Introduzione

The application of big data analytics like machine learning and artificial intelligence holds the potential to transform drug development by means of improved patient outcomes, identification of new treatments and reduction of costs and development time.
This transformation is facilitated not only by the development of the analytical techniques, but also by the ever-expanding availability of data from legacy information, clinical trials, and medical records from participants in data collection initiatives as well as the even broader “real world”.
The enrichment of biological, clinical and patient preference large-scale data could enable computational inference relevant to real-world pharmaceutical research, particularly in the areas of:

  • Identification of predictive factors for patient response
  • More efficient clinical trial management and recruitment
  • Supplementing clinical trial data with real world data
  • Drug candidate selection and pipeline development
  • Orphan drugs, rare diseases and drug repurposing

The 11th edition of the European Statistical Forum is therefore dedicated to understanding if and how these new techniques may be changing the drug development paradigm, to highlighting opportunities and pitfalls, and to exploring how the role of the biostatistician may evolve and interact with these new approaches.
In scope are presentations for example on:

  • Regulatory views on the new analytical techniques incorporating data science elements
  • Advanced methods for response prediction or subgroup identification
  • Novel approaches to trial design incorporating flexible elements for patient stratification
  • Innovative ways to incorporate real world data into the clinical study design or analysis
  • Early identification of Adverse Drug Reactions
  • Real case studies of collaboration between biostatisticians and data scientists
  • Opportunities and risks with novel data science methodologies.

The European Statistical Forum conference will be preceded by a seminar / training on data science and machine learning methodology.

Scientific board
Jens-Otto Andreas - Head Statistical Sciences & Innovation - Bone & New Diseases at UCB Biosciences GmbH
Lisa Comarella - Director Biostatistics at CROS NT
Giacomo Mordenti - Head of Biostatistics & Data Management Europe at Daiichi Sankyo Europe GmbH
Marc Vandemeulebroecke - Global Group Head for Dermatology at Novartis Biostatistics

Who should attend?
The conference is addressed to statisticians, pharmacometricians, physicians, regulators, academia and other experts interested in the field belonging to: Pharmaceutical, and Biotechnology companies, CROs, Universities/Hospitals, Academic Research.

Programma

All times indicated are Central Europe Time

9 November 2020
14:00
16:00
Seminar | Machine Learning in clinical drug development
Markus Lange - Senior Principal Statistical Consultant at Novartis AG
Lorenz Uhlmann - Principal Biostatistician at Novartis AG
16:00
16:10
Break
16:10
18:00
Seminar | Machine Learning in clinical drug development
Markus Lange - Senior Principal Statistical Consultant at Novartis AG
Lorenz Uhlmann - Principal Biostatistician at Novartis AG
10 November 2020
10:00
10:20
Welcome
10:50
11:20
AIML and Statistics: don’t get lost in translation
Graeme Archer - VP & Head, Non-Clinical & Translational Statistics at GlaxoSmithKline Pharmaceuticals R&D

In 2001, Leo Breiman, a Professor in the Department of Statistics, University of California, Berkeley, wrote an influential – and not uncontroversial – paper, in which he stated: “There are two cultures in the use of statistical modelling to reach conclusions from data. One assumes that the data are generated by a given stochastic data model. The other uses algorithmic models and treats the data mechanism as unknown.” The “data modelling” culture (so-named by Professor Breiman) obsesses with identifying a specific form of nature lying inside the black box that turns inputs (of whatever form) into outputs (response values of scientific interest) by specifying parametric data generating mechanisms, fitting these to available data, then making predictions and/or classifications about the output variables conditional on that fit. Data modellers are nearly always what we’d call “statisticians”.

Breiman set this up in opposition to what he called the “algorithmic modelling” culture, which (supposedly) doesn’t care about the structure within the black box, and instead identifies a function that links input with output with sufficiently high accuracy. Such an objective is indeed how the ML scientists of my acquaintance define their work.

But is the disjunction (data vs algorithm) valid? I will argue that it isn’t – that any successful modelling activity requires an understanding of the properties of both data and algorithm, and whether one calls oneself a statistician or an ML scientist is a matter to which the universe, with regard to the validity of one’s predictions, is entirely indifferent.

