Evidence Thread AI

Exploring AI for evidence generation.

An independent research project testing AI workflows for literature review, evidence synthesis, and research planning in Medical Affairs.

Explore case studies

Research pipeline

Literature screening

Apply PICO criteria to abstracts and evaluate proposed decisions against human review.

Current stage: Initial pilot

View case study

Evidence synthesis

Organize study findings by population, intervention, and outcome, with links to sources.

Current stage: Concept design ongoing

Evidence gap assessment

Explore whether AI can identify unanswered questions that warrant further study.

Current stage: Concept design ongoing

Knowledge networks & GraphRAG

Connect evidence across studies and retrieve answers with supporting publications.

Current stage: Concept design ongoing

Stages describe research maturity. Validation means evaluation against prespecified criteria; deployed means active use by an intended user or team.

AI-assisted abstract screening

This pilot evaluates title and abstract screening for systematic literature reviews. The workflow uses prespecified PICO criteria (population, intervention, comparator, and outcomes) to propose screening decisions for human review.

An initial set of PubMed abstracts has been screened, reviewed, and loaded into a prototype evidence graph. The next evaluation will compare AI screening proposals with independent human decisions and track missed records, uncertain cases, and rationales that need closer review.

Illustrative screening workflow
  1. Source abstractTitle, abstract, and PICO criteria
  2. AI agent 1Assesses eligibility
    AI agent 2Independently assesses eligibility
  3. Screening proposalCombines assessments and flags uncertainty
  4. Human reviewChecks the source and makes the decision

Publications

Conference abstract in preparation

AI-assisted abstract screening for systematic literature reviews

Planned report of the abstract-screening pilot using prespecified PICO criteria.

Insights

Notes on methods, limitations, and lessons from the research.

Team

Stefan Kolata, PhD

Founder & Research Lead

Global Medical Affairs leader with 15+ years of combined experience in scientific research and biopharma, spanning medical strategy, global launch readiness, evidence generation, and lifecycle planning.

More about Stefan

I combine scientific expertise with strategic thinking, cross-functional leadership, and experience navigating complex global development alliances. I earned my PhD at Rutgers University, with a concentration in behavioral neuroscience.

I champion responsible AI adoption for evidence synthesis and medical communications in regulated environments. I received an internal AI Innovation Award for work on secure multi-agent verification workflows and served on an enterprise AI group supporting governance and global AI training.

I’ve been invited to speak at international life sciences and biotechnology conferences on Medical Affairs, scientific publications, and compliant AI innovation.

Wayne Su

HEOR & Global Value Strategy Advisor

Oncology integrated evidence generation leader with 16+ years in HEOR and RWE. Wayne advises on evidence generation, health outcomes, and global value strategy. He helps shape research concepts and evaluate how AI-assisted workflows can support evidence synthesis and address questions relevant to clinical and payer decision-making.

Connect on LinkedIn

Manish Patel, PharmD

Medical Affairs Advisor

Medical Affairs and clinical development leader with 20+ years of experience in biopharma. Manish contributes a Medical Affairs perspective to research design, human review, and new concept development. He helps assess whether the workflows address practical scientific questions and support evidence review.

Connect on LinkedIn

About the project

Evidence Thread AI is an independent research project. The team develops and tests workflows using published literature, with scientific reviewers checking proposed decisions against the source.