Guided Notes

Machine Learning for Informaticists

Supervised vs unsupervised learning, the model lifecycle, features and labels from EHR data, evaluation (discrimination and calibration), bias, drift and what informaticists must ask before deployment.

Types of machine learning

Slide 1 / 5
TypeLearns fromHealthcare example
SupervisedLabeled outcomesPredict 30-day readmission; detect pneumonia on X-ray
UnsupervisedPatterns without labelsCluster patient subgroups with similar trajectories
ReinforcementRewards from actionsResearch on treatment strategies (e.g. sepsis fluids)
Deep learningLarge data with neural networksImaging, waveforms, text
Foundation models / LLMsMassive text (and multimodal) dataSummaries, drafting, extraction
← Clinical Research Informatics