The real cultural separation, I will argue, between the statistical and ML communities (and why the former keeps losing talent to the latter) isn’t to do with models for data and algorithms, but is much less tangible, and to do with disposition: “you shouldn’t do that”, versus “why not try?” This is the real challenge to the statistical community: can we open-up our attitudes quickly enough to remain relevant in a world that ought to be crying out for our talents. We seem to have boxed ourselves in to something unfashionable; I think we can learn from our ML friends in order to change, and the best way to learn is to work together. I’ll explore all these thoughts in the talk with some examples from my work in pharmaceutical R&D.

Reference
Breiman, L (2001) Statistical Modelling: The Two Cultures. Statistical Science, Vol 16, No.3, 199-231.

10:20
10:50
The challenges and opportunities in using (and regulating) broader data and applied analytics in guidance development and technology assessment in the UK
Thomas Lawrence - Data scientist, Managed Access at NICE

The National Institute for Health and Care Excellence (NICE) provides national guidance and advice to improve health and social care. In January 2020 we published a Statement of Intent to increase and extend the use of data in the development and evaluation of our guidance. This explores:

  • What kind of evidence does NICE currently use to develop guidance
  • What broader types of data are available
  • When and why should broader types of data be considered
  • Practical considerations associated with data analytics

We have since defined the programme to develop a methods and standards framework for activities involving broader sources of data and applied analytics. This is summarised into five key topics, which are crucial to address to ensure best practice in conducting high quality analyses of data. These are Research Governance; Data; Analysis; Results and Dissemination. In addition to these topics, the programme will consider some cross cutting issues ranging from transparency and public trust, to the validation and evaluation of artificial intelligence [AI] in digital technology.

The presentation will give an overview of the transformational journey and the detail on the issues we are considering; which will be crucial for any organisation seeking to ensure their approach is suitable for regulatory assessment/evaluation.

11:20
11:30
Break
11:30
12:00
Challenges and Opportunities of Machine Learning Methods in Biostatistics
Marietta Kirchner - Biostatistician at Institute of Medical Biometry and Biostatistics, University of Heidelberg

In the 21st century, data is the most valuable asset of companies and researchers. For many fields, the availability of Big Data holds the promise to answer questions that would have been out of reach just a couple of years ago. The analysis of Big Data requires expert knowledge, which is why data science is becoming an increasingly important topic. There is an enormous curiosity to explore new approaches and an increased visibility of data analytics to support decision making. However, the focus is often on data analysis and important steps of design, report, and communicating complex concepts are not addressed. Statistics can make a decisive contribution to a successful and safe application of e.g. machine learning (ML) techniques. While there are workshops on data science available, teaching the relevant techniques with real-life application to medical data is currently still a niche subject. To fill this gap, the Department of Medical Biometry (University of Heidelberg) offers a certified course that introduces and deepens the essentials of medical data science. The course is structured into four different modules teaching the skills to answer clinically relevant questions by analyzing Big Data.

This talk provides insight into the programme and addresses the challenges and opportunities of applying ML methods in biostatistics by the presentation of a practical example on prediction dealing with clustered or nested data. Clustered data is mainly analyzed using generalized mixed-effects regression models, because ML algorithms, like tree-based models, usually do not consider clustered data structure. Fokkema et al. (2018) propose the generalized linear mixed-effects model tree (GLMM tree) algorithm which accounts for the clustered data structure and automatically performs variable selection as done by classical tree-based algorithms. The GLMM tree algorithm will be illustrated in the context of developing a prediction tool for tooth loss, where teeth are clustered within patients. To conclude, ML techniques can facilitate workflows, but there are situations where these methods may need further development to be applicable to the particular needs of medical research. Teaching the relevant techniques for a safe application is important.

References: M. Fokkema, N. Smits, A. Zeileis, et al. (2018). Detecting treatment-subgroup interactions in clustered data with generalized linear mixed-effects model trees. Behav Res, 50:2016–2034.

12:00
12:30
Drug candidate selection and pipeline development - a data science approach
Dimitrios Skaltsas - Co-founder & Executive Director at Intelligencia

Biotech and Pharmaceutical companies alike are increasingly relying on Artificial Intelligence applied on expertly curated data to identify complex patterns in order to better understand and minimize the risk of drug development.

