Eikosstatistics & data science

Machine Learning & Artificial Intelligence · Medical AI & Healthcare Imaging

Medical artificial intelligence: clinical natural language processing

Public introduction · full guide in Eikos

Introduction

What this guide covers

Introduction Medical Computing Area · NLP

Overview

Topics covered

  • Introduction
  • Clinical Natural Language Processing: End-to-End Modeling
  • Introduction to clinical NLP and unique challenges of the medical domain
  • Clinical tokenization and text preprocessing
  • 2.1 Difficulties of classical tokenization in medical texts
  • 2.2 Subword Algorithms (Subword Tokenization): WordPiece, BPE and SentencePiece

Related concepts

Main connections

  • Self-attention & Transformer architectures
  • Preprocessing pipelines & transform recipes
  • Linear algebra & matrices
  • Vector embeddings & latent space
  • Supervised machine learning
  • Calculus & differentiation

Compatible notation

Mathematical sample in LaTeX

The expression is rendered accessibly, with its LaTeX source preserved below.

P(𝐲∣𝐱)=1Z(𝐱)exp(∑i=1n∑j=1Kλjfj(yi−1,yi,𝐱,i))
View LaTeX sourceP(\mathbf{y} \mid \mathbf{x}) = \frac{1}{Z(\mathbf{x})} \exp\left( \sum_{i=1}^{n} \sum_{j=1}^{K} \lambda_j f_j(y_{i-1}, y_i, \mathbf{x}, i) \right)