Clinical Trial Industry Moon shots AI could solve

Dear Start-ups! So you have cutting edge AI platform and talent who can solve for complex problems? Here's your invitation – the presentation will walk through the moon shots, mountain shots and flare shots of our industry (Pharma/Biotech) – from writing a Study Protocol document to designing/developing studies, collecting & cleaning data, standardizing said data to submitting objective evidence to regulatory bodies.

Transcript

1. Dear Startups Chandi Kodthiwada
2. Opportunity for AI Impact on Clinical Trials • Moon shots: Long-shot goals, may take years, a lot of collaboration and cutting-edge innovation • Flare Shots: Short-focused efforts can solve crisply defined problem sets • Mountain Shots: Large efforts required to work with Regulatory, Pharma and everyone involved to arrive at a pragmatic solution – short, validating steps are paramount
3. Moon shots Leap in value Transformations
4. Overarching AI engine to run Clinical Trials • Help Design Protocols – Reduce Protocol Amendments & Increase Patient Recruitment Rates • Machine learning driven Study development & Data Standardization • AI companion for Study Conduct: Data Management, Patient Safety, Medical Monitoring etc. • NLP/U generated Patient Narratives, CSR & other Study TLFs
5. Flare shots Help at the moment of need
6. Help at the precise moment of need (aka increase the speed of knowledge acquisition ) • Mine, Extract, Classify/Categorize, Learn from various unstructured content – Public & Private content • Connect Researchers to Research • Connect Patients with Drugs • Inference Engines: Recommended response for Regulatory responses, Best Next Step for Protocols (What-If Scenarios) • Event driven notifications with just-in-time predictions with explainable AI • Application of NLP/Voice assistants across the spectrum of Clinical Trial Functional teams (Ops, data management, monitoring, safety etc.) • AI/NLP generated PSUR/ASRs
7. Mountain Shots Herculean efforts with Just enough Just in-time execution
8. Just Enough Just In-Time • ML-driven data harmonization of all historical trial-data at Pharma • ML-generated continuous insights for enabling AI-assisted human study conduct –proactive fraud detection, data cleansing, patient cohort analysis etc. • Synthetic Cohorts – Reduce the burden and cost of running a clinical trial by enabling a competitor drug or Placebo synthetic Cohorts • S/AE (Adverse Event) prediction for critical-care patients
9. LetÊs build! Chandi Kodthiwada