a psychiatrist and Chief Medical Officer at HMNC Brain Health

Hans Eriksson, MD, PhD

New Genetic Tool Shows Promise for Targeted MDD Treatment, With Hans Eriksson, MD, PhD

Each year, research on the use of artificial intelligence (AI) in healthcare continues to grow, tracing back to the 1970s with MYCIN, an early system designed to recommend treatments for blood infections.

But with the rise of chatbots like ChatGPT, AI has become even more top-of-mind for many people.

Digital Health Advisory Committee (DHAC) met on November 20, 2025, for its second meeting dedicated to AI-enabled content in medical devices

The agency addressed several AI risks, including output errors, misinterpretations of what a chatbot says, and healthcare providers' lack of understanding of how to effectively monitor the technology. Yet, at the same time, AI tools improve access to care.

A report released shortly afterward outlined the FDA’s expectations for AI: rigorous performance testing (assessing repeatability, reproducibility, uncertainty, hallucination rates, and error rates); ongoing automated auditing and quality assurance after market entry; and strong human oversight, training, transparency, informed use, shared responsibility, and risk-management practices. The agency also emphasized the importance of detailed device submissions that specify the intended use, care environment, and standardized model cards, as well as benchmarking to compare device performance against established standards.

This regulatory backdrop frames HMNC Brain Health’s work in the OLIVE trial, which is testing an AI-assisted, genetically guided precision approach for 

 The company announced pivotal data on August 5, 2025.

“I think we all feel a bit uneasy about AI,” Hans Eriksson, PhD, MD, from HMNC Brain Health, told 

. “How do we ensure that what we get is accurate, that what we get is not just made up by a machine? But in our case, the AI component is…earlier on. The AI component was used…to map the result of this physiological challenge test to a certain outcome of a genetic test. For the individual patient, there is no real AI component involved [once the blood is drawn]. That happened before the algorithm was created.”

OLIVE, a randomized, double-blind, placebo-controlled phase 2b trial, evaluated BH-200 (nelivaptan), a selective vasopressin V1b receptor antagonist, in patients with MDD. BH-200 produced a clinically meaningful improvement, with separation from placebo on HAM-D17 emerging at week 4 (

 By week 8, the mean difference between BH-200 and placebo reached –2.98 (

This study used HMNC’s proprietary genetic selection tool, which classifies patients based on biomarkers linked to vasopressin signaling and regulation of the hypothalamic-pituitary-adrenal (HPA) axis. The tool sorted patients into 3 vasopressin-related biological subgroups

Findings showed that lower peripheral vasopressin activity correlates with stronger central vasopressin activity in relevant brain areas, resulting in a more robust antidepressant response. This finding confirms that a genetic test can guide patient selection for BH-200.

Previous vasopressin blockers reached large clinical trials before but were never approved, likely because only a subset of patients had the underlying HPA-axis disturbance these drugs target. In broad, unselected populations, treatment effects were diluted.

To identify the right patients, investigators once relied on a “cumbersome” physiological challenge test requiring hospitalization, a synthetic steroid, a CRH injection, and repeated blood draws, according to Eriksson. Conducted in about 400 patients at the Max Planck Institute of Psychiatry in Munich, the test helped link specific vasopressin-related genes to test outcomes. Investigators then used these data to map physiological responses to distinct genetic profiles.

“We do not have to run the test [anymore]; we just draw blood from the patients, send it for genetic analysis, and a few days later, it comes back,” Eriksson said. “In the first version of the test, it came back with 3 different [responding] groups: high, medium, [and] low. But the intention is to…further refine this test, so it will actually answer yes or no to the question… ‘is this patient a suitable candidate for this treatment?”’

