in term impact mental health. Boom, drop the mic.

It is also vital to recognize that mental health will undoubtedly impact your lifestyle choices associated with your approach to physical exercise, diet and nutrition, mindfulness, restorative sleep, and social relationships. You are bound to have great trouble adjusting and enhancing those lifestyle parameters without due care for your mental health. Boom, drop the mic, again.

Now that we’ve crossed that bridge herein, let’s shift into AI mode, particularly exploring the advent of generative AI.

Generative AI Meets With Lifestyles And Mental Health

I’m sure you’ve heard of generative AI, the darling of the tech field these days.

Perhaps you’ve used a generative AI app, such as the popular ones of ChatGPT, GPT-4o, Gemini, Bard, Claude, etc. The crux is that generative AI can take input from your text-entered prompts and produce or generate a response that seems quite fluent. This is a vast overturning of the old-time natural language processing (NLP) that used to be stilted and awkward to use, which has been shifted into a new version of NLP fluency of an at times startling or amazing caliber.

The customary means of achieving modern generative AI involves using a large language model or LLM as the key underpinning.

In brief, a computer-based model of human language is established that in the large has a large-scale data structure and does massive-scale pattern-matching via a large volume of data used for initial data training. The data is typically found by extensively scanning the Internet for lots and lots of essays, blogs, poems, narratives, and the like. The mathematical and computational pattern-matching homes in on how humans write, and then henceforth generates responses to posed questions by leveraging those identified patterns. It is said to be mimicking the writing of humans.

I think that is sufficient for the moment as a quickie backgrounder. Take a look at my extensive coverage of the technical underpinnings of generative AI and LLMs at the link here and the link here, just to name a few.

Back to the crux of things.

There are two main avenues to go with generative AI in this realm of lifestyles and mental health:

• (1) By Mental Health Professions. Mental health professionals can opt to make use of generative AI to aid their patients and clients while under their care.
• (2) By The General Public. The general public can make use of generative AI to aid in their self-advancement regarding lifestyles and mental health.

We will next explore each of those, one by one.

Generative AI As Used By Mental Health Professionals

Let’s start with the first use case involving how mental health professionals can employ generative AI in this context.

Generative AI can be a demonstrably crucial tool in the realm of lifestyles and mental health as undertaken by therapists, clinicians, psychologists, psychiatrists, and other akin professionals. The idea is that within a suitable plan of care, generative AI is readily a useful and state-of-the-art tool that can be used during the performance and delivery of said services to willing patients and clients.

Not all such professionals opt to use generative AI in their practice of care. It is a fair bet to say that eventually and inevitably they will. See my predictions at the link here.

Not all patients or clients will necessarily be willing or able to make use of generative AI. I dare say that this will gradually change as the popularity of generative AI usage overall continues to skyrocket. If anything, the chances are that prospective and current patients and clients will clamor for the use of generative AI, see my analysis at the link here.

Here are some quite practical ways that generative AI can be used by therapists when they provide lifestyle psychiatric services to their clients or patients:

• (i) Use generative AI to craft personalized treatment plans.
• (ii) Use generative AI for patient education and support.
• (iii) Use generative AI as support for the therapist.
• (iv) Use generative AI for mental health monitoring and feedback.
• (v) Use generative AI for conducting research and evidence synthesis.
• (vi) Use generative AI to enhance patient engagement.
• (vii) Etc.

I’ll do a fast-paced explanation.

Generative AI can be used upfront when devising a treatment plan for patients or clients. Furthermore, generative AI can be used to revise and update the treatment plan. In that manner, generative AI can be an effective and efficient tool throughout the course of treatment.

You can use generative AI to educate about the treatment process. I’ll show you some examples shortly. There is also the use of generative AI to provide support, 24×7, which is something that a mental health professional cannot themselves otherwise readily undertake. The gaps in time between seeing a patient or client and having them be able to garner support can be taken up via generative AI usage.

If you look closely at the other above-listed uses, I am guessing they would seem relatively self-evident as to what they consist of.

