NetraMark Unveils AI-Discovered Treatment-Responsive Subgroups in A4 Alzheimer’s Trial at AD/PD Conference

Rhea-AI Summary

NetraMark (OTCQB: AINMF) presented a poster at the AD/PD 2026 conference (March 17-21) showing that its explainable AI, NetraAI, identified two treatment-responsive subgroups in the Phase 3 A4 solanezumab dataset.

Findings include biologically interpretable subgroups with preserved limbic/temporal network integrity and effect sizes up to Cohen’s d 1.52, suggesting AI-enabled precision enrichment may reveal masked therapeutic signals.

Results illustrate how NetraMark’s advanced AI can potentially support precision enrichment strategies in future trials

TORONTO, March 19, 2026 (GLOBE NEWSWIRE) -- NetraMark Holdings Inc. (the “Company” or “NetraMark”) (TSX: AIAI) (OTCQB: AINMF) (Frankfurt: PF0), a company developing advanced artificial intelligence solutions for clinical trial optimization and precision medicine, today announced new findings illustrating the ability of its proprietary explainable AI platform, NetraAI, to uncover clinically meaningful responder subgroups within the landmark Anti-Amyloid Treatment in Asymptomatic Alzheimer’s Disease (A4) trial.

The results, were presented in a poster titled, “Decoding Heterogeneity in A4: Explainable ML Identifies Solanezumab-Responsive Subgroups in Preclinical AD,” which highlight how NetraMark’s technology has the potential to reveal therapeutic signals that may be obscured in conventional clinical trial analyses.

The poster was presented at the Alzheimer’s Disease & Parkinson’s Diseases (AD/PD) 2026 International Conference, taking place March 17 - 21, 2026, in Copenhagen, Denmark during the poster sessions.

Explainable AI Identifies Hidden Treatment Response

Using a dynamical-systems-based explainable machine learning approach, NetraAI analyzed multimodal baseline variables including imaging, cognitive assessments, demographics, and biomarkers from participants in the A4 study.

Although the original Phase 3 A4 trial showed no statistically significant overall benefit for solanezumab (a humanized monoclonal antibody designed to treat Alzheimer’s disease by binding to and clearing soluble amyloid-beta), NetraAI identified two distinct patient subgroups suggesting meaningful treatment effects relative to placebo.

Key findings include:

• Identification of two biologically interpretable responder subgroups characterized by higher regional brain volume and stronger baseline cognitive performance.
• Large treatment effects, within these subgroups, with effect sizes reaching Cohen’s d up to 1.52.
• Participants within subgroups showing treatment effects were associated with greater baseline limbic and temporal network integrity, including higher right amygdala or right superior temporal cortex volume, alongside stronger psychomotor speed and attention scores on the Digit Symbol Substitution Test.
  

These findings suggest that preserved neural reserve may be an important determinant of anti-amyloid treatment response in preclinical Alzheimer’s disease.

Implications for Alzheimer’s Drug Development

The results underscore a significant challenge in Alzheimer’s clinical development: being patient heterogeneity can mask meaningful drug response within overall trial populations.

By identifying explainable, model-derived subgroups defined by only a small number of baseline variables, NetraAI illustrates how advanced AI can potentially support precision enrichment strategies in future trials.

For the pharmaceutical industry, this approach could:

• Improve trial design by identifying patients most likely to respond to investigational therapies
• Enable retrospective re-analysis of historical trials to extract new insights
• Reduce development risk and cost through data-driven patient stratification
  

Timely Advances for the Alzheimer’s Research Community

The upcoming presentation comes at a pivotal time for the Alzheimer’s field, as therapeutic development increasingly focuses on earlier disease stages and precision-guided treatment strategies.

NetraMark’s explainable AI methodology aligns with this shift by supporting researcher efforts aimed at understanding not only whether a therapy demonstrates an effect, but also which patients may be most likely to benefit and why.

"These findings suggest that patient heterogeneity may be masking treatment effects in Alzheimer’s trials, underscoring the need for approaches such as NetraAI that may identify interpretable patient subpopulations most likely to benefit from emerging therapies,” said Dr. Joseph Geraci, Chief Technical Officer and Founder of NetraMark. “Technologies capable of identifying biologically meaningful responder subgroups could fundamentally reshape how Alzheimer’s clinical trials are designed.”

As the industry continues to explore disease-modifying treatments targeting amyloid and other pathways, technologies capable of interpretable patient segmentation have the potential to play a critical role in unlocking therapeutic signals that traditional analyses fail to detect.

