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

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

The US Food & Drug Administration’s Digital Health Advisory Committee (DHAC) met on November 20, 2025, for its second meeting dedicated to AI-enabled content in medical devices.2 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 major depressive disorder (MDD).3 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 HCPLive. “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 (P <.05) and increasing over time.3 By week 8, the mean difference between BH-200 and placebo reached –2.98 (P =.0003).

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?”’

References

1. The Evolution of AI in Healthcare. Xsolis. Published February 2, 2021. https://www.xsolis.com/blog/the-evolution-of-ai-in-healthcare/

2. 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

3. 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