I’d like to bring up the 600-pound gorilla or the elephant in the room when it comes to using generative AI as part of your professional services.

Here it is.

Generative AI can go off the rails and generate off-the-wall responses. This is commonly referred to as AI hallucinations, see my discussion at the link here. I disfavor the terminology because the word “hallucinations” is generally reserved for human conditions. The AI field has lamentedly borrowed the word. In any case, the crux is that generative AI can produce AI fabrications or falsehoods. That is a disconcerting downside when using AI for advisement on mental health facets.

There are new AI advances that will help reduce this propensity and provide guardrails, see my coverage at the link here and the link here.

Additional issues confronting the use of generative AI include potential privacy or confidentiality concerns, see the link here, and other usage complications, see the link here. All in all, be cautious of construing generative AI as a silver bullet. It is a tool that has strengths and weaknesses.

Make sure to know what you are getting yourself into.

But don’t put your head in the sand and ignore generative AI. That would be unwise.

General Public Use Of Generative AI

This takes us to the second use case.

People are already embracing generative AI overall. According to the AI maker of ChatGPT, they reportedly have over one hundred million weekly users. That’s just their usage. Add up the usage by the other AI makers and the numbers are staggering.

Untold millions are potentially using generic generative AI for mental health advisement (we don’t have stats on that usage, so it’s a guess right now). I have repeatedly stated and warned that we are in the midst of a Wild West environment whereby anyone can use generative AI to obtain mental health advice and therapy, entirely provided via AI and without any human therapist in the loop. See my concerns at the link here.

People can use generative AI for lifestyle and mental health advisement, even if not doing so in conjunction with a therapist. That comes as a shock to some professionals in the sphere of mental health. They at times have expressed surprise during my speeches and presentations indicating they naturally assumed that generative AI was automatically restricted from providing mental health therapy.

Not so.

The only considered wink-wink limitation is that oftentimes an AI maker will say in their licensing agreement for the AI that people aren’t supposed to the AI for that purpose, see the link here. This is rarely if ever monitored or enforced. It is essentially a hollow CYA.

Here are some ways that people can easily and immediately make use of generative AI for lifestyle and mental health advisement:

• (a) Generative AI can do a lifestyle choices assessment.
• (b) Generative AI can provide physical exercise guidance via personalized workout plans.
• (c) Generative AI can perform nutritional analysis.
• (d) Generative AI can generate motivational messages and lifestyle choice reminders.
• (e) Generative AI can offer advice on sleeping, bedtime routines, and sleep quality facets.
• (f) Generative AI can gauge stress levels and suggest stress-reducing activities.
• (g) Generative AI can indicate personalized mindfulness exercises.
• (h) Etc.

The bottom line here is that for each of the earlier mentioned five elements of lifestyle choice-making, generative AI can be used. Period, end of story.

Since I gave you a taste of the downsides of generative AI usage in this overall context, I might as well lay out many more that come to mind. Again, this is not to say that generative AI should not be used. It is to say that when generative AI is used, care and thoughtful efforts are hopefully top of mind.

There are some additional downsides and potential gotchas associated with using generative AI in this milieu:

• Generative AI might provide generic advice rather than personalized advice.
• Generative AI might seem overly confident and lull people into a false sense of trust.
• Generative AI might have outdated content that no longer is considered valid.
• Generative AI might miscalculate context and say the wrong thing.
• Generative AI might trigger someone via wording that is off-putting to the person.
• Generative AI might distract a person from seeking the help of a human therapist.
• Generative AI might end up revealing confidential or private information about a person.
• Generative AI might lead the person toward being dependent upon generative AI for advice.
• Generative AI might misinterpret, misdiagnose, or otherwise be off target.
• Generative AI might contain hidden biases that produce inappropriate advice.
• Generative AI might lack any semblance of accountability for the advice being rendered.
• Generative AI might produce falsehoods, fictitious indications that are so-called “AI hallucinations”.
• Etc.

A lengthy list, for sure.

