MarkerScout: A Disease-Agnostic Machine Learning Framework for Biomarker Prediction from Multi-Scale Mechanistic Models https://www.biorxiv.org/content/10.64898/2026.05.30.727266v1

MarkerScout: A Disease-Agnostic Machine Learning Framework for Biomarker Prediction from Multi-Scale Mechanistic Models https://www.biorxiv.org/content/10.64898/2026.05.30.727266v1

Temporal Biodynamics: An AI Platform for Identification of Stage-Relevant Targets and Biomarkers https://www.biorxiv.org/content/10.64898/2026.06.03.729984v1

Ahmed Abdeen Hamed, Luis M. Rocha: Protocol for evaluating ChatGPT in biomedical association generation and verification using a RAG-enabled, cross-model majority voting workflow https://arxiv.org/abs/2605.30400 https://arxiv.org/pdf/2605.30400 https://arxiv.org/html/2605.30400

Protocol for evaluating ChatGPT in biomedical association generation and verification using a RAG-enabled, cross-model majority voting workflow: STAR Protocols www.cell.com/star-protoco... #LLMs #GenAI #KnolwedeVerification

Protocol for evaluating ChatGPT in biomedical association generation and verification using a RAG-enabled, cross-model majority voting workflow

We present a protocol to evaluate ChatGPT’s ability to generate disease-centric biomedical associations. It outlines how we generate the associations, validate the biological entities using biomedical...

cell.com

After 18th month worth of work this work is finally paying off. Thrilled to publish again along side with Dr. @lmrocha.bsky.social

Luís M. Rocha@lmrocha.bsky.social · 3mo ago

Our reusable protocol for using LLMs in biomedical association extraction and verification, important steps to build network models in #biomedicine is out. Driven by Ahmed A. Hamed & sponsorship from SUNY/Google AI Platform #DigitalMedicine #NetworkScience #AI www.sciencedirect.com/science/arti...

Thrilled to see this piece is finally out!!!

Luís M. Rocha@lmrocha.bsky.social · 2mo ago

Fun work with Ahmed Abdeen Hamed, Ph.D.. using #AI for network inference for drug repurposing in ER+ breast cancer. I would not say eliminate, but reduce hallucinations... Still, very effective and fast at network inference. #BiomedicalInformatics #networkMedicine www.binghamton.edu/news/story/6...

Check out Josh's latest, soon to be Dr. Loecker! @joshloecker.com MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic Models. #AgenticAI #MechanisticModeling #ConstraintBasedModeling #MetabolicModels www.biorxiv.org/content/10.6...

The firing of the domestic terrorist, Kristi Noem, doesn't bring back Renee Good or Alex Pretty. But it is a small measure of justice that feels somewhat right. We must continue to demand full justice until it is done!

Congrats to Dr. Luís M. Rocha & Dr. Ahmed Abdeen Hamed on their SUNY - The State University of New York AI Platform Award to support work on “LLM-Accelerated Multilayered Network Construction for Breast Cancer Drug Repurposing and Combination Discovery through Agentic AI Collaboration." #BingPride

A nice blog on our publication titled: ["From knowledge generation to knowledge verification: examining the biomedical generative capabilities of ChatGPT"] #ChatGPT #KnowledgeVerification #SelfConsistency healthmedicinet.com/hmn-2025-can...

HMN 2025: How Can ChatGPT diagnose you? New analysis suggests promise however reveals information gaps and hallucination points – healthmedicinet

When folks fear that they are getting sick, they’re more and more turning to generative synthetic intelligence like ChatGPT for a prognosis. But how correct are the solutions that AI offers out?

healthmedicinet.com

How Accurate Is ChatGPT When Asked About Your Health? a press release on our publication titled: ["From knowledge generation to knowledge verification: examining the biomedical generative capabilities of ChatGPT"]["https://shorturl.at/UwZKS"] #ChatGPT #Verification www.usnews.com/news/health-...

I don't know if it is me or just #ChatGPT5 is too darn slow and not responding to every prompt before it crashes!!!

@medicalxpress.com.web.brid.gy‬ wrote about our work with @drahmedabdeenhamed.bsky.social‬ : " #ChatGPT’s performance in #biomedical queries, revealing accuracy in identifying disease terms (88–97%), drug names (90–91%), and genetic information (88–98%)" medicalxpress.com/news/2025-07... #LLM

Can ChatGPT diagnose you? New research suggests promise but reveals knowledge gaps and hallucination issues

When people worry that they're getting sick, they are increasingly turning to generative artificial intelligence like ChatGPT for a diagnosis. But how accurate are the answers that AI gives out?

medicalxpress.com

Here is a nice piece of news coverage on our recent publication titled: "From knowledge generation to knowledge verification: examining the biomedical generative capabilities of ChatGPT". #ChatGPT #Health #FactChecking www.sciencenewstoday.org/can-you-trus...

Can You Trust ChatGPT with Your Health?

In a quiet office buzzing with fluorescent lights and rows of high-performance computers, Ahmed Abdeen Hamed stared at something remarkable—and…

sciencenewstoday.org

ChatGPT demonstrates high accuracy in identifying diseases, drugs, and genetic terms, but shows notable gaps and hallucinations, particularly when interpreting symptoms and genetic accession numbers. doi.org/g9tgkz

Can ChatGPT diagnose you? New research suggests promise but reveals knowledge gaps and hallucination issues

When people worry that they're getting sick, they are increasingly turning to generative artificial intelligence like ChatGPT for a diagnosis.

medicalxpress.com

The press release on our recent iScience publication titled: "From knowledge generation to knowledge verification: examining the biomedical generative capabilities of ChatGPT" medicalxpress.com/news/2025-07... #ChatGPT #KnowledgeVerification #MedicalDiagnoses #Hallucination

Can ChatGPT diagnose you? New research suggests promise but reveals knowledge gaps and hallucination issues

When people worry that they're getting sick, they are increasingly turning to generative artificial intelligence like ChatGPT for a diagnosis. But how accurate are the answers that AI gives out?

medicalxpress.com

🤖 What if machines could learn to walk like humans, naturally and robustly, without being told how? A new #iScience study shows it's possible. No #motion data. No #demonstrations. Just smart, adaptive learning. 👉 www.sciencedirect.com/science/arti... #AI #Biomechanics #Robotics #MotorControl