Toggle navigation sidebar

Toggle in-page Table of Contents

SAMueL Stroke Audit Machine Learning 1

Introduction to SAMueL-1 (Stroke Audit Machine Learning)

Summary

Abstract
Plain English Summary (short)
Plain English Summary (long)
Scientific Summary
Summary slides
Contact and Project Team
YouTube videos

Introduction

An introduction to stroke and thrombolysis
What is clinical audit?
Introduction to machine learning methods
Clinical pathway simulation

Data and software

Data
Software

Descriptive statistics

Outline - what is in this section?

Machine Learning

Assessing accuracy of models with stratified k-fold cross-validation
Logistic Regression
- Logistic Regression Classifier - Fitting to all stroke teams together
- Logistic Regression Classifier - Fitting hospital-specific models
Random Forests
Neural Networks
Ensemble Models

Pathway Simulation

Model building and validation
Testing of alternative what-if? scenarios

Qualitative research and PPI

Qualitative research
Public and Patient Involvement

Appendicies

Acknowledgements

Additional analysis (not in NIHR report)

Using NIHSS to select large artey occulsion stroke patients (most suitable for thrombectomy)
Analysis of stroke admission numbers and types using NIHSS 11+ as a surrogate for large vessel occlusions
Analysis of stroke type and pre-stroke modified Rankin Scale by age
Analysis of pre-stroke modified Rankin Scale

Powered by Jupyter Book

Index

By SAMueL project team
© Copyright 2022.