BullFrog AI-Driven Precision Oncology Analytics Identifies 3x Increase in Overall Survivability in Patient Subgroups through Key Biomarkers in Pancreatic Cancer

Rhea-AI Summary

BullFrog AI (NASDAQ: BFRG) reported that its bfLEAP® platform identified treatment-effect heterogeneity and key biomarkers in a post-hoc analysis of the randomized phase 3 trial TH-CR-302, finding an almost threefold increase in mean survival from control to treatment arms in specific pancreatic cancer subgroups.

Findings will be presented at the ASCO GI Symposium on Jan. 9, 2026 (poster B) and will appear in the Journal of Clinical Oncology supplement. The analysis, conducted with Eleison Pharmaceuticals and Moffitt Cancer Center authors, highlights bfLEAP® and bfPREP™ as tools for data-driven patient clustering, early predictor identification, and precision-oncology stratification in glufosfamide development.

Positive

• Almost 3x mean survival increase in identified patient subgroups
• bfLEAP® detected treatment-effect heterogeneity in phase 3 data
• Results scheduled for ASCO GI Jan. 9, 2026 and JCO supplement

Negative

• Finding from a post-hoc analysis, not a prospective randomized subgroup result
• Glufosfamide is described as an investigational agent, not approved

Key Figures

Survival benefit 3x Almost threefold increase in mean survival from control to treatment arms

Market Reality Check

$0.2415 Last Close

Volume Volume 133,257 is 1.45x the 20-day average of 92,205, indicating elevated pre-news activity. normal

Technical Trading at $0.872, below the 200-day MA of $1.42 and 81.98% under the 52-week high.

Peers on Argus

Peers show mixed moves: DRIO +17.51%, HCTI -14.18%, VSEE -5.85%, others near flat. With no scanner momentum and BFRG down 0.93%, trading appears more stock-specific than sector-driven.

Historical Context

Date	Event	Sentiment	Move	Catalyst
Dec 30	Shareholder letter	Positive	+2.8%	Annual letter on commercialization milestones, Eleison deployment, and 2026 catalysts.
Nov 18	AI whitepaper	Positive	+0.9%	Whitepaper detailing bfLEAP and BullFrog Data Networks bioinformatics methods.
Nov 12	Conference presentation	Positive	+0.0%	Planned bfPREP talk at AI Drug Discovery & Development Summit 2025.
Nov 04	ASCO GI abstract	Positive	-6.0%	ASCO GI abstract acceptance for glufosfamide precision-oncology poster.
Oct 30	Investor webinar	Positive	-2.3%	Investor webinar outlining AI platforms and Sygnature Discovery collaboration.

Pattern Detected

AI/platform news has generally produced modest moves, with some divergence where positive updates were followed by notable declines.

Recent Company History

Over the last few months, BullFrog AI has focused on showcasing its bfLEAP® and bfPREP™ platforms through investor outreach, technical talks, and publications. Events on Oct 30, Nov 4, Nov 12, Nov 18, and Dec 30 highlighted collaborations, conference presentations, and commercialization progress. Price reactions ranged from -6.03% to +2.78%, suggesting that AI‑themed announcements can elicit both supportive and contrarian trading responses ahead of catalysts like ASCO GI.

Market Pulse Summary

This announcement showcases bfLEAP® and bfPREP™ applied to pancreatic cancer, highlighting an almost 3x increase in mean survival in certain glufosfamide-treated subgroups and identifying key biomarkers and treatment effect heterogeneity. It builds on prior AI-tagged events around the same study and platforms. Investors may track how often BullFrog AI converts such analytics into paid deployments, as well as future datasets, additional indications, and any follow-on publications from the ASCO GI work.

Key Terms

pancreatic adenocarcinoma medical

"“Data-driven subtyping and differential glufosfamide benefit in pancreatic adenocarcinoma,”"

Pancreatic adenocarcinoma is a type of cancer that starts in the cells of the pancreas, the organ that helps digestion and controls blood sugar. It matters to investors because it is often aggressive and hard to detect early, so progress or setbacks in diagnostics, drugs or clinical trials can strongly affect the value of companies working on treatments—similar to how a breakthrough or failure in fixing a critical bridge can change the fortunes of contractors and insurers.

biomarkers medical

"the analysis discovered key biomarkers that influenced an almost threefold increase"

Biomarkers are measurable indicators found in the body, such as substances in blood or tissues, that reveal information about health or disease. For investors, they can signal how well a medical treatment is working or whether a disease is developing, helping to assess the potential success or risks of healthcare companies or innovations. Think of biomarkers as biological signals that provide clues about a person’s health status.

