logo
Orchestrating Mental Health Advice Via Multiple AI-Based Personas Diagnosing Human Psychological Disorders

Orchestrating Mental Health Advice Via Multiple AI-Based Personas Diagnosing Human Psychological Disorders

Forbes6 days ago
Orchestrating multiple AI personas in the medical domain and in mental health therapy by AI is a ... More promising approach.
In today's column, I examine a newly identified innovative approach to using generative AI and large language models (LLMs) for medical-related diagnoses, and I then performed a simple mini-experiment to explore the efficacy in a mental health therapeutic analysis context. The upshot is that the approach involves using multiple AI personas in a systematic and orchestrated fashion. This is a method worthy of additional research and possibly adapting into day-to-day mental health therapy practice.
Let's talk about it.
This analysis of AI breakthroughs is part of my ongoing Forbes column coverage on the latest in AI, including identifying and explaining various impactful AI complexities (see the link here).
AI And Mental Health Therapy
As a quick background, I've been extensively covering and analyzing a myriad of facets regarding the advent of modern-era AI that produces mental health advice and performs AI-driven therapy. This rising use of AI has principally been spurred by the evolving advances and widespread adoption of generative AI. For a quick summary of some of my posted columns on this evolving topic, see the link here, which briefly recaps about forty of the over one hundred column postings that I've made on the subject.
There is little doubt that this is a rapidly developing field and that there are tremendous upsides to be had, but at the same time, regrettably, hidden risks and outright gotchas come into these endeavors too. I frequently speak up about these pressing matters, including in an appearance last year on an episode of CBS's 60 Minutes, see the link here.
If you are new to the topic of AI for mental health, you might want to consider reading my recent analysis of the field, which also recounts a highly innovative initiative at the Stanford University Department of Psychiatry and Behavioral Sciences called AI4MH; see the link here.
Orchestrating AI Personas
One of the perhaps least leveraged capabilities of generative AI and LLMs is their ability to computationally simulate a kind of persona. The idea is rather straightforward. You tell the AI to pretend to be a particular type of person or exhibit an outlined personality, and the AI attempts to respond accordingly. For example, I made use of this feature by having ChatGPT undertake the persona of Sigmund Freud and perform therapy as though the AI was mimicking or simulating what Freud might say (see the link here).
You can tell LLMs to pretend to be a specific person. The key is that the AI must have sufficient data about the person to pull off the mimicry. Also, your expectations about how good a job the AI will do in such a pretense mode need to be soberly tempered since the AI might end up far afield. An important aspect is not to somehow assume or believe that the AI will be precisely like the person. It won't be.
Another angle to using personas is to broadly describe the nature of the persona that you want to have the AI to pretend to be. I have previously done a mini-experiment of having ChatGPT pretend to be a team of mental health therapists that confer when seeking to undertake a psychological assessment (see the link here). None of the personas represented a specific person. Instead, the AI was generally told to make use of several personas that generally represented a group of therapists.
There are a lot more uses of AI personas.
I'll list a few. A mental health professional who wants to improve their skills can carry on a dialogue with an LLM that is pretending to be a patient, which is a handy means of enhancing the psychological analysis acumen of the therapist (see the link here). Here's another example. When doing mental health research, you can tell AI to pretend to be hundreds or thousands of respondents to a survey. This isn't necessarily equal to using real people, but it can be a fruitful way to gauge what kind of responses you might get and how to prepare accordingly (see the link here and the link here).
And so on.
Latest Research Uses AI Personas
A recently posted research study innovatively used AI personas in the realm of performing medical diagnoses. The study was entitled 'Sequential Diagnosis with Language Models' by Harsha Nori, Mayank Daswani, Christopher Kelly, Scott Lundberg, Marco Tulio Ribeiro, Marc Wilson, Xiaoxuan Liu, Viknesh Sounderajah, Jonathan Carlson, Matthew P Lungren, Bay Gross, Peter Hames, Mustafa Suleyman, Dominic King, Eric Horvitz, arXiv, June 30, 2025, and made these salient remarks (excerpts):
There are some interesting twists identified on how to make use of AI personas.
The crux is that they had an AI persona that served as a diagnostician, another one that was feeding a case history to the AI-based diagnostician, and they even had another AI persona that acted as an assessor of how well the clinical diagnosis was taking place. That's three AI personas that were set up to aid in performing a medical diagnosis on various case studies presented to the AI.
