Portinari : A Data Exploration Tool to Personalize Cervical Cancer - - PowerPoint PPT Presentation

portinari a data exploration tool to personalize cervical
SMART_READER_LITE
LIVE PREVIEW

Portinari : A Data Exploration Tool to Personalize Cervical Cancer - - PowerPoint PPT Presentation

Portinari : A Data Exploration Tool to Personalize Cervical Cancer Screening Sagar Sen , Manoel Horta Ribeiro , Certus V&V Center and HPV Research Group, Department of Computer Science, Universidade Raquel C. de Melo


slide-1
SLIDE 1

Portinari: A Data Exploration Tool to Personalize Cervical Cancer Screening

Sagar Sen∗, Manoel Horta Ribeiro†, Raquel C. de Melo Minardi†, Wagner Meira Jr.†, Mari Nygård‡

∗ Certus V&V Center and HPV Research Group,
 † Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil, ‡ HPV Research Group, Cancer Registry of Norway, Oslo, Norway 1

slide-2
SLIDE 2

Software’s Impact in Societal Processes

Through which means societies organize themselves?

2

slide-3
SLIDE 3

Software’s Impact in Societal Processes

politics Through which means societies organize themselves?

2

slide-4
SLIDE 4

Software’s Impact in Societal Processes

politics Through which means societies organize themselves?

2

slide-5
SLIDE 5

Software’s Impact in Societal Processes

politics Through which means societies organize themselves? social bonds

2

slide-6
SLIDE 6

Software’s Impact in Societal Processes

politics Through which means societies organize themselves? social bonds

2

slide-7
SLIDE 7

Software’s Impact in Societal Processes

politics Through which means societies organize themselves? social bonds labour

2

slide-8
SLIDE 8

Software’s Impact in Societal Processes

politics Through which means societies organize themselves? social bonds labour

2

slide-9
SLIDE 9

Self-organizing vs. Centralized

3

slide-10
SLIDE 10

Self-organizing vs. Centralized

3

slide-11
SLIDE 11

Self-organizing vs. Centralized

vs

3

slide-12
SLIDE 12

Self-organizing vs. Centralized

vs

3

slide-13
SLIDE 13

4

slide-14
SLIDE 14

Norway’s Screening Program

Cytology

Unsatisfactory 1 -3 months

HPV-test

HPV +ve 6 - 12 months HPV Normal 3 years

New Cytology and HPV- test

ASC-US/LSIL Immediately Cytology Normal 3 years

Colposcopy with biopsy

AGUS/ASC-H/HSIL/ACIS/Ca Immediately HPV Normal and Cytology Normal/ASC-US 3 years HPV +ve Immediately HPV Normal and LSIL or LSIL/AGUS/ ASC-H/ACIS/Ca Immediately Entry intro screening program 25-69 years of age Definitions ACIS: Adenocarcinoma in situ AGUS: Atypical glandular cells of undetermined significance, under cell. ASC-H: Irregular squamous cells with changes suggestive of high grade lesion, but do not meet all the criteria for diagnosis ASC-US: Irregular squamous cells with abnormalities of uncertain significance Ca: All types of cancer Cytology: Test to look at abnormal cells HPV: Humanpapillomavirus HSIL: High-grade squamous intraepithelial lesion LSIL: Low-grade squamous intraepithelial lesion

5

slide-15
SLIDE 15

Triage Algorithm Screening Exams Invitation and Reminders

6

slide-16
SLIDE 16

Triage Algorithm Screening Exams Invitation and Reminders

6

slide-17
SLIDE 17

Triage Algorithm Screening Exams Invitation and Reminders Verification and Validation

6

slide-18
SLIDE 18

Triage Algorithm Screening Exams Invitation and Reminders Verification and Validation

6

slide-19
SLIDE 19

Triage Algorithm Screening Exams Invitation and Reminders Verification and Validation

Statistics by epidemiologists

6

slide-20
SLIDE 20

Triage Algorithm Screening Exams Invitation and Reminders Verification and Validation

Statistics by epidemiologists Data exploration and visualization

6

slide-21
SLIDE 21

7

slide-22
SLIDE 22

What data?

8

slide-23
SLIDE 23

9

slide-24
SLIDE 24

What representation?

10

slide-25
SLIDE 25

Querying

11

slide-26
SLIDE 26

12

slide-27
SLIDE 27

Portinari Flow Diagrams of Future Paths

The flow diagram starts where the query patterns ends, showing Each layer represents the distribution of diagnosis n exams into the future. Hovering over the edges or nodes of the graph shows stats! Portinari allows two charts to be displayed side by side!

13

slide-28
SLIDE 28

Explorations

14

slide-29
SLIDE 29

Exploring effects of screening guidelines

Cytology Normal Cytology Normal 3-4 years

What happens after 3 years to this cohort?

15

slide-30
SLIDE 30

261133 individuals 230,331 individuals 39 individuals

Next Diagnosis in 3 years

16

slide-31
SLIDE 31

280572 individuals 193543 individuals

Next Two Diagnoses

Did not return

17

slide-32
SLIDE 32

Exploring existing screening guidelines

Cytology Normal Cytology Normal 3-4 years

What if women come back in the next 30 days?

18

slide-33
SLIDE 33

4337 individuals

Cytology not good enough for some?

19

slide-34
SLIDE 34

Cytology Normal HPV +ve next exam

Comparing two scenarios in the triage algorithm Come back within 1 year Come back in 1 to 2 years vs. (Guideline)

20

slide-35
SLIDE 35

Returned in 1 -2 years Returned within 1 year

13297 individuals 278 individuals (19) 6.83% HPV +ve (227) 1.61% HPV +ve

21

slide-36
SLIDE 36

Conclusion

➤ Alternative way of verifying and validating paths

taken by people in a socio-technical system.

➤ Use of easy-to-query graph database. ➤ Generalizable to event-driven data. ➤ Generation hypothesis for further statistical

investigation.

22

slide-37
SLIDE 37

https://github.com/manelhr/portinari/ homepages.dcc.ufmg.br/~manoelribeiro/ manoelribeiro

Questions?

Manoel Horta Ribeiro

23

slide-38
SLIDE 38

https://github.com/manelhr/portinari/ homepages.dcc.ufmg.br/~manoelribeiro/ manoelribeiro

Questions?

Manoel Horta Ribeiro

23