Data Transparency Breaking Down Data Silos for Improved Insight - - PowerPoint PPT Presentation

data transparency breaking down data silos for improved
SMART_READER_LITE
LIVE PREVIEW

Data Transparency Breaking Down Data Silos for Improved Insight - - PowerPoint PPT Presentation

Data Transparency Breaking Down Data Silos for Improved Insight Dr Peter Tormay DH08 Transparency An Organisational View Transparency is all about the release of information by institutions or companies that is relevant for the


slide-1
SLIDE 1

Data Transparency – Breaking Down Data Silos for Improved Insight

Dr Peter Tormay DH08

slide-2
SLIDE 2

Transparency is all about the release of information by institutions or companies that is relevant for the evaluation of these institutions/companies

  • penness

communication accountability

Trust & Reputation

Transparency – An Organisational View

slide-3
SLIDE 3

Transparency Granularity

Policy Process Data

why what how

Hosseini et al, Requirements Eng (2018) 23: 251-275

context quality privacy secrecy meaningfulness

usefulness constraints

slide-4
SLIDE 4

Transparency – a Data View

Transparency is all about the free flow of information between stakeholders for the purpose of informed decision making

Discovery Candidate selection Preclinical testing Phase I Phase II Phase III Marketing /Sales

slide-5
SLIDE 5

Transparency – a Data View

Explicit knowledge Tacit knowledge

Discovery Candidate selection Preclinical testing Phase I Phase II Phase III Marketing /Sales

slide-6
SLIDE 6

Data Quality as a Key Driver in Data Transparency

Wang et al, J. Manage. Inf. Syst. 12, no. 4

Data Quality Intrinsic

Accuracy Believability Objectivity Reputation

Contextual

Value –added Relevance Timeliness Completeness Appropriate amount

Representational

Interpretability Ease of understanding Representational consistency Concise representation Data Model

Accessible

Accessibility Access security

slide-7
SLIDE 7

Transparency – Benefits and Challenges

Benefits

  • Autonomy
  • Self Control and Motivation
  • Accountability
  • Feedback

Challenges

  • Context
  • Privacy
  • Security
  • Blame culture
  • Not a guarantee the right decisions will

be made

slide-8
SLIDE 8

IT Systems as Real World Representation

Real World Real World inferred from the IS Information System Transparency challenges Representation Interpretation

slide-9
SLIDE 9

Ontological Data Model

Formal representation of a knowledge domain, describing its entities, events and processes and the relationships connecting these entities, events and processes

  • To share common understanding of the structure of

information among people or software agents

  • To enable reuse of domain knowledge
  • To make domain assumptions explicit
  • To analyse domain knowledge

Benefits

slide-10
SLIDE 10

Ontologies in Life Sciences

  • Snomed CT
  • ICD-09/10
  • MedDRA

Concerned with the meaning of labels rather than the entity the labels are describing Terminologies – Code lists

slide-11
SLIDE 11

Holons

  • A concept that can be interpreted by itself
  • Classified according to content
  • Contains information
  • Fields, groups and attributes
  • Contains relations to other Holons
  • Each relation has a specific meaning

Patient Study

Id: Age: AgeU: Sex: Id: Design: Blinding: Control:

has is part

slide-12
SLIDE 12

Real World Information Modelling Holons in Action

Patient Results Measurement Sampling

slide-13
SLIDE 13

Real World Information Modelling Holons in Action

Patient Results Measurement Notification Sampling Physician

slide-14
SLIDE 14

Real World Information Modelling Holons in Action

Patient Results Measurement Notification Sampling Indication Treatment Medicine Intake Actual Product Batch Physician

slide-15
SLIDE 15

Real World Information Modelling Holons in Action

Patient Results Measurement Notification Sampling Person Indication Treatment Medicine Intake Actual Product Batch Physician Person CV

Building a Conceptual “Mind Map” of Related Holons

slide-16
SLIDE 16

Real World Information Modelling Holons in Action

Patient Results Measurement Notification Sampling Person Indication Treatment Medicine Intake Actual Product Batch Physician Person CV

Building a Conceptual “Mind Map” of Related Holons

slide-17
SLIDE 17

Ontology vs Instances

Patient 1 Patient 2 Patient 3

slide-18
SLIDE 18

Graph Database Implementation

  • individual nodes (identity index)
  • node types (node type identity index)
  • property values (property index)
  • existence of indirect relationships (relation index)

S 1 P 1 P 2 P 3 V 1 BP n BP h V 1 BP h V 2 BP h BP n V 1 T A T B T A

slide-19
SLIDE 19

Graph Database Query

What adverse events have been reported for patients with elevated liver values

S 1 P 1 V 1 LV 1 V 2 LV 10 P 2 V 1 V 2 LV 1 AE Headache AE Nausea LV 2 AE Insomnia AE Depression

slide-20
SLIDE 20

Graph database query

S 1 P 1 V 1 V 2

LV 10 AE Headache AE Nausea

Select data: Type of Node: “Patient” With (Type of Node: ”Liver Value”, Property: ”Value > 5”) Fetch: Type of Node:”Adverse Event”, property:”Name”

What adverse events have been reported for patients with elevated liver values

slide-21
SLIDE 21

Conclusions

  • Data transparency is not just externally but

also internally focused

  • It enables autonomy, self motivation as well

as accountability

  • It makes domain knowledge explicitly available across the company
  • New technology such as graph databases are data transparency

enablers

  • Ontology based information models with focus on nodes enable

better data structures and search capabilities

slide-22
SLIDE 22

Thank you

Peter Tormay peter.tormay@capish.com Anna Berg anna.berg@capish.com

?