Medical Training AIAI in Genomics and Precision Medicine
You'll be able to interpret AI-assisted genomic findings and reason through their use in variant classification, pharmacogenomics, and treatment selection.
What this track covers
This track covers how machine learning is applied across the genomics workflow, from sequencing data and variant calling to pathogenicity classification and therapy matching. It emphasizes how clinicians can critically evaluate AI-generated genomic outputs rather than treat them as black boxes, including where ACMG criteria and pharmacogenomic and cancer genomics models fit into clinical decisions.
What you will practice
- Interpret an AI-generated variant call and identify where it may need manual review
- Apply ACMG criteria alongside an AI pathogenicity prediction to classify a variant
- Evaluate an AI-based pharmacogenomic recommendation against a patient's clinical context
- Assess a tumor profiling report that used mutation signature analysis for therapy matching
- Explain the limits of an AI genomics tool's output to a patient or care team
Simulator scenario
A simulator case where the virtual patient has a newly reported variant of uncertain significance, and the clinician must decide how to counsel the patient given AI-assisted classification and ACMG evidence.
Board question topics
- Applying ACMG criteria to variant classification
- Strengths and limitations of ML-based variant calling
- Interpreting pharmacogenomic AI recommendations
- Using tumor mutation signatures in therapy matching
Ask the tutor
The tutor only answers from licensed sources (FDA prescribing information, public guidelines and our own material) and says when it has none. Educational use only, never patient-specific advice.
Free during the beta. Sign in with your email, no password.
Start free