Stanford Root

Schedule

Stanford Root

Schedule

CS 273D

Generalization and Causality in Biohealth (STATS 354)

UNITS:1-3
GRADING:Letter or Credit/No Credit
LEVEL:Graduate
GER:—

While modern machine learning models often achieve superhuman performance on biohealth benchmarks, they frequently fail to generalize to new hospitals, patient populations, or biological contexts. This course investigates the theoretical and practical foundations of generalizable inference in biomedicine, focusing on the critical gap between predictive performance and mechanistic validity. We will examine how to build "world models" that leverage biological structure, enabling generalization beyond the training distribution. Key topics include: inductive biases (biologically relevant priors), causal representation learning (discovering latent state variables), hybrid models (combining mechanistic ODEs with neural networks), learning from interventional data (spanning high-throughput perturbation screens to policy learning from clinical interventions), and causal transportability. Students will engage with cutting-edge literature, dissecting success stories and analyzing "failure modes" where black-box models fall short of clinical reality.

Syllabus for selected term:
View Spring 2027 Syllabus

Sections

1 Term
Lecture 1Open
ID: 6570
0 / 37 enrolled
DAYS:Monday, Wednesday
TIME:10:30 AM – 11:50 AM
LOCATION:TBD
INSTRUCTOR:
Fox, Emily
units
Lecture 2Open
ID: 6571
0 / 37 enrolled
DAYS:Monday, Wednesday
TIME:10:30 AM – 11:50 AM
LOCATION:TBD
INSTRUCTOR:
Fox, Emily
units

CS 273D: Generalization and Causality in Biohealth (STATS 354)

1-3 units · Letter or Credit/No Credit

While modern machine learning models often achieve superhuman performance on biohealth benchmarks, they frequently fail to generalize to new hospitals, patient populations, or biological contexts. This course investigates the theoretical and practical foundations of generalizable inference in biomedicine, focusing on the critical gap between predictive performance and mechanistic validity. We will examine how to build "world models" that leverage biological structure, enabling generalization beyond the training distribution. Key topics include: inductive biases (biologically relevant priors), causal representation learning (discovering latent state variables), hybrid models (combining mechanistic ODEs with neural networks), learning from interventional data (spanning high-throughput perturbation screens to policy learning from clinical interventions), and causal transportability. Students will engage with cutting-edge literature, dissecting success stories and analyzing "failure modes" where black-box models fall short of clinical reality.

Offered in Spring 2027 at Stanford University.

Spring 2027 sections

  • Lecture — Monday Wednesday 10:30 AM – 11:50 AM — Fox, Emily (Graduate)
  • Lecture — Monday Wednesday 10:30 AM – 11:50 AM — Fox, Emily (Graduate)

More CS courses

  • CS 269I: Incentives in Computer Science (MS&E 206)
  • CS 270: Modeling Biomedical Systems (BMDS 210)
  • CS 272: Introduction to Biomedical Informatics Research Methodology (BIOE 212, BMDS 212, GENE 212)
  • CS 272H: Methods for Reproducible Population Health and Clinical Research (BMDS 244, EPI 203, HRP 203)
  • CS 273B: Deep Learning in Genomics and Biomedicine (BMDS 273, GENE 236)
  • CS 273C: Cloud Computing for Biology and Healthcare (BMDS 222, GENE 222)
  • CS 274: Representations and Algorithms for Computational Molecular Biology (BIOE 214, BMDS 214, GENE 214)
  • CS 275: Translational Bioinformatics (BIOE 217, BMDS 217, GENE 217)
  • CS 275A: Symbolic Musical Information (MUSIC 253)
  • CS 275B: Computational Music Analysis (MUSIC 254)
  • CS 277: Foundation Models for Healthcare (BMDS 271, RAD 271)
  • CS 278: Social Computing (SOC 174, SOC 274)

All CS courses · All departments