Subscribe to The Podcast by KevinMD. Watch on YouTube. Catch up on old episodes!

Psychiatrist Muhamad Aly Rifai discusses his article, “The future of psychiatry: How AI and genetics are reshaping mental health care.” Muhamad explores how the integration of genetic research, biomarkers, electrophysiology, and artificial intelligence is transforming psychiatry into a more precise and preventative field. He explains how advances in pharmacogenomics and digital diagnostics are helping tailor treatment strategies and improve patient outcomes. From AI-assisted diagnostic tools to wearable technology and brain-computer interfaces, Muhamad emphasizes the need to move beyond reactive care and embrace a holistic, evidence-based approach to mental health in the 21st century.

Our presenting sponsor is Microsoft Dragon Copilot.

Want to streamline your clinical documentation and take advantage of customizations that put you in control? What about the ability to surface information right at the point of care or automate tasks with just a click? Now, you can.

Microsoft Dragon Copilot, your AI assistant for clinical workflow, is transforming how clinicians work. Offering an extensible AI workspace and a single, integrated platform, Dragon Copilot can help you unlock new levels of efficiency. Plus, it’s backed by a proven track record and decades of clinical expertise and it’s part of Microsoft Cloud for Healthcare–and it’s built on a foundation of trust.

Ease your administrative burdens and stay focused on what matters most with Dragon Copilot, your AI assistant for clinical workflow.

VISIT SPONSOR → https://aka.ms/kevinmd

SUBSCRIBE TO THE PODCAST → https://www.kevinmd.com/podcast

RECOMMENDED BY KEVINMD → https://www.kevinmd.com/recommended

Transcript

Kevin Pho: Hi, and welcome to the show. Subscribe at KevinMD.com/podcast. Today we welcome back Muhamad Aly Rifai, an internal medicine physician and psychiatrist. Today’s KevinMD article is “The future of psychiatry: How AI and genetics are reshaping mental health care.” Mohamed, welcome back to the show.

Muhamad Aly Rifai: Thank you very much for having me to talk to your audience about the future of psychiatry and how new modalities are gonna be helpful for our patients.

Kevin Pho: Tell us what this article is about for those who didn’t get a chance to read it.

Muhamad Aly Rifai: So, in the article, I introduced the audience to the field of psychiatry. And not a lot of people know, but actually in the field of psychiatry and medicine, four of the signatories on the Declaration of Independence are physicians. Hmm. Out of 39, 4 of them are physicians. So the art of medicine—the art of psychiatry—has been in the core of this nation. Dr. Benjamin Rush, who is the father of American psychiatry, has his face on the emblem of the American Psychiatric Association. His silhouette. He was one of the signatories of the Declaration of Independence, and he actually led the Pennsylvania delegation that ratified the Constitution.

So psychiatry and medicine have been at the core of this country for a long time, but we are seeing a significant, seismic shift in the field of psychiatry because we are now utilizing new tools that are gonna help us both with assessment and diagnosis of individuals who have psychiatric illness on all levels. And we’re gonna be able to move away from this subjective approach where we ask patients how they feel, and we base our treatments on that as well as on the clinical opinion of the treatment psychiatrist, which ends up with a lot of interrater reliability issues, where if you have a psychiatric diagnosis, 50 percent of psychiatrists will agree with that and the other 50 percent won’t agree with that and will have a different diagnosis. So I think we’re moving in the right way of being able to offer our patients accurate diagnoses and offer them some accurate treatment modalities.

Kevin Pho: Now, why has psychiatry historically lagged behind other medical fields when it comes to adopting objective diagnostic measures?

Muhamad Aly Rifai: The field of psychiatry has been very difficult to crack. You know, in cardiology you have the ability to do an EKG. You have the ability to do imaging, echocardiograms, cardiac CTs, cardiac catheterization. So you have the ability to visualize what’s going on, and you know, the heart technically is a simpler organ than the brain. We’ve not been able to do that for psychiatry. I mean, we have neuroimaging, we have functional MRIs. We’ve been able to slightly, now with new modalities, be able to look at the actual activity of the brain in real time. We have EEGs, we have functional EEGs, but we think that there are some improvements because, for example, Neuralink, which is a device that links with the brain and is able to translate some of the brain signals into instructions for individuals, for example, with different paralysis—they’re able to utilize that device to gain some movement. But we’ve also been able to utilize some EEG modalities specifically, both for diagnosis as well as for treatment. There is now a new device that’s being approved for both the treatment of PTSD and anxiety that utilizes an AI model where an EEG is hooked to the brain, and it involves a biofeedback loop where a person is supposed to calm down, be able to settle down by integrating into an AI environment, and be able to deescalate their anxiety and depression. And that’s actually being FDA approved for both depression and anxiety. So we are seeing some improvement, but we’re really far away from that just because of the complexity of the brain.