Example use case:

What is the probability of technical and regulatory success (PTRS) for a program in clinical development and what are key drivers for this? The application of Machine Learning techniques can help analyze external historic data and provide a powerful perspective. We examine as a case study an ongoing program in Diffuse Large B-Cell Lymphoma (DLBCL), and address several related questions, e.g., (a) how does the PTRS in this program compare to historic averages, (b) how does the PTRS compare to competing ongoing programs, (c) what are the key drivers (e.g., outcomes, number of patients) for the Machine Learning analysis, (d) what are historic benchmarks for such drivers, (e) how do historic benchmarks compare to current trends in ongoing clinical development programs?

12:30
12:40
Morning Wrap up
12:40
14:00
Lunch break
14:00
14:30
Integrating clinical and genetics data for predicting anti-epileptic drug response
Johann de Jong - Principal Scientist / A.I. Data Scientist at UCB

Johann De Jong (UCB); Ioana Cutcutache (UCB); Sami Elmoufti (UCB); Robert Power (UCB); Cynthia Dilley (UCB); Matthew Page (UCB); Martin Armstrong (UCB); Holger Froehlich (former UCB 1)

Epilepsy treatment and drug development are hampered by high rates of non-response. A better understanding of non-response can help clinical trial design and disease management, by focusing therapies on probable responders, and providing optimal treatment earlier in a patient’s disease course.

We collected clinical trial data for the anti-epileptic drug (AED) brivaracetam (n = 235 patients; single trial). We combined a hybrid data-/knowledge-driven feature extraction with advanced machine learning to systematically integrate available clinical and genetic data, and successfully predict drug response (cross-validated AUC = 0.76, external validation cohort: AUC = 0.75). The most important predictors represented a mix of clinical and genetic features, e.g. prior AED use, epileptic focus localization and enrichment of certain classes of genetic variants. Additionally, we showed that by enriching for responders, such models can be used to substantially reduce sample sizes required in confirmatory studies, albeit at the expense of stricter inclusion-/exclusion criteria.

Our analysis represents the first of its kind in epilepsy: Even with limited sample size, integrating clinical and genetic data can inform AED response prediction. Furthermore, such models can substantially impact clinical trial design. This also shows that we can begin thinking more systematically about personalized healthcare in epilepsy.

UCB Pharma-funded

1. Current affiliation: Fraunhofer Institute for Scientific Computing and Algorithmcs (SCAI), Business Area Bioinformatics, Schloss Birlinghoven, 53754 Sankt Augustin, Germany
Email: holger.froehlich@scai.fraunhofer.de

14:30
15:00
Recent examples of how data science is being used in clinical development. Reflections on lessons learnt
David Wright - Head of Statistical Innovation at AstraZeneca

In recent years there has been an massive increase in the use of advanced analytics techniques in a wide variety of areas associated with clinical development.

This presentation will provide details of a number of such examples such as finding drug candidates to include in clinical trials, site selection, subgroup detection and analysis of sensor data. Reflection on what has worked well and where opportunities have not been fully grasped will be given and suggestions for new areas in clinical development where data science could be applied will be provided.

15:00
15:10
Break
15:10
15:50
ROUND TABLE | Data Science in Drug Development: are we in presence of revolution?
Graeme Archer - VP & Head, Non-Clinical & Translational Statistics at GlaxoSmithKline Pharmaceuticals R&D
Marietta Kirchner - Biostatistician at Institute of Medical Biometry and Biostatistics, University of Heidelberg
Johann de Jong - Principal Scientist / A.I. Data Scientist at UCB
Thomas Lawrence - Data scientist, Managed Access at NICE
Dimitrios Skaltsas - Co-founder & Executive Director at Intelligencia
David Wright - Head of Statistical Innovation at AstraZeneca

Moderator: Giacomo Mordenti – Head of Biostatistics & Data Management Europe at Daiichi Sankyo Europe GmbH

15:50
16:00
Conclusion
Relatori
Jens-Otto Andreas
Info Scientific Board

Jens-Otto Andreas

Project Lead Statistician at UCB Biosciences GmbH
Jens-Otto received a diploma in Mathematics in 1993. In 1994 he started his career in Biostatistics at Grünenthal GmbH in Aachen. Here he worked in several therapeutical areas like gynecology and pain. Later on he became a specialist in the Phase 1 area. In 2005 he started to UCB (legacy Schwarz Pharma) as a Project Biostatistician in Phase 1. With the restructuring at UCB in 2008 Jens-Otto became the Head EU Biostatistics supervising Biostatisticians located in Monheim (Germany) and Brussels. Since 2016 he is also the Head of the East Asia Biostatistics of UCB. UCB’s key indications are CNS and immunology. From 2017 to 2019  Jens-Otto was the Head of Statistical Sciences – Bone & New Diseases at UCB Biosciences GmbH. Currently Jens-Otto is holding the position of a Project Lead Statistician at UCB Biosciences GmbH. 
Lisa Comarella
Info Scientific Board

