Big Data meets Medicines Regulation: Which Data and when? Luca - - PowerPoint PPT Presentation

big data meets medicines regulation
SMART_READER_LITE
LIVE PREVIEW

Big Data meets Medicines Regulation: Which Data and when? Luca - - PowerPoint PPT Presentation

Big Data meets Medicines Regulation: Which Data and when? Luca Pani, MD EUMTB Chair - CHMP and SAWP Member, EMA London, UK Dept. of Psychiatry and Behav. Sci., University of Miami Miami, USA lpani@miami.edu - @Luca__Pani Public


slide-1
SLIDE 1

Big Data meets Medicines Regulation:

Which Data and when?

Luca Pani, MD

EUMTB Chair - CHMP and SAWP Member, EMA – London, UK

  • Dept. of Psychiatry and Behav. Sci., University of Miami – Miami, USA

lpani@miami.edu - @Luca__Pani

slide-2
SLIDE 2

Public Declaration of transparency/interests*

The view and opinions expressed are those of the individual presenter and should not be attributed to AIFA / EMA

* Luca Pani, in accordance with the Revised Conflict of Interest Regulations approved by AIFA Board of Directors (25.03.2015) and published on the Official Journal of 15.05.2015 according to EMA policy /626261/2014 on the handling of the conflicts of interest for scientific committee members and experts. NB For this talk I receive NO compensation.

slide-3
SLIDE 3

Type and Size of Data

slide-4
SLIDE 4

What are we talking here really?

slide-5
SLIDE 5

What are we talking here really?

If 1 by byte e equa quals ls a a grain in o

  • f rice,

e, t then hen 1 Zetta tabyte te w will fill t l the P e Pacif ific ic Ocea ean wi n with r h rice. e.

slide-6
SLIDE 6

58% 41% 62%

TRANSITIONING FROM DATA TO KNOWLEDGE IS A MAJOR CHALLENGE1 SYSTEMS CANNOT PROCESS LARGE VOLUMES OF DATA FROM DIFFERENT SOURCES GROWTH OF UNSTRUCTURED, NON- CONTEXTUALIZED DATA2

1 PwC 5TH annual IQ survey 2 International Data Group Research

Data ≸ Information ≸ Knowledge

slide-7
SLIDE 7

Automated categorization

Relative prominence of research activities Perceived influence on

  • ther health care

providers Comparative clinical behavior Level of engagement with industry

Programmatic data transformation:

Deep Learning Unprecedented volumes of public data Billions of data connections made

Pillars of Exponential Data Paradigmatic Shock

Examples: Monocles; Zephyr Health

slide-8
SLIDE 8

Innovative data models could be game changer

Entity table Data source 1 Data source 2 Data source n

Traditional, relational model Entity centric model

Entity Attributes Entity Attributes Entity Attributes Meta data …… …… …… …… …… …… …… …… …… …… …… …… ……

slide-9
SLIDE 9

In summary we are still dealing with…

slide-10
SLIDE 10