Kevin Pho: Now, you talk about several options. You mentioned a few just now, and we have things like pharmacogenetics; we have biomarkers. So tell us some of the more promising approaches that we have to look forward to going forward when it comes to objective psychiatric measures.

Muhamad Aly Rifai: One of the most promising ones is actually genetics and genomics. The Human Genome Project cracked our human genome at the beginning of the 2000s. We used to think that our body had maybe millions of genes, but we were surprised to find out that we only have about a hundred thousand genes. However, there are a lot of areas in the genome that are silent areas, but they actually affect the translation of our different genes and function. We have not been able to really crack the code, literally, of being able to say, if you have this gene, you are more susceptible to this psychiatric diagnosis. We’re still not there yet. We have some polymorphisms that we think are promising; we have some polymorphisms that we use and that are FDA approved for our response to psychotropic medications and whether we’re gonna be able to metabolize them. But we are far away. But we think AI may be able to help us in terms of doing a genome analysis and telling a person who is 15 or 16, well, you’re gonna be developing depression, anxiety, schizophrenia. We’re not there yet, but we are hoping that we’ll be there one day, and that hopefully we’re gonna have more of a preventative approach rather than a therapeutic approach. Somebody develops schizophrenia, and then you treat them. Maybe if you’re able to find out that they’re gonna be at risk for developing schizophrenia, you may treat them prophylactically. Maybe they will not smoke marijuana and be at a higher risk. Maybe they won’t use drugs, maybe they won’t be in a stressful scenario that would ignite that schizophrenia. So we’re hoping that we’re gonna be there soon.

We also think that AI is gonna be able to help us in terms of being able to have preliminary diagnoses on our patients. So there are AI models now that are looking at speech. So as I speak, AI is gonna be able to do a comparison between somebody who has no psychiatric illness and another individual who has, for example, schizophrenia, depression, or anxiety. And we are very close to having some large databases where AI is gonna be able, just from listening to somebody’s speech for about three to five minutes, to put a high likelihood of somebody having depression, anxiety, or maybe schizophrenia. Facial features with AI are also coming as something that’s gonna be available. We are currently using AI for facial features to detect adverse effects with antipsychotic medications. So, tardive dyskinesia: AI is able to assist clinicians in diagnosing tardive dyskinesia, which is a side effect of antipsychotic medication, just by looking at the pictures and somebody’s movement. Within a minute, AI is able to give you a significant probability of whether somebody does or does not have tardive dyskinesia. So we are already there in some measures, but not where we wanna be, where we’re having these tools assist us in diagnosing psychiatric illness.

Kevin Pho: You also brought up the biomarkers category. So what kind of biomarkers can we measure, say, through the blood that may point to potential psychiatric diagnoses?

Muhamad Aly Rifai: So, we’re looking at different biomarkers, and psychiatry was one of the oldest fields to have some biomarkers. In cardiology you have blood sugar, you have insulin levels. Early on, psychiatry developed, looking at cortisol levels and cortisol suppression tests, and the association of that with depression and anxiety. There are multiple biomarkers that we’re looking at in terms of blood analysis for depression, anxiety, and PTSD, and specifically also for dementia, as well as autism spectrum disorder. They’re still being tested. I don’t think that we’re there yet with anything definitive, but there are several that are in phase 2 and phase 3 trials in terms of diagnostic value for individuals with psychiatric illness. But we’re not there yet. We still utilize just the regular markers that we’ve utilized 50 or 60 years ago, but we’re hoping that we’ll be there in the next few years. AI is gonna help with that also.

Kevin Pho: So give us a scenario or story of one of these technologies and how that would change what you do in the office with a psychiatric patient. So tell us, how would it change your therapeutic and diagnostic approach once we have some of these technologies in play?