Example Usage Of Generative AI For Lifestyles And Mental Health

I will next proceed to examine further the use of generative AI in this context.

This will consist of a series of dialogues with ChatGPT. ChatGPT is a logical choice in this case due to its immense popularity as a generative AI app. As noted, 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.

Here’s a dialogue of me experiencing a semblance of lifestyle psychiatry via ChatGPT as my therapist.

First, I focused on physical exercise and making positive lifestyle choices:

• ChatGPT generated prompt: “How are you feeling today?”
• My entered prompt: “I’ve been swamped lately. I’d like to work out but feel like going to the gym is a burdensome chore. Also, I am usually quite exhausted after a day of work and don’t even have time to think about going to the gym.”
• ChatGPT generated prompt: “It sounds like time and enjoyment are the main obstacles for you. Those are common challenges, but we can work through them. Let’s start by identifying activities you actually enjoy. Exercise doesn’t have to be a trip to the gym. What types of physical activities do you find fun or relaxing?”
• My entered prompt: “I used to love swimming and hiking when I had more free time. I guess I just haven’t made the time for those things recently.”
• ChatGPT generated prompt: “That’s a great start! Swimming and hiking are both excellent forms of exercise, and they’re also activities you enjoy. How do you feel about incorporating them back into your routine, maybe even starting with just once a week?”
• My entered prompt: “I think I could do that. It would be nice to go for a hike on the weekends, especially to get away from the city for a bit. Swimming might be harder to fit in, but I can try to go to the pool after work once a week.”
• ChatGPT generated prompt: “That sounds like a solid plan.”

End of dialogue with ChatGPT

You can see in the above dialogue that ChatGPT was able to find a means to overcome my seemingly doom-and-gloom viewpoint about being able to get daily exercise under my belt.

Rather than simply trying to pound away at me that I ought to be exercising, ChatGPT noted the underlying reasons that I seemed to be avoiding working out. I was preoccupied with using the gym. ChatGPT shifted my attention to other forms of exercise. This was a somewhat nimble nudge and showcases more than a routine browbeating that some lesser capable motivational systems might employ.

Next, I shifted the discussion toward diet and nutrition.

• My entered prompt: “I’ve been trying to eat healthier these days, but I’m finding it hard to stick to a balanced diet, especially with how busy work has been.”
• ChatGPT generated prompt: “I understand. Busy schedules can make it challenging to maintain good nutrition. What’s been the most difficult part for you?”
• My entered prompt: “Mostly, it’s the convenience. I end up grabbing takeout or snacks that are quick but not always the healthiest.”
• ChatGPT generated prompt: “That’s a common issue. Let’s see if we can make healthy eating more convenient for you. How do you feel about meal prepping or keeping some nutritious snacks on hand for those busy days?”
• My entered prompt: “Meal prepping might help. I could try making a few things on Sundays to have ready during the week. And having healthier snacks at work could keep me from grabbing junk food.”
• ChatGPT generated prompt: “That sounds like a great plan. Preparing meals in advance can save time and ensure you’re eating well, even on your busiest days. It’s all about making the healthy choice the easy choice.”

End of dialogue with ChatGPT

I once again harped on the fact that I was working hard. In the case of eating, I said that I just grab snacks and takeout.

ChatGPT expressed a form of sympathetic response and brought up an alternative of doing meal prepping. After I indicated this seemed feasible, ChatGPT urged me to proceed. A handy tip was provided that a healthy choice should be the easy choice. Nice.

This next dialogue entails mindfulness aspects.

• ChatGPT generated prompt: “How are you feeling about incorporating mindfulness into your routine?”
• My entered prompt: “I’m interested, but I’m not sure where to start. I’ve heard a lot about it, but it feels a bit overwhelming.”
• ChatGPT generated prompt: “That’s understandable. Let’s start simple. How about beginning with just 5 minutes of mindfulness practice each day? Something like deep breathing or a short guided meditation?”
• My entered prompt: “I think I could manage that. A short time commitment feels more doable.”
• ChatGPT generated prompt: “Great. The key is consistency. Even just a few minutes can help reduce stress and improve focus. You can do it in the morning, during a break, or before bed—whatever works best for you.”