The researchers opted to go further with this promising approach by having a panel of AI personas that performed medical diagnoses. They decided to have five AI personas that would each, in turn, confer while stepwise undertaking a diagnosis. The names given to the AI personas generally suggested what each one was intended to do, consisting of Dr. Hypothesis, Dr. Test-Chooser, Dr. Challenger, Dr. Stewardship, and Dr. Checklist.
Without anthropomorphizing the approach, the aspect of using a panel of AI personas would be considered analogous to having a panel of medical doctors conferring about a medical diagnosis. The AI personas each have a designated specialty, and they walk through the case history of the patient so that each specialty takes its turn during the diagnosis.
Orchestration In AI Mental Health Analysis
I thought it might be interesting to try a similar form of orchestration by doing so in a mental health analysis context. I welcome researchers trying this same method in a more robust setting so that we could have a firmer grasp on the ins and outs of employing such an approach. My effort was just a mini-experiment to get the ball rolling.
I used a mental health case history that is a vignette publicly posted by the American Board of Psychiatry and Neurology (ABPN) and entails a fictionalized patient who is undergoing a psychiatric evaluation.
It is a handy instance since it has been carefully composed and analyzed, and serves as a formalized test question for budding psychiatrists and psychologists. The downside is that due to being widely known and on the Internet, there is a chance that any generative AI used to analyze this case history might already have scanned the case and its posted solutions.
Researchers who want to do something similar to this mini-experiment will likely need to come up with entirely new and unseen case histories. That would prevent the AI from 'cheating' by already having potentially encountered the case.
Overview Of The Vignette
The vignette has to do with a man in his forties who had previously been under psychiatric care and has recently been exhibiting questionable behavior. As stated in the vignette: 'For the past several months, he has been buying expensive artwork, his attendance at work has become increasingly erratic, and he is sleeping only one to two hours each night. Nineteen years ago, he was hospitalized for a serious manic episode involving the police.' (source: ABPN online posting).
I made use of a popular LLM and told it to invoke five personas, somewhat on par with the orchestration approach noted above, consisting of:
After entering a prompt defining those five personas, I then had the LLM proceed to perform a mental health analysis concerning the vignette.
Orchestration Did Well
Included in my instruction to the LLM was that I wanted to see the AI perform a series of diagnoses or turns. At each turn, the panel was to summarize where they were in their analysis and tell me what they had done so far. This is a means of having the AI generate a kind of explanation or indication of what the computational reasoning process entails.
As an aside, be careful in relying on such computationally concocted explanations since they may have little to do with what the internal tokenization mechanics of the LLM were actually doing, see my discussion of noteworthy cautions at the link here.
I provided the LLM persona panel with questions that are associated with the vignette. I then compared the answers from the AI panel with those that have been posted online and are considered the right or most appropriate answers.
To illustrate what the AI personas panel came up with, here's the initial response about the overall characteristics of the patient at the first turn:
The analysis ended up matching overall with the posted solution. In that sense, the AI personas panel did well. Whether this was due to true performance versus having previously scanned the case history is unclear. When I asked directly if the case had been seen previously, the LLM denied that it had already encountered the case.
Don't believe an LLM that tells you it hasn't scanned something. The LLM might be unable to ascertain that it had scanned the content. Furthermore, in some instances, the AI might essentially lie and tell you that it hasn't seen a piece of content, a kind of cover-up, if you will.
Leaning Into AI Personas
AI personas are an incredibly advantageous capability of modern-era generative AI and LLMs. Using AI personas in an orchestrated fashion is a wise move. You can get the AI personas to work as a team. This can readily boost the results.
One quick issue that you ought to be cognizant of is that if the LLM is undertaking all the personas, you might not be getting exactly what you thought you were getting. An alternative approach is to use separate LLMs to represent the personas. For example, I could connect five different LLMs and have each simulate the personas that I used in my mini-experiment. The idea is that by using separate LLMs, you avoid the chances of the single LLM lazily double-dealing by not really trying to invoke personas. An LLM can be sneaky that way.
A final thought for now.
Mark Twain famously provided this telling remark: 'Synergy is the bonus that is achieved when things work together harmoniously.' The use of orchestration with AI personas can achieve a level of synergy that otherwise would not be exhibited in these types of analyses. That being said, sometimes you can have too many cooks in the kitchen, too.
Make sure to utilize AI persona orchestration suitably, and you'll hopefully get sweet sounds and delightfully impressive results.
Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