post-hoc analysis technical

"In the post-hoc analysis of TH-CR-302, a randomized phase 3 clinical trial"

Post-hoc analysis is an examination of data carried out after an experiment, trial, or reporting period to look for patterns or explanations that were not specified beforehand. It matters to investors because such findings can suggest new opportunities or risks but are more likely to be chance results than preplanned conclusions, so they require independent confirmation before being treated as reliable — like noticing a pattern on a map after a trip and then testing it on the next journey.

randomized phase 3 clinical trial medical

"post-hoc analysis of TH-CR-302, a randomized phase 3 clinical trial evaluating"

A randomized phase 3 clinical trial is a late-stage medical study in which a large group of patients are randomly assigned to receive either a new treatment or a standard/placebo option to compare outcomes. Think of it as a large-scale A/B test or final dress rehearsal that produces the strongest evidence on whether a therapy works and is safe; its results strongly influence regulatory approval odds, prescribing use, and the commercial value of a drug, making it critical for investors assessing clinical and financial risk.

best supportive care (BSC) medical

"clinical trial evaluating glufosfamide against the best supportive care (BSC)"

Best supportive care (BSC) is the routine medical treatment given to relieve symptoms and maintain quality of life for patients, without trying to cure the underlying disease. For investors, BSC matters because it is often the baseline or control against which new therapies are measured in clinical trials; a therapy that outperforms BSC can show clear patient benefit, affect regulatory success, market adoption, and reimbursement decisions. Thinking of BSC as the standard safety net helps gauge how much added value a new drug provides.

treatment effect heterogeneity medical

"bfLEAP® platform successfully identified treatment effect heterogeneity and possible"

Treatment effect heterogeneity is the fact that a medical treatment or intervention does not work the same way for every patient or population; some people may improve a lot, some a little, and others not at all. For investors this matters because it shapes a drug’s effective market size, pricing, regulatory labeling, and sales forecasts—like a garden where the same fertilizer helps some plants thrive but leaves others unchanged, altering overall yield and value.

patient stratification medical

"data-driven clustering approaches to refine patient stratification and guide"

Patient stratification is the practice of grouping patients into subgroups based on shared characteristics — such as symptoms, test results, or likely response to treatment — so therapies and trials can be targeted more precisely. For investors, it matters because better matching of treatments to the right patients can raise the chances of clinical success, reduce time and costs in development, and increase the likelihood of regulatory approval and profitable market adoption, much like tailoring a product to the right customer segment.

chemotherapeutic agent medical

"glufosfamide, an investigational chemotherapeutic agent for pancreatic cancer."

A chemotherapeutic agent is a drug designed to kill or stop the growth of cancer cells and slow tumor spread; think of it as a specialized weed killer that targets rapidly growing cells. Investors care because the success, safety, regulatory approval, and patent protection of these drugs determine a company’s future sales, development costs and legal risks—outcomes that can quickly change a drugmaker’s valuation.

AI-generated analysis. Not financial advice.

Company’s bfLEAP® platform successfully identified treatment effect heterogeneity and possible early predictors of outcomes in pancreatic cancer in data to be presented at ASCO GI

GAITHERSBURG, Md., Jan. 06, 2026 (GLOBE NEWSWIRE) -- BullFrog AI Holdings, Inc. (NASDAQ: BFRG; BFRGW) ("BullFrog AI" or the "Company"), a technology company using artificial intelligence (“AI”) and machine learning to turn complex biomedical data into actionable insights, highlights the presentation of data derived from the use of the Company’s proprietary platform bfLEAP® with pancreatic cancer trial data to identify an almost three times increase in mean survival from the control to treatment arms. The data will be presented at the 2026 American Society of Clinical Oncology Gastrointestinal Cancers Symposium (ASCO GI) on Jan. 9 at poster session B.

The presentation, in collaboration with Eleison Pharmaceuticals and the Moffitt Cancer Center, is titled, “Data-driven subtyping and differential glufosfamide benefit in pancreatic adenocarcinoma,” and will subsequently appear in the Journal of Clinical Oncology (JCO) supplement corresponding to the symposium.

“The glufosfamide case study in pancreatic cancer successfully showcased the utility of our platform to provide drug developers with an end-to-end analytical tool engineered to resolve multimodal biological complexity at scale,” said BullFrog AI Founder and CEO Vin Singh. “Too much time and capital are wasted in drug development traveling down incorrect pathways, ultimately leaving patients without effective treatments. The power of bfLEAP® and bfPREP™ is their ability to give drug developers a clear path forward based on previous data and indicators to focus on key benchmarks, limiting the amount of wasteful spending on less-than-ideal targets.”

