9 November 2020 | 2:00 PM – 6:00 PM CET
PRE-CONFERENCE SEMINAR

Machine Learning in clinical drug development
Advanced statistical tools and techniques

Introduction
There is tremendous interest and excitement surrounding the application of Machine learning (ML) in drug development. Machine Learning (ML) tools can process information much faster, cheaper and more accurately than any human, and some people expect no less than a change to the clinical drug development paradigm.
In this online course, we will get the participants up to speed with the opportunities of ML in drug development. We will discuss the statistical details behind the ideas, the implementation using software (R) as well as the interpretation of the results. Any examples will be inspired by real problems.

Who should attend?
Recommended for any quantitative scientist seeking an overview of machine learning and artificial intelligence (AI) and its application in the pharmaceutical industry.

Programme

Overview of ML in pharma – “match made in heaven” or “it’s complicated”?
Discussion of key ML concepts
Key elements and principles for building and assessing supervised machine learning methods (e.g. loss functions, metrics, cross-validation, hold out data, bootstrap)
(Regularized) regression models such as Lasso, Ridge, Elastic Net, GAM
Ensemble methods based on classification and regression trees (e.g bagging, random forest and boosting)
A basic knowledge of Neural Networks and how they lead to deep learning methods

Type of training
Shared presentation by Markus und Lorenz that aims to provide theoretical background and practical examples. Questions are welcome, we are hoping for lively discussions.

Lecturers
Markus Lange, Senior Principal Statistical Consultant – Novartis AG

  • Studies of mathematics at the Ruhr-University Bochum
  • Doctoral thesis at the Hannover medical school
  • More than 5 years of industry experience
  • Senior Principal Statistical Consultant at Novartis

Lorenz Uhlmann, Principal Biostatistician – Novartis AG

  • Studies of statistics at the LMU Munich
  • Doctoral thesis at the Institute for Medical Biometry and Informatics (IMBI), Heidelberg University
  • Head of the working group “Statistical Modeling” at the IMBI
  • Principal Biostatistician at Novartis

Participant experience
The attendees should have solid knowledge of general statistics (such as generalized linear models). Basic knowledge of R programming is recommended but not required.

At the end of the training, you will be able to:

  • understand different types of machine learning (e.g. supervised, unsupervised, re-enforcement) and the types of problems where they might be applied
  • identify whether it is appropriate to apply machine learning or artificial intelligence techniques to a drug development problem
  • assess and provide guidance on ML and AI solutions proposed by others (e.g. external vendors)
  • interpret results from machine learning solutions
  • get started if you want to apply the discussed techniques on your own
 Indietro