About NetraAI

In contrast to other AI-based methods, NetraAI is uniquely engineered to include focus mechanisms that separate small datasets into explainable and unexplainable subsets. Unexplainable subsets are collections of patients that can lead to suboptimal overfit models and inaccurate insights due to poor correlations with the variables involved. NetraAI uses explainable subsets to derive insights and hypotheses (including factors that influence treatment and placebo responses and adverse events), potentially increasing the likelihood of a clinical trial's success. Many other AI methods lack these focus mechanisms and assign every patient to a class, often leading to "overfitting", which drowns out critical information that could have been used to improve a trial's chance of success.

About NetraMark

NetraMark is a company focused on being a leader in the development of Generative Artificial Intelligence (Gen AI)/Machine Learning (ML) solutions targeted at the Pharmaceutical industry. Its product offering uses a novel topology-based algorithm that has the ability to parse patient data sets into subsets of people that are strongly related according to several variables simultaneously. This allows NetraMark to use a variety of ML methods, depending on the character and size of the data, to transform the data into powerfully intelligent data that activates traditional AI/ML methods. The result is that NetraMark can work with much smaller datasets and accurately segment diseases into different types, as well as accurately classify patients for sensitivity to drugs and/or efficacy of treatment.

For further details on the Company please see the Company’s publicly available documents filed on the System for Electronic Document Analysis and Retrieval+ (SEDAR+).

Forward-Looking Statements

This press release contains "forward-looking information" within the meaning of applicable Canadian securities legislation including statements regarding the potential of NetraMark’s NetraAI platform and analyses to reveal therapeutic signals that may not be apparent in conventional clinical trial analyses; the potential application of NetraAI to support precision enrichment strategies in future clinical trials; the potential to improve clinical trial design, enable retrospective analyses of historical trials, and reduce development risk and cost through data‑driven patient stratification; and the potential role of interpretable patient segmentation technologies in identifying treatment‑responsive subgroups, which are based upon NetraMark’s current internal expectations, estimates, projections, assumptions and beliefs, and views of future events. Forward-looking information can be identified by the use of forward-looking terminology such as "expect", "likely", "may", "will", "should", "intend", "anticipate", "potential", "proposed", "estimate" and other similar words, including negative and grammatical variations thereof, or statements that certain events or conditions "may", "would" or "will" happen, or by discussions of strategy. Forward-looking information includes estimates, plans, expectations, opinions, forecasts, projections, targets, guidance, or other statements that are not statements of fact. The forward-looking statements are expectations only and are subject to known and unknown risks, uncertainties and other important factors that could cause actual results of the Company or industry results to differ materially from future results, performance or achievements. Any forward-looking information speaks only as of the date on which it is made, and, except as required by law, NetraMark does not undertake any obligation to update or revise any forward-looking information, whether as a result of new information, future events, or otherwise. New factors emerge from time to time, and it is not possible for NetraMark to predict all such factors.

When considering these forward-looking statements, readers should keep in mind the risk factors and other cautionary statements as set out in the materials we file with applicable Canadian securities regulatory authorities on SEDAR+ at www.sedarplus.com including our Annual Information Form for the year ended September 30, 2025. These risk factors and other factors could cause actual events or results to differ materially from those described in any forward- looking information. The Toronto Stock Exchange does not accept responsibility for the adequacy or accuracy of this release.

Contact Information:

Swapan Kakumanu - CFO | swapan@netramark.com | 403-681-2549

Or

Adam Peeler – Investor Relations | adam.peeler@loderockadvisors.com | 416-427-1235

LodeRock Advisors

FAQ

What did NetraMark announce at AD/PD 2026 about AINMF and the A4 trial?

NetraMark reported that NetraAI identified two responder subgroups in the A4 solanezumab data, with effect sizes up to Cohen’s d 1.52. According to the company, the subgroups were defined by preserved limbic/temporal volumes and stronger baseline cognitive scores.

How large were the treatment effects NetraAI found in A4 according to AINMF?

NetraAI found large subgroup treatment effects with effect sizes reaching Cohen’s d up to 1.52. According to the company, these effects were observed within explainable subgroups defined by imaging and cognitive baseline variables.

Which baseline features defined the NetraAI responder subgroups in AINMF’s analysis?

Responder subgroups were distinguished by higher right amygdala or right superior temporal cortex volume and stronger psychomotor speed. According to the company, Digit Symbol Substitution Test scores and network integrity drove subgroup definitions.

What are the implications of NetraMark’s A4 reanalysis for Alzheimer’s drug development?

The analysis suggests AI-based patient segmentation could enable precision enrichment in trials, potentially uncovering masked drug responses. According to the company, this may improve trial design and enable retrospective insights from historical datasets.

When and where did AINMF present the NetraAI A4 findings at AD/PD 2026?

NetraMark presented the poster titled “Decoding Heterogeneity in A4” during the AD/PD 2026 poster sessions in Copenhagen, March 17–21, 2026. According to the company, the work was shown as part of the conference poster program.