Muhamad Aly Rifai: Sure, absolutely. I’ll give you a practical story, a real story that I encountered with one of my patients in using a modality that we didn’t talk about: wearables. Now they’re very prominent. Everybody has an Apple Watch, which is either an Apple Watch or some other modality. A patient was complaining that they were not sleeping well, and I encouraged them to wear a wearable that they have so we could have a better understanding and analysis of their sleep pattern. Their impression was that they were not sleeping; their impression was that they are not feeling rested in the morning. So we encouraged them to use a wearable—an Apple Watch—just to look at their sleep pattern and whether they were sleeping or not. When they returned for their next appointment, because they were asking for a sleep aid that may not have been very therapeutic or helpful for them because of their condition, we found out, looking at the wearable, that they were actually getting about six or seven hours of sleep, which is a reasonable amount of sleep, while their impression was that they’re not sleeping at all or only one or two hours a night. So this is a modality where, actually, if the physician is integrated into the wearables, they can do home monitoring. Additionally, things like medication management as well as systems to ensure medication compliance—whether the patient took their medication or not—so we have the integration of technology into that therapeutic system.

Also, for example, I had one of my patients whom I was actually trying to help lose weight after he gained a significant amount of weight with his antipsychotic medication, and he actually went to an outside company that would do, for about 50 bucks, a genomic analysis on multiple variables where there is some literature about how a person should go about their diet. And he discovered that he was very sensitive to carbohydrates and that those would actually initiate his insulin resistance pattern. So he actually cut carbohydrates completely, or as much as possible, from his diet, and he ended up losing 25 pounds. This is how much weight he had gained with the antipsychotic medication, also guided by genomic testing that wasn’t even physician initiated. He got the test on his own. There was a large clinical trial that looked at that polymorphism, and he found out that if he cut carbohydrates, he would lose weight. So our patients, if we ally with them, can really be very helpful in terms of trying to assist us with wearables, with AI, and with available testing that is outside the medical field. So I think being able to utilize some of those modalities would be very helpful for our patients.

Kevin Pho: So how far off are we in terms of implementing or seeing some of these technologies used in everyday psychiatric practice? Are we talking about way off in the future? Are we talking about in the coming months? So what vision do you have?

Muhamad Aly Rifai: I think it’s coming in the coming years. For some of them, we’re already here. I mean, with wearables, I think we’re already here. I think any physician who’s not utilizing wearables with behavioral analysis of how the patient is doing at home is doing a disservice to their patient. They need to use that data from the wearables to assist their patients. I think AI is here. I’m actually involved in a pilot project where we actually take a 15-to-30-second video of our patient and look at movement disorders in tardive dyskinesia. Also, speech pattern is there. There is a company that is collecting a large database of speech patterns for patients and doing comparisons to normal individuals to see if they can have an AI pattern for psychiatric illness or at least predictive of psychiatric illness, whether current or future. So I think we’re here, and in the next year or two, we’re gonna see a deluge of those modalities coming into the medical fields. And I think physicians really need to be up to date on that because our patients are gonna be asking about it, and we need to be ready for that.

Kevin Pho: What about psychiatrists themselves? Do you think they’re ready for more objective measures? Do you see any resistance among the psychiatric profession to adopt some of these new technologies in a field that traditionally has been resistant to objective measures?

Muhamad Aly Rifai: I think I see some of that from my colleagues, but I think we have to go with our patients. I mean, we can’t have patients come to us and say, well, look, here’s what my wearable says: I’m not sleeping, I need you to help me with this. Or you can ask your patient for data, and then you can have a dialogue with them: well, look, this says that you’re sleeping well, you don’t need a sleep aid, your sleep is sufficient; if you’re not feeling well, then maybe we need to look at other things. And also just using that technology to help our patients, and keeping us updated about how they’re doing, and doing surveys, I think that that is there. But, you know, some of the older-generation psychiatrists are resistant to that change. But I think it’s here, and we have to adopt it; otherwise, we’re gonna be left behind by our patients who are demanding it.

Kevin Pho: We’re talking to Muhamad Aly Rifai. He’s a psychiatrist and internal medicine physician. Today’s KevinMD article is “The future of psychiatry: How AI and genetics are reshaping mental health care.” Muhamad, as always, let’s end with some take-home messages that you want to leave with the KevinMD audience.

Muhamad Aly Rifai: I think AI and genetics as well as biomarkers are here to stay. They’re the future of psychiatry. There’s some apprehension from the older-generation psychiatrists about this change that’s going to be happening, but we have to embrace it. In my case, I was a thought leader in the field of telehealth, and we’re seeing all of these modalities coming. And I think we need to adopt them for the benefit of our patients and to move the field of psychiatry forward with treatment as well as therapeutic values.

Kevin Pho: Muhamad, as always, thank you so much for sharing your perspective and insight, and thanks again for coming back on the show.

Muhamad Aly Rifai: My pleasure. Thank you.