PSI Training Course: Introduction to Machine Learning

Dates: 
Session 1 - Monday 13th October 2025
Session 2 - Tuesday 14th October 2025
Session 3 - Wednesday 15th October 2025
Session 4 - Thursday 16th October 2025
Time: 09:00 - 12:30 BST
Location: Online via Zoom

Who is this event intended for? 
This course is aimed at statisticians who are new to or with limited experience of machine learning. 

What is the benefit of attending? 

Attendees will learn about a range of topics in machine learning, including practical sessions in R.

Overview

Four sessions will include ML foundation (including an introduction, data exploration for ML and dimensionality reduction and feature selection), Supervised learning (including support vector machines and model evaluation and interpretation), model optimization and unsupervised learning (including clustering) and advanced topics (including neural networks, deep learning and large language models).

Cost

Early Bird PSI Members: £320 +VAT
PSI Members: £360 +VAT

Early Bird Non-PSI Members: £430 +VAT
Non-PSI Members: £470 +VAT
*Please note: Non-Member rates include PSI membership until 31 Dec. 2025.

Registration

Early Bird registration closes on Friday 5th September.
To register for this event, please click here.

Agenda

Day 1: ML Foundation

• Definitions and terminology
• Key aspects of ML workflow
• Planning
• Pre-processing
• Data splitting
• Modelling, cross validation, hyperparameter estimation
• Evaluation
• Reporting
• “ML in a day”. Overview of simple ML workflow using R packages dplyr, caret, ggplot2 using logistic regression. This will be used as a starting point to exemplify key aspects of ML, and as a point of comparison for further methods such as Elastic Net (regularised regression), gradient boosting and neural networks.
• Common pitfalls and key considerations for using ML models in practice, and reviewing ML analyses, with a focus on the analysis of clinical trial data

Day 2: Supervised learning

• What is supervised learning?
• Definitions and examples of scenarios
• Supervised learning workflow (short recap)
• Supervised Algorithms:
• LASSO and Elastic Net
• Decision trees and Random Forest
• Support Vector Machines
• Evaluation and interpretation of these algorithms
• Practical session in R: Application of above methods in caret

Day 3: Unsupervised learning

• Definitions and comparison to supervised learning
• K-means, PCA, Non-linear approaches such as tSNE
• Worked examples in R

Day 4: Neural Networks and Deep Learning

• DEMO: ML in SASHow to use R ML from SAS Viya
• How to use no-code/low-code ML
• How to use SAS ML procs in R Studio
• Introduction to neural networks and basic architectures
• Deep learning, Large Language models, Computer Vision
• Discussion of Machine Learning vs Statistics: what are the differences, how much to they overlap, when to use what 

Speaker details

Speaker	Biography	Abstract
Jolyon Faria Data Science Director, AstraZeneca	Jolyon Faria is in the Clinical Data Sciences Lung Team within Oncology Data Science & AI, Oncology R&D, in AstraZeneca. His role is to lead and perform retrospective analyses of AZ clinical trials, Real World Data and multimodal data, with a focus on Statistics and Machine Learning, to inform the AZ Strategy for instance for PhIII Investment Decisions. He has a background in Biology: PhD (Univ. Leeds); Postdoc (Princeton Univ.), and Applied Statistics: (MSc Univ. Oxford) and is a Chartered Statistician (CSTAT; Royal Statistical Society, UK).
Moira Verbelen Computational Methodology Lead, UCB	Moira Verbelen is Computational Methodology Lead in the Advanced Methods and Data Science team at UCB and is passionate about adopting and implementing cutting-edge AI methods in pharmaceutical research, in particular delivering AI solutions throughout all phases of clinical development. With a background bridging Pharmaceutical Sciences and Biostatistics, Moira holds a PhD from King’s College London, specializing in Machine Learning applied to Pharmacogenetics	This session introduces supervised learning in the context of pharmaceutical data analysis, focusing on its definition and practical applications. We'll briefly discuss the supervised learning workflow before diving into key algorithms including LASSO, Elastic Net, Decision Trees, Random Forests, and Support Vector Machines. Emphasis will be placed on how to evaluate and interpret these models effectively. Participants will gain hands-on experience using the caret package in R.
Leo Souliotis Associate Director, RWE, AstraZeneca	Leonidas Souliotis is part of the CDS Hematology team within the Oncology Data Science at AstraZeneca. His role includes developing statistical and ML methods and tools for evidence synthesis in the Heme space. He is also leading an internal course on how to use Python for Data Analysis. He is a Data Camp instructor, after developing the “Efficient Python coding in pandas". He has a background in Statistics: MSc (Imperial College London), PhD (University of Warwick).
Dan de Vassimon Manela UCB	Dan de Vassimon Manela is a Machine Learning R&D and Innovation Lead at UCB and is interested in using Probabilistic Machine Learning methods to solve clinical problems across the pharmaceutical development chain. He has a background in Physics (BA, MSc Cambridge) and Statistical Machine Learning (MSci UCL).