WEBINAR on Computational Medicine: An Introduction

Khader Shameer, Kipp W Johnson, Benjamin S Glicksberg and Joel T Dudley

Departments of Medical Informatics and Research Informatics, Northwell Health, New Hyde Park, NY 2Institute of Next Generation Healthcare, Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, Mount Sinai Health System, New York, USA 3 Institute for Computational Health Sciences, University of California San Francisco, San Francisco, USA

 Contact:skhader@northwell.edu

 Hosted by: Dr. Naveen P

Date: 14 December 2017

Host Institute: School of Biotechnology and Bioinformatics, D Y Patil Deemed to be University, Navi Mumbai

 Background: Translational bioinformatics is swiftly developing as “the discipline that will enable the seamless merging of high-dimensional biology and medicine.” Designing right data models (for example, individualome1), visual analytic engines (for example EHDViz, a clinical dashboard development framework2), deep learning (see Deep Patient3) and healthcare context-aware computing platforms (Mount Sinai HealthBase and HealthIO; work-in-progress) are vital for delivering precision healthcare. Integrating health information technology applications using probabilistic modeling and hybrid cloud computing environments will enhance the implementation of translational bioinformatics workflows in healthcare. Automated agents capable of risk estimations, diagnoses, and prognoses, similar to “packet sniffers” in network computing, will become ubiquitous. Building a culture of wellness engagement, as part of preventive care and patient engagement is needed to improve the perception of wellness as an informed choice so that patients will be able to accept it, just like the culture of disease management of the current era4. The scientific, computing and operational challenges of implementing precision healthcare by converging precision wellness and precision medicine are immense. Precision medicine approaches are introducing a multitude of data and tools for effective clinical decision-making. For example, genome sequencing has added a significant amount of information that needs careful evaluation and interpretations to derive clinically actionable information. Computational algorithms, bioinformatics databases, and big data analytics tools are now an integral part of medicine. Thus, computational medicine will be a unique approach to understand the drivers, pathways and outcomes associated with diseases.

Taught program: In this tutorial, we plan to introduce the fundamental concepts of computational medicine and related public resources. No previous programming or genomics experience is required. We will discuss and demonstrate emerging concepts in diagnoses (patient sub-typing5, AI-assisted diagnoses6, and stratification7), treatment (molecular-data driven therapy matching8 and drug repositioning9) and outcome assessment (patient readmission prediction10) with a focus on case studies in oncology and cardiology. We will also discuss analytical strategies based on Bayesian methods, machine learning, and deep learning. We will also demonstrate few of the databases, algorithms, and tools that are relevant to computational medicine.

 Target Audience: This tutorial is targeted at undergraduate, masters, medical or doctoral students with an interest or focus in precision medicine, clinicians interested to learn the landscape of computational medicine (clinical cases will be from oncology or cardiology), researchers and students with a broad interest in translational bioinformatics, clinical informatics, health informatics and biomedical informatics.

 Prerequisite: Background in one of the following areas recommended: biology, medicine, genomics, bioinformatics, computing, programming and Linux.

 Duration: 1.5 hours

 References:

  1. https://www.ncbi.nlm.nih.gov/pubmed/26876889

  2. https://www.ncbi.nlm.nih.gov/pubmed/27013597

  3. https://www.ncbi.nlm.nih.gov/pubmed/27185194

  4. https://www.ncbi.nlm.nih.gov/pubmed/26511511

  5. https://www.ncbi.nlm.nih.gov/pubmed/27307606

  6. https://www.ncbi.nlm.nih.gov/pubmed/27884247

  7. https://www.ncbi.nlm.nih.gov/pubmed/25579574

  8. https://www.ncbi.nlm.nih.gov/pubmed/26221189

  9. https://www.ncbi.nlm.nih.gov/pubmed/28200013

  10. https://www.ncbi.nlm.nih.gov/pubmed/27896982

Supported by the following National Institutes of Health (NIH) grant: National Center for Advancing Translational Sciences (NCATS, UL1TR000067) Clinical and Translational Science Award (CTSA)