The study explored data-driven precision-oncology approaches leveraging BullFrog AI’s bfLEAP® and bfPREP™ platforms to analyze complex clinical datasets, uncover biologically meaningful patient clusters, and identify patient subtypes that may demonstrate enhanced response to glufosfamide, an investigational chemotherapeutic agent for pancreatic cancer. In the post-hoc analysis of TH-CR-302, a randomized phase 3 clinical trial evaluating glufosfamide against the best supportive care (BSC), the analysis discovered key biomarkers that influenced an almost threefold increase in mean survival from the control to treatment arms.

The research group concluded that ensemble approaches like bfLEAP® can successfully identify patient subgroups within existing glufosfamide clinical trial data. Treatment effect heterogeneity was identified among clusters, identifying possible early predictors of outcomes, and highlighting the effectiveness of data-driven clustering approaches to refine patient stratification and guide the development of personalized treatment strategies.

The study was co-authored by Richard Kim, M.D., Service Chief of Medical Gastrointestinal Oncology and Senior Member in the Gastrointestinal Oncology Department at Moffitt Cancer Center, Nikolas Naleid, M.D., Pharm.D., Hematology/Oncology Fellow at Moffitt Cancer Center, Eleison Pharmaceuticals, and BullFrog AI.

About BullFrog AI

BullFrog AI leverages artificial intelligence and machine learning to advance drug discovery and development. Through collaborations with leading research institutions, BullFrog AI uses causal AI in combination with its proprietary bfLEAP® platform to analyze complex biological data, aiming to streamline therapeutics development and reduce failure rates in clinical trials. For more information visit BullFrog AI at: https://bullfrogai.com.

Safe Harbor Statement

This press release contains forward-looking statements. We base these forward-looking statements on our expectations and projections about future events, which we derive from the information currently available to us. Such forward-looking statements relate to future events or our future performance, including: our financial performance and projections; our revenue and earnings; and our business prospects and opportunities. You can identify forward-looking statements by those that are not historical in nature, particularly those that use terminology such as “may,” “should,” “could,” “will,” “expects,” “anticipates,” “contemplates,” “estimates,” “believes,” “plans,” “projected,” “predicts,” “potential,” or “hopes” or the negative of these or similar terms. In evaluating these forward-looking statements, you should consider various factors, including: our ability to change the direction of the Company; our ability to keep pace with new technology and changing market needs; our and our partners’ ability to market and sell our offerings and services, including BullFrog Data Networks™; our ability to maintain compliance with Nasdaq listing rules; and the competitive environment of our business. These and other factors may cause our actual results to differ materially from any forward-looking statement. Forward-looking statements are only predictions. The forward-looking events discussed in this press release and other statements made from time to time by us or our representatives, may not occur, and actual events and results may differ materially and are subject to risks, uncertainties, and assumptions about us. We are not obligated to publicly update or revise any forward-looking statement, whether as a result of uncertainties and assumptions, the forward-looking events discussed in this press release and other statements made from time to time by us or our representatives might not occur.

Contact:

Investors:
CORE IR
ir@bullfrogai.com

Media:
CORE PR
pr@bullfrogai.com

FAQ

What did BullFrog AI (BFRG) report about pancreatic cancer survival at ASCO GI 2026?

BullFrog AI reported bfLEAP® identified an almost threefold increase in mean survival for specific subgroups in a post-hoc analysis of TH-CR-302.

When and where will BullFrog AI present the pancreatic cancer bfLEAP® data (BFRG)?

The data will be presented at the ASCO GI Symposium on Jan. 9, 2026 in poster session B and will appear in the JCO supplement.

Does the BullFrog AI analysis (BFRG) show glufosfamide is approved for pancreatic cancer?

No; the release describes glufosfamide as an investigational chemotherapeutic agent evaluated in the phase 3 trial TH-CR-302.

What methodology did BullFrog AI (BFRG) use to find responsive patient subgroups?

The company used its bfLEAP® and bfPREP™ platforms for ensemble, data-driven clustering and biomarker discovery in clinical trial data.

Who collaborated with BullFrog AI on the pancreatic cancer analysis (BFRG)?

The study was co-authored with Eleison Pharmaceuticals and researchers from Moffitt Cancer Center.