The Evolution of AI in Healthcare. Xsolis. Published February 2, 2021. 

https://www.xsolis.com/blog/the-evolution-of-ai-in-healthcare/

Eriksson H. FDA Examines Generative AI in Psychiatry, With Hans Eriksson, MD, PhD. Hcplive.com. Published December 5, 2025. Accessed December 5, 2025. 

https://www.hcplive.com/view/fda-examines-generative-ai-psychiatry-hans-eriksson-md-phd

HMNC BRAIN HEALTH | a disruptive clinical stage biopharma company pioneering precision psychiatry. Hmnc-brainhealth.com. Published 2025. Accessed December 5, 2025. 

https://www.hmnc-brainhealth.com/news/HMNC-Brain-Health-Announces-Phase-2-Results-from-OLIVE-Trial-in-Major-Depressive-Disorder-MDD-with-Genetically-Guided-Precision-Approach

Videos

As the FDA strengthens AI standards after its recent meeting, a new AI-assisted genetic tool shows promise for pinpointing patients who may respond to a vasopressin blocker.

New Genetic Tool Shows Promise for Targeted MDD Treatment, With Hans Eriksson, PhD, MD

FDA Examines Generative AI in Psychiatry, With Hans Eriksson, MD, PhD

 evaluates the safety and clinician utility of generative AI in 

, questions are emerging about its potential role in psychiatric care.

On November 20, 2025, the FDA convened its Digital Health Advisory Committee (DHAC) to examine how generative AI may influence the safety and effectiveness of medical devices, particularly digital mental health products. This was the second DHAC meeting dedicated to AI-enabled content in medical devices, following the committee’s broader 2024 discussion on total product life cycle considerations for generative AI.

The new report, released ahead of the agency’s upcoming work in this space, outlines the regulatory challenges presented by patient-facing AI systems that generate new content, update frequently, and may provide therapeutic guidance without clinician oversight. The FDA noted a rapid rise in AI therapists and mental health chatbots designed to offer behavioral interventions, diagnostic suggestions, or therapy-like conversations, which introduces novel risks for patients.

Shortly after the meeting, HCPLive spoke with Hans Eriksson, MD, PhD, a psychiatrist and Chief Medical Officer at HMNC Brain Health, on his thoughts regarding AI use in the psychiatry field. He said there are 2 ways you can use AI tools in development: to evaluate individual patient characteristics or to analyze populations and create algorithms that assign patients to different treatment groups. Ultimately, AI tools can help eliminate the standard practice of trial and error when prescribing medication.

“There are lots of different biologics, and unless we can pinpoint these biologics, it's very difficult to find the right intervention,” he said.

The FDA recognized that generative AI offers substantial public health benefits, including improving access to care. However, AI also comes with risks: output errors, patients’ misinterpreting what the chatbot gives them, and a physician or healthcare provider not understanding how to monitor the technology.

The agency also stated that AI tools should have detailed submissions with intended use, indications, use cases, the care environment, and standardized model cards. They added that devices must undergo rigorous performance testing using tailored metrics, such as the evaluation of repeatability, reproducibility, measurement of uncertainty, hallucination rates, error rates, and stress testing across intended user populations and settings. The FDA said that benchmarking is important for comparing device capabilities and performance against established standards.

After the tool hits the market, the FDA said there should be automated auditing and quality assurance checks to ensure consistency across multiple sites. There also needs to be new tools to evaluate opaque foundation models.

The FDA emphasized the importance of maintaining human oversight and adequate training, real-world transparency, informed use, shared responsibility, and risk management frameworks.

“[I] have not been directly interacting with [FDA’s AI report], so the interactions we've had with the FDA have been with projects that are not necessarily including the AI tools, but I think from the conversations, it becomes evident that they are very interested in the field, and they are aware that it's a very rapid development,” Eriksson said.

Generative Artificial Intelligence Enabled Digital Mental Health Medical Devices. The US Food & Drug Administration; 2025.

As mental health AI tools rise, the FDA weighs benefits and risks, emphasizing oversight and performance testing. Eriksson discusses AI in psychiatric care.

Hans Eriksson, MD, PhD

Articles