Lisa Comarella

Director Biostatistics at CROS NT
Lisa Comarella joined CROS NT in 2000 as a Statistician and Data Manager. In the past 19 years, she has developed a career in CROS NT as a Principal Statistician and since 2010 has been managing the team of biostatisticians as Director of Biostatistics. In her role as head of the department, Lisa is responsible for the management of statistics resources, supervision of the quality of deliverables, and contributing to complex and strategic projects as statistical lead. Lisa holds a Master’s degree in Statistics and Demographic Sciences from the University of Padua in Italy. She is a scientific committee chair for ESF – the European Statistical Forum, she is a member of associations of statisticians in Europe (PSI, EFSPI).
Giacomo Mordenti
Info Scientific Board

Giacomo Mordenti

Head of Biostatistics & Data Management Europe at Daiichi Sankyo Europe GmbH
After the degree in statistical sciences from the University of Florence (1998), Giacomo stared his career in drug development in Menarini where he was exposed to different therapeutic areas and development phases. In 2007 he moved to Geneva to join Merck Serono, where he led a biostatistical team dedicated to early development in oncology. In 2013 Giacomo joined Grunenthal as global head of Biostatistics. In 2016 he moved to medical device industry in Livanova as Global Head of Data Management and Statistics. In 2020 he joined Daiichi-Sankyo as Head of Biostatistcs and Data Management Europe. Since 2011 he is part of the scientific board of European Statistical Forum; since 2013 he is part of the European Statistical Leader group of EFSPI. His main research interests are in the field of Bayesian statistics, adaptive design and applications of data science techniques to drug development.
Marc Vandemeulebroecke
Info Scientific Board

Marc Vandemeulebroecke

Global Group Head for Dermatology at Novartis Biostatistics
Marc Vandemeulebroecke joined Novartis in 2006, coming from Schering AG in Berlin. He has been supporting development programs in early and late phase development across various disease areas (incl. Neuroscience, Gastrointestinal, Parasitology, Cardio-metabolic, Immunology, Transplant and Hepatology) as statistician and pharmacometrician. Currently he is Global Group Head for Dermatology. Marc holds a maîtrise in mathematics from the University Paris XI, a diploma in mathematics from the University of Münster, a PhD in mathematical statistics from the University of Magdeburg, and an MSc in PKPD modeling from the University of Manchester. He received the Gustav-Adolf-Lienert award from the German Region of the International Biometric Society (IBS) for his PhD thesis, which focused on adaptive designs. He co-authored various scientific publications and one R package and is Associate Editor of Pharmaceutical Statistics. Marc’s current interests include statistical graphics and machine learning.
Graeme Archer
Info Speaker

Graeme Archer

VP & Head, Non-Clinical & Translational Statistics at GlaxoSmithKline Pharmaceuticals R&D
Graeme Archer is VP & Head of the Non-clinical and Translational Statistics (NCTS) group. NCTS ensures integrity in the design, analysis and interpretation of models and experiments developed by GSK R&D’s Research Units – Graeme is particularly focused on ‘translation’ (what do we predict will be observed in man, and how confident in those predictions should we be?) On GSK’s Research governance boards he strives for statistical rigour in portfolio decision-making – and was joint winner of the 2019 Royal Statistical Society’s Pharmaceutical Excellence award for his work on Quantitative Decision-Making. His 1990s PhD, from the University of Glasgow, concerned Bayesian methods for image analysis – early ‘machine learning’? – and as a consequence he is a champion for synergy between the statistical and AI/ML communities. Graeme spent a sabbatical year in 2016 as a speech-writer for a British cabinet minister.
Johann de Jong
Info Speaker