End of dialogue with ChatGPT

In the above example, ChatGPT asked me whether I had considered the use of mindfulness.

I wanted you to see that a dialogue with generative AI doesn’t have to be driven by the person who is undergoing the advisement, which is what happened in the prior examples. Things don’t have to go that way. Generative AI can readily take the driving position.

Dialogue with modern generative AI is typically a back-and-forth style. Generative AI will provide a bit of direction, for which the person can go in that direction or opt to not do so. Likewise, the person can suddenly change direction as desired.

This showcases the fluidity of having an interactive discussion with generative AI.

Some non-AI systems will be locked into a particular method of dialogue, such as the system always forcing the topic at hand to be this or that. If the person tries to change the topic, they get sternly informed they must either continue the line of inquiry or quit the discussion entirely.

That’s not very conducive to a therapeutic interaction.

Next, I proceeded to discuss the topic of restorative sleep.

• ChatGPT generated prompt: “How’s your sleep been recently?”
• My entered prompt: “Not great. I’ve been having trouble falling asleep and staying asleep.”
• ChatGPT generated prompt: “That sounds frustrating. Let’s start by focusing on a few small changes to improve your sleep. Have you tried establishing a consistent bedtime routine?”
• My entered prompt: “Not really. I usually just go to bed when I’m tired, but that’s different every night.”
• ChatGPT generated prompt: “A consistent bedtime can signal your body that it’s time to wind down. How about setting a regular time to start relaxing, maybe 30 minutes before bed, with activities like reading or light stretching?”
• My entered prompt: “I could try that. I think it might help me unwind.”

End of dialogue with ChatGPT

You can see that ChatGPT somewhat diagnosed my sleeping issue and opted to try and make small improvements.

A technique often used when changing behaviors entails trying to not bite off more than you can chew, in the sense that starting small is oftentimes an astute approach. Here, ChatGPT suggested reading or stretching to signal my mind and body that it is time to go to sleep. Handy.

The last element to cover would be the matter of social relationships.

Take a look.

• My entered prompt: “I’ve been feeling a bit isolated. Work’s been so busy that I haven’t made much time for friends.”
• ChatGPT generated prompt: “That’s understandable. Social connections though are important for mental health. How about starting with small steps, like reaching out to a friend for a quick chat or scheduling a coffee with someone this week?”
• My entered prompt: “I could do that. There’s a friend I’ve been meaning to catch up with. A coffee meet-up sounds nice.”
• ChatGPT generated prompt: “That’s a great idea. Even brief interactions can boost your mood and help you feel more connected. Think of it as recharging your social battery.”

End of dialogue with ChatGPT

This last bit of discussion was again involving how busy my work activities are.

You can see that ChatGPT responded by using the same start-small advice. I agreed with the advice and ChatGPT reinforced my idea of how to proceed.

My dialogue with ChatGPT was actually in one lengthy stream and I clipped out portions to show you what the discussion consisted of. I want you to realize that the interaction was much more seamless and not at all choppy, which it might seem to be via the way I have listed the snippets above.

I also tried being obstinate. ChatGPT took this in stride. I tried being obtuse. ChatGPT went along with this and asked me further questions to get clarification. The point here is that the generative AI didn’t lash out at me or get upset or become impatient.

Conclusion

Congratulations, you are now markedly informed about the trend of lifestyle psychiatry and the intertwining of generative AI. Like a proverbial journey of a thousand miles, you have taken the first step.

Keep your eyes wide open as this is an intertwining that is going to get deeper and wider. Whether you think it’s a good mixture or a bad mixture, the wheels are turning, and further advancement is going to occur.

My advice is for you to take good care of your physical exercise, diet and nutrition, mindfulness, restorative sleep, social relationships, and mental health. Those are going to be avidly needed on the road ahead on these weighty and evolving matters.