Christine Von Raesfeld introduced me to the people at Arena International, who asked me to give a series of talks at their conferences. 

Here's the list of talks, their outlines and links to the associated blog posts.

It is repetitive, but repeating the same points has allowed me to sharpen the presentions, and to get more insight into the material.  For example, I figured out that hackathon teams anologized to tumor boards a few years ago, but after repeating the point, it occurs to me that each "arm" (tumor board participant) is elucidating a possible future for the patient.  And so once each future is characterized, the patient can better determine which alternative future they want to pick.

If you are interested in reading an article, check out the last link on this page: 20210314 - Hackathons: Catalyzing Research using Ensembles of Classifiers

20241023 - 21st BioPharma Clinical Trials Nexus Conference (New Jersey): Using AI to Traverse the Path from Clinical Trials to Personalized Medicine

presentation.pdf

Using AI to Traverse the Path from Clinical Trials to Personalized Medicine

• Rare Cancers: I have one. They aren’t researched much. How I deal with it.
• Oncologic Clinical Trials: Success rate is lousy. My goal is to increase it.
• Portfolios, Juries, Parole and Tumor Boards: I do this using Personalized Tumor Boards.
  • Tumor Boards:
    • “A meeting of healthcare professionals that discuss complex cancer cases to determine the best treatment plan for a patient.”
  • Insights from two 13 member Tumor Boards I created.
    • EVEREST: "Should Bill participate in the EVEREST Trial".
    • Pro/Photon: "Should Bill use Proton or Photon radiation to treat his Brain Tumor."
• Hackathons: 80 person competition between 17 “gamified” Tumor Boards
  • "Result ranking" functions are used to determine who won the game.
• LLMs: Increase tumor board membership to 15 by adding claude.ai and chatGPT-4o.
• Moderators: “Moderate” the EVEREST and Pro/Photon Tumor Boards using LLMs.
  • Human tumor board members spend a lot of time explaining their positions to each other. 
• You can help!.

20240910 - Clinical Trials in Rare Diseases (Burlingame): presentation.pdf

20240423 - Clinical Trials in Oncology West Coast (Burlingame): Using AI methods to enable clinical trial success

• presentation.pdf, presentation.mp4
• Increasing Clinical Trial success rate by better patient pre qualification
• Tumor boards provide personalized advice and pre-qualify patients.
• Hackathons formalize, scale and tune the tumor board process
• Working to fully automate Hackathons

​20240416 - Festival of Biologics (San Diego): Using Gamified Tumor Boards to accelerate Cancer Research

• Ad hoc tumor boards aided me in my Medical Decisions:
  • Evaluating a clinical trial and radiation therapy
• Hackathons formalize and scale the tumor board process:
  • Focusing 17 Gamified Tumor Boards on one rare disease patient advanced Research 
• Hackathons can be fully automated:
  • Replacing Patients and Tumor Board members with LLMs (Large Language Models).

20240415 - Festival of Biologics (San Diego): Alternatives after Patients are past Standard of Care and have run out of Clinical Trials: p1RCC Hackathon Report

• The Problem: From the Patient POV, Medical research has issues
  • Reproducibility, Reporting, Novelty/Agility, Urgency, Inclusion, Cost/Speed
• A Solution: "Hackathons": Patient led research modeled on Kaggle
  • One Patient, Many Competing Teams, Unrestricted Rich Data Set
• p1RCC Hackathon 2018, 2020
  • Report and Conclusions

20240206 - Outsourcing in Clinical Trials West (Burlingame): A Patient’s Approach to Innovative Clinical Research

• Room for improvement: Current Critiques of medical innovation
  • As outlined by the FDA's Janet Woodcock and Dr. Azra Raza
• Hackathons: Using Gamified Tumor Boards to advance Research on particular patients
  • Oncologic clinical trials, where one researcher looks at "n" patients, fail 96.5% of the time.
  • A better building block is a "tumor board" where n doctors look at one pateint.
  • We describe a 2018 "hackathon" consisting of 17 competing tumor boards (each with n doctors) looking at one patient.
  • The "winning" team had the best research process.
• Research Agents and Digital Twins: Next generation environments for automated data sharing and research
  • This can be autometed. Human teams are digitized using LLM technology.

Hers's a list of related blog posts (upon which the above presentations are based), 

• 20231110 - Sigma Xi's iFoRE (San Diego): Reimagining Research
• 20230406 - ARPA-H DASH Submission: Gamifying Research
• 20211103 - Catalyzing Research Using Patient Centered Games
• 20210918 - Vanessa Hackathon: Healing research
• 20210314 - Hackathons: Catalyzing Research using Ensembles of Classifiers