Johann de Jong

Principal Scientist / A.I. Data Scientist at UCB
Johann de Jong obtained his PhD in Computational Cancer Biology from Delft University of Technology. Since then, he has gained experience in a wide variety of domains, ranging from gene regulation and chromatin biology to cancer research and neurological disorders, in both academia (the Netherlands Cancer Institute) and industry (BASF, UCB). He currently works as a Principal Scientist at UCB, and develops and applies methods grounded in machine learning (including deep learning) and statistics for the analysis of biological and clinical datasets, within the context of precision medicine.
Marietta Kirchner
Info Speaker

Marietta Kirchner

Biostatistician at Institute of Medical Biometry and Biostatistics, University of Heidelberg
I studied sports medicine and maths in Frankfurt am Main (Germany) and received my PhD in 2013 working on nonlinear time series analysis. In July 2013 I successfully applied for a position at the Department of Medical Biometry in Heidelberg. As biostatistician I am involved in clinical trials. Additionally, I am responsible for our Master’s programme Medical Biometry/ Biostatistics and set up our certificate programme Medical Data Science in 2018/19. 
Markus Lange
Info Speaker

Markus Lange

Senior Principal Statistical Consultant at 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
Thomas Lawrence
Info Speaker

Thomas Lawrence

Data scientist, Managed Access at NICE
Tom is a data scientist in the data and analytics team at the UK National Institute for Health and Care Excellence (NICE). This team provides central oversight, advice and support on all aspects of data and analytics; spearheading the transformation programme to enable more sophisticated collection, management, storage and exploitation of data across NICE to enable better evidence based decisions across all its business. Tom joined NICE in 2019 following 10 years of working in data science at the University of Manchester.
Dimitrios Skaltsas
Info Speaker

Dimitrios Skaltsas

Co-founder & Executive Director at Intelligencia
Dimitrios is co-founder and Executive Director to Intelligencia, a NY based data science company. Intelligencia focuses on making novel therapies available to patients faster, by assessing their probability of success during clinical development. Prior to that, Dimitris was with McKinsey & Co, as a consultant and later as the domain lead for New Ventures in Life Sciences R&D. He has worked with organizations and governments in North America, Europe, Middle East, Africa and SE Asia. He is an advisor and angel investor to technology companies with a focus on big data. Dimitris holds an LLM from UCL, and an MBA from INSEAD, where he currently serves as an Executive in Residence for AI/ Digital.
Lorenz Uhlmann
Info Speaker

Lorenz Uhlmann

Principal Biostatistician at 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
David Wright
Info Speaker

David Wright

Head of Statistical Innovation at AstraZeneca
Biography available soon
Seminar

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
Contatti

Ilaria Butta
Events & Training Executive
+39 379.1492960
ilaria.butta@lsacademy.com

Valeria Quintily
Project & Scientific Manager
+39 329.4683329
valeria.quintily@lsacademy.com

Quote di iscrizione

CONFERENCE
€ 590,00* Early Bird fee until October 30th, 2020
€ 690,00* Ordinary fee
€ 430,00* Freelance, Academy, Public Administration

PRE-CONFERENCE SEMINAR
€ 570,00* Early Bird fee until October 30th, 2020
€ 665,00*
Ordinary fee
€ 360,00* Freelance, Academy, Public Administration

PRE-CONFERENCE SEMINAR + CONFERENCE
€ 1080,00* Early Bird fee until October 30th, 2020
€ 1195,00*
Ordinary fee
€ 670,00* Freelance, Academy, Public Administration

* for Italian companies: +22% VAT

Fee includes: access to the virtual seminar/conference, organizational support, certificate of attendance, slide presentations in pdf format provided post-event.

Edizioni Passate
2019
Statistical Methodology for the Assessment and Analysis of Risk and Safety Data in Clinical Development
2018
Innovative Clinical Trial Designs
2017
Statistical Methods for rare diseases and special populations
2016
Estimands and Missing Value
2015
Applications of Statistical Methodology in early Drug Development
2014
The current status of the application of Bayesian Methods in Drug Development
Acquista

Ticket non più acquistabile



Sponsors

<p style="text-align: center;">Virtual conference with presentations, slots for Q&amp;A and discussion among delegates.<br />
<em>LS Academy will provide the link to join the conference some days before.</em></p>

Virtual conference with presentations, slots for Q&A and discussion among delegates.
LS Academy will provide the link to join the conference some days before.

<p style="text-align: center;">Virtual conference with presentations, slots for Q&amp;A and discussion among delegates.<br />
<em>LS Academy will provide the link to join the conference some days before.</em></p>