AI for Evidence-Based Medicine

AI for Evidence Generation

How can AI help generate the evidence that we need?

See the work →
AI for Evidence Utilization

How can AI help people fully utilize the existing evidence?

See the work →
Medical AI Evaluation

How do we rigorously evaluate medical AI systems?

See the work →

AI for Evidence Generation

How can AI help produce the evidence at each tier of the pyramid?

AI for Evidence Utilization

How can AI fully utilize existing evidence?

AI for Evidence Generation and Utilization

How can AI generate — and make use of — medical evidence?

Systematic Reviews
TrialMind
Automating evidence synthesis
TrialMind
npj Digit Med, 2025
Clinical Trials
TrialGPT
Zero-shot trial matching
TrialGPT
Nat Commun, 2024
Case Reports
PMC-Patients
Patient-level case corpus
PMC-Patients
Scientific Data, 2023
Retrieve
LADER
Log-augmented dense retrieval
LADER
SIGIR, 2023
PubMed and Beyond
Survey of AI search tools
PubMed and Beyond
eBioMedicine, 2024
MedCPT
Zero-shot PubMed retriever
MedCPT
Bioinformatics, 2023
Summarize
MedRAG
Benchmarking medical RAG
MedRAG
ACL Findings, 2024
i-MedRAG
Iterative follow-up RAG
i-MedRAG
PSB, 2025
MedReview
Summarizing systematic reviews
MedReview
npj Digit Med, 2025
MedCite
Verifiable answer citations
MedCite
ACL Findings, 2025
Verify
Med-V1
Scalable evidence attribution
Med-V1
arXiv, 2026
GeneAgent
Self-verifying gene-set agent
GeneAgent
Nature Methods, 2025
Medical AI Evaluation

How do we know when medical AI is good enough to trust?

routinely measured
rarely measured