Walmart bets on AI 'super agents' to boost e-commerce growth
Walmart bets on AI 'super agents' to boost e-commerce growth

Yahoo

time17 minutes ago

  • Yahoo

Walmart bets on AI 'super agents' to boost e-commerce growth

STORY: Walmart is deepening its push into AI, unveiling four new "super agents" on Thursday, aiming to improve the shopping experience and better compete with rival retailers. Powered by agentic AI - which needs minimal human intervention - the super agents will serve as primary entry points for every AI interaction with Walmart shoppers, store employees, suppliers and sellers, and software developers. The new agents will replace several existing AI tools, and the retailer hopes they'll attract more shoppers away from Amazon, which has its own range of AI-powered tools. One of Walmart's agents, Sparky, is already available on its app as a Gen-AI powered tool, where it currently assists customers with product suggestions, such as athletic wear or the right ink for a printer. In its "super agent" form, Walmart says Sparky will be able to plan themed parties and offer product recipes by looking at the contents of a shopper's fridge through its computer vision. Another super agent, Marty, is being developed for sellers, suppliers, and advertisers in an effort to streamline the onboarding process, manage orders and create ad campaigns. Walmart declined to say whether the super agents would replace human jobs.

New data from Global Water Intelligence reveals impact of hyperscale data center boom on onsite water consumption and unprecedented growth in water technology and infrastructure spending
New data from Global Water Intelligence reveals impact of hyperscale data center boom on onsite water consumption and unprecedented growth in water technology and infrastructure spending

Yahoo

time17 minutes ago

  • Yahoo

New data from Global Water Intelligence reveals impact of hyperscale data center boom on onsite water consumption and unprecedented growth in water technology and infrastructure spending

OXFORD, United Kingdom, July 24, 2025 (GLOBE NEWSWIRE) -- New research from GWI has found that onsite water consumption for data center cooling is forecast to increase by just over 50% by 2030, despite data center capacity doubling over the same findings reflect significant efficiency gains in water use, with a shift to water-efficient cooling technologies. These technologies require higher quality water, and GWI therefore predicts that these strides in responsible water use will be supported by unprecedented double digit annual growth in water-related technology and infrastructure spending for data centers. Hybrid air-water cooling, as well systems designed for AI workloads, where chips are in direct contact with a water-based coolant, are increasingly the norm for data centers. Additionally there is a shift to lower-quality recycled water as the sector cuts its freshwater use. However, the extent of these efficiency gains is not globally balanced, nor are they always related to concerns of water stress. In India, for example, data center water use is set to more than double by 2030, posing major risks in a country already facing extreme water stress. Data centers can reduce their onsite water footprint by switching to dry cooling, but this drives up energy use, leading to greater indirect water consumption from power generation. As power demand continues to surge through 2030 and beyond, water-efficient cooling will be essential to the sustainable growth of data centers. Access the full dataset via our rich forecast data dashboard. Book a demo directly at For general inquiries contact: sales@ About Global Water Intelligence Global Water Intelligence (GWI) is the leading market intelligence and events company serving the international water industry. Over the last 25 years we have built our business around being a trusted interface between our clients and their markets, providing our customers with high-level intelligence that enables them to make the most informed strategic decisions for their business. We cover municipal markets and every industrial vertical as well as technology, finance and economics. GWI runs an advanced manufacturing conference focusing on semiconductors and data centers: CONTACT: Victor SmithCOMPANY: Global Water IntelligencePHONE: 01865 204208 EMAIL: sales@ A photo accompanying this announcement is available at

ServiceNow (NOW) Stock Soars After Smashing Q2 Targets Amid AI Boom
ServiceNow (NOW) Stock Soars After Smashing Q2 Targets Amid AI Boom

Yahoo

time17 minutes ago

  • Yahoo

ServiceNow (NOW) Stock Soars After Smashing Q2 Targets Amid AI Boom

July 24 - ServiceNow (NYSE:NOW) shares surged more than 5% in Thursday morning trading after the enterprise?software firm posted a strong second quarter driven by AI?related growth. Warning! GuruFocus has detected 3 Warning Sign with NOW. Subscription revenue climbed to $3.113 billion, up 21.5% year?over?year in constant currency and exceeding guidance by roughly two percentage points. Operating margin widened to 29.5%, more than 2.5 points above projections, while free cash flow margin rose to 16.5%, up three points from last year. Remaining performance obligations reached $23.9 billion, a 25.5% jump, with current RPO at $10.92 billion, up 21.5%. ServiceNow closed 89 deals over $1 million in net new annual contract value, including 11 above $5 million, as renewal rates held at 98%. The company ended the quarter with $10.8 billion in cash and investments and repurchased about 381,000 shares under its $2.6 billion buyback authorization. Management raised full?year subscription revenue guidance by $125 million to a $12.775 billion$12.795 billion range, signalling roughly 20% growth. Third?quarter subscription revenue is expected between $3.260 billion and $3.265 billion, with operating margin forecast at 30.5%. CEO Bill McDermott noted rapid adoption of its AI Pro Plus platform, which may drive larger deals and deeper customer engagement going forward. This article first appeared on GuruFocus.

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into a world of global content with local flavor? Download Daily8 app today from your preferred app store and start exploring.
app-storeplay-store