Important Dates:

• Deadline for submissions: October 17, 2011, 11:59 pm PT
• Notification of acceptance: October 31, 2011

Confirmed Invited Speakers:

• Prof. Dr. Pierre Baldi, Director of the Institute for Genomics and Bioinformatics, UC Irvine
• Prof. Dr. Bertram Müller-Myhsok, Head of Statistical Genetics Group, Max Planck Institute for Psychiatry, Munich
• Prof. Dr. Florence Demenais, Genetic Variation and Human Diseases Laboratory (U946), Inserm-University Paris Diderot, Fondation Jean-Dausset, Paris

Background:

Technological advances to profile medical patients have led to a change of paradigm in medical prognoses. Medical diagnostics carried out by medical experts is increasingly complemented by large-scale data collection and quantitative genome-scale molecular measurements. Data that are already available as of today or are to enter medical practice in the near future include personal medical records, genotype information, diagnostic tests, proteomics and other emerging ‘omics’ data types.

This rich source of information forms the basis of future medicine and personalized medicine in particular. Predictive methods for personalized medicine allow to integrate these data specific for each patient (genetics, exams, demographics, imaging, lab, genomic etc.), both for improved prognosis and to design an individual-specific optimal therapy.

However, the statistical and computational approaches behind these analyses are faced with a number of major challenges. For example, it is necessary to identify and correcting for structured influences within the data; dealing with missing data and the statistical challenges that come along with carrying out millions of statistical tests. Also, to render these methods useful in practice computational efficiency and scalability to large-scale datasets are an integral requirement. Finally, any computational approach needs to be tightly integrated with medical practice to be actually used and the experiences gained need to be fed back into future development and improvements.

To both address these technical difficulties ahead and to allow for an efficient integration and application in a medical context, it is necessary to bring the communities of statistical method developers, medics and biological investigators together.

Goal:

The purpose of this cross-discipline workshop is to bring together machine learning and healthcare researchers interested in problems and applications of predictive models in the field of personalized medicine. The goal of the workshop will be to bridge the gap between the theory of predictive models and the applications and needs of the healthcare community. There will be exchange of ideas, identification of important and challenging applications and discovery of possible synergies. Ideally this will spur discussion and collaboration between the two disciplines and result in collaborative grant submissions. The emphasis will be on the mathematical and engineering aspects of predictive models and how it relates to practical medical problems.

Although, predictive modeling for healthcare has been explored by biostatisticians for several decades, this workshop focuses on substantially different needs and problems that are better addressed by modern machine learning technologies. For example, how should we organize clinical trials to validate the clinical utility of predictive models for personalized therapy selection? This workshop does not focus on issues of basic science; rather, we focus on predictive models that combine all available patient data (including imaging, pathology, lab, genomics etc.) to impact point of care decision making.

Workshop schedule (December 16, 2011)

7.30-7.35 Welcome and Introduction

Workshop Chairs

7.35-8.25 Keynote: From Genomes to Personalized Medicine: Reverse Engineering Biological Systems

Pierre Baldi

8.25-9.15 Keynote: New advances in the genetics of melanoma: how can it contribute to personalized medicine?

Florence Demenais

9.15-10.05 Poster spotlight, poster session and coffee break

Jose Leiva-Murillo, Jesse Davis, Anima Singh, Yonatan Halpern

10.05-10.30 Detecting similar high-dimensional responses to experimental factors from human and model organism

Tommi Suvitaival

16.00-16.05 Welcome and Introduction

Workshop Chairs

16.05-16.55 Keynote: From bed to bench and back: current perspectives of personalized medicine in psychiatry

Bertram Müller-Myhsok

16.55-17.20 Inferring a measure of physiological age from multiple ageing related phenotypes

David Knowles

17.20-18.20 Poster spotlight, poster session and coffee break

Ali Faisal, Jenna Wiens, Christoph Lippert, Gad Abraham, Norman Poh

18.20-18.45 Accuracy test for genome wide selection of bio-markers

Adam Kowalczyk

18.45-20.00 Panel discussion

Invited Speakers

Accepted contributions:

Oral presentations

Inferring a measure of physiological age from multiple ageing related phenotypes

David Knowles (Knowles_etal.pdf)

Accuracy test for genome wide selection of bio-markers

Adam Kowalczyk (Kowalcyzk_etal.pdf)

Detecting similar high-dimensional responses to experimental factors from human and model organism

Tommi Suvitaival (Suvitaival_etal.pdf)

Poster spotlights

Sparse Linear Models Explain Phenotypic Variation and Predict Risk of Complex Disease

Gad Abraham (Abraham_etal.pdf)

Discovering Latent Structure in Clinical Databases

Jesse Davis (Davis_etal.pdf)

Biomarker discovery via dependency analysis of multi-view functional genomics data

Ali Faisal (Faisal_etal.pdf)

Visualization and Prediction of Disease Interactions with Continuous-Time Hidden Markov Models

Jose Leiva-Murillo (LeivaM?_etal.pdf)

FaST? linear mixed models for genome-wide association studies

Christoph Lippert (Lippert_etal.pdf)

Modeling Rate of Change in Renal Function for Individual Patients: A Longitudinal Model Based on Routinely Collected Data

Norman Poh (Poh_etal.pdf)

Learning Classification Trees for Personalized Cardiovascular Risk Stratification

Anima Singh (Singh_etal.pdf)

On the Promise of Topic Models for Abstracting Complex Medical Data: A Study of Patients and their Medications

Jenna Wiens (Wiens_etal.pdf)

Patient Surveillance Algorithms for the Emergency Department

Yonatan Halpern (Halpern_etal.pdf)

Topics of Interest:

We welcome submissions on any aspect of machine learning in statistical genetics and personalized medicine. We would like to encourage submissions on any of (but not limited to) the following topics:

• Preventive medicine
• Therapy selection
• Statistical genetics
• Medical genetics
• Precision diagnostics (more precise diagnostics, diseases sub-typing)
• Companion diagnostics/Therapeutics
• Patient risk assessment (for incidence of diseases)
• Personalized medicine
• Integrated diagnostics combining multiple modalities like imaging, genomics and in-vitro diagnostics

Submission Instructions:

The deadline for submissions has now passed.

Organizers

• Karsten Borgwardt, Max Planck Institutes and University of Tübingen, Germany
• Oliver Stegle, Max Planck Institutes Tübingen, Germany
• Shipeng Yu, Siemens Healthcare, USA
• Glenn Fung, Siemens Healthcare, USA
• Faisal Farooq, Siemens Healthcare, USA
• Balaji Krishnapuram, Siemens Healthcare, USA