data science og big data kan bidra til bedre helse · data science in health •all this comes, not...
TRANSCRIPT
![Page 1: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/1.jpg)
Data science og big data
kan bidra til bedre helse
Arnoldo Frigessi
OCBE Oslo Centre for Biostatistics and Epidemiology
University of Oslo
Oslo University Hospital
![Page 2: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/2.jpg)
Big Data in Health
1.Genetics and genomics
2.Electronic health records, incl. images, videos, text
3.Biomedical sensors, incl. wearables, apps
![Page 3: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/3.jpg)
![Page 4: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/4.jpg)
2002 2013 2016 20182005
![Page 5: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/5.jpg)
![Page 6: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/6.jpg)
Millions of connected wearables worldwide
![Page 7: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/7.jpg)
1.Geography
![Page 8: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/8.jpg)
Data Science in Health
Bio-medicine
StatisticsComputer
science
Machine
learning
Bio
informatics
Bio
statistics
DATA
SCIENCE
![Page 9: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/9.jpg)
Data Science in Health
Knowledge
Data
Questions
Analytics
Estimation
Prediction
Uncertainty
Computation
Data bases
DATA
SCIENCE
![Page 10: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/10.jpg)
Data Science in Health
• Algorithms
• Models = digital twins
• Decision support
• What-if machines
• Process automation
• Robots
• …
DATA
SCIENCE
![Page 11: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/11.jpg)
Data Science in Health
• Prevent
• Diagnose
• Treat
• Prognose
• AftercareDATA
SCIENCE • Organise
• Lean
• Patient safety
![Page 12: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/12.jpg)
AI in Health
AI
EngineeringBioTec
![Page 13: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/13.jpg)
2. Methods
![Page 14: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/14.jpg)
Angela
Therapy works ?
?
Factors (genes, clinics,…)
![Page 15: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/15.jpg)
Angela
Therapy works ?
Y
y
y
N
y
We LEARN a RULE from complete data
which we apply to ANGELA
• Supervised: a Training data set with patients with known outcome.
![Page 16: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/16.jpg)
• Supervised: People with outcome known.
• Classification rule
Y
N
Angela
factor 2
factor 1
![Page 17: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/17.jpg)
Reg ression
Classification (x)x
• Regression! • Using all factors x. • Producing a level of uncertainty in the classification:
Angela: Therapy works with probability 73% Lukas: Therapy works with probability 53%
• Model based methods• Can be understood: how the classification depends on x. • Maybe some x can be intervened on, to improve the classification?
![Page 18: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/18.jpg)
Deep learning
Classification (x)x
• Deep learning! • Using all factors x. • Creates automatically many combinations of x, and among these
finds the ones that give best classification
x
Deep learning
Classification (x)
![Page 19: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/19.jpg)
CLA
SSIFICA
TION
![Page 20: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/20.jpg)
• Black box model• Cannot be understood: how the classification depends on x. • No intervention possible. • Producing no level of uncertainty in the classification
x
Deep learning
Classification (x)
![Page 21: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/21.jpg)
AI Classification (x)x
Select the factors that really matter!
Classification ( ) =
![Page 22: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/22.jpg)
y
y
Ny
No outcome known: useless to design the rule
Therapy works ?
![Page 23: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/23.jpg)
Use all data!
We can use all the patients, also the onesnot treated, to estimate the decision rule much better.
Angela
![Page 24: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/24.jpg)
Answers
Published online December 10, 2018
![Page 25: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/25.jpg)
• Deep learning can exploit subtle and complex associations that are
not visible otherwise (say a series of mutations appearing together)
• Image-rich specialities: Radiology, pathology, ophtalmology,
cardiolgy.
• For some diseases, it is not clear how the training data should be:
heart failure
• Uncertainty is necessary, no decision is 100% safe.
• Difficult to accept a classification which we cannot understand and
discuss. (lack of explainability: why will the therapy fail?)
• How to assess evidence of efficacy? RCT with AI arm vs non-AI
arm.
• Legal issues related to responsibility when failing.
![Page 26: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/26.jpg)
3. Data science for precision medicine
4. Data science for medical care
![Page 27: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/27.jpg)
Sept. 11, 2018
• Slow effects
• Not enough personalised
• Diseases are polygenic: difficult
to invent one drug that attacks,
repairs all
• Mostly genetic risk signatures
for prevention and prognoses.
• Very costly: towards a more
unequal health system.
![Page 28: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/28.jpg)
Vinay Prasad
• «Promises of personalised medicine have largely not materialised
• Impact of personalised medicine has been exaggerated
• No evidence (yet) that precision oncology is taking off.
• (as expected, breakthroughs are rare!)»
@VPplenarysesh
![Page 29: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/29.jpg)
• Estimate R&D cost to pring a drug to market:
800 million USD
• Industry’s own figure: 2600 million USD.
![Page 30: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/30.jpg)
![Page 31: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/31.jpg)
Personalised cancer therapy
![Page 32: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/32.jpg)
Breast cancer is many diseases.
![Page 33: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/33.jpg)
Oncologist
Radiologist
Molecular biologist
Biostatistician
Bioinformatician
Pathologist
![Page 34: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/34.jpg)
vs.CURRENT
BEST DRUG
Randomised clinical trial
• Significantly better
• BUT efficient only for 35% of patients
• Looking for a genomic biomarker of the cancer
![Page 35: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/35.jpg)
vs.CURRENT
BEST DRUG
Randomised clinical trial
RCT more and more difficult
1 to n
![Page 36: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/36.jpg)
Personalised cancer therapy
Assigning the best therapy to each patient
![Page 37: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/37.jpg)
There are maaaaaany options!
time
![Page 38: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/38.jpg)
There are maaaaaany options!
time
• drugs
• combinations
• doses
• order
• breaks
• ….. COMBINATORIAL many!
![Page 39: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/39.jpg)
Strategy 1 (despite all…) exploit similarities
![Page 40: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/40.jpg)
Strategy 1 (despite all…) exploit similarities
• Find who patient is a similar with, at least in part.
• Merge this information
• Which therapies worked?
![Page 41: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/41.jpg)
![Page 42: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/42.jpg)
• Systematic search in “all” data bases and literature
to find “everything” known about similar cases and
therapies.
• Text mining, cognitive natural language processing
![Page 43: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/43.jpg)
“ 230 healthcare organizations worldwide use
Watson technology “
![Page 44: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/44.jpg)
![Page 45: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/45.jpg)
![Page 46: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/46.jpg)
![Page 47: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/47.jpg)
Strategy 2 Copies of the patient
![Page 48: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/48.jpg)
Strategy 2 Copies of the patient
• In silico copies, quite similar to the patient.
• Simulate therapies.
• Which worked?
![Page 49: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/49.jpg)
Revision Cancer Research 2018
• Model based
• Personalised
• Based on computer simulation of therapy effect.
• UiO Life Science Convergence Environment PerCaThe
• Digital Life Norway NFR
![Page 50: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/50.jpg)
cancer
patient
personalised computer
simulationsstrategy 1
strategy 2
strategy 3
oncologistoptimal
treatment plan
personal
clinical
data
MRI histology molecular
multi-scale
mathematical
model
of cancer
growth
?
Personalised computer simulation
![Page 51: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/51.jpg)
![Page 52: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/52.jpg)
AVASTIN
FEC
Start 12 weeks3 6 9
FEC FEC FEC
AVASTIN AVASTIN AVASTIN?
![Page 53: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/53.jpg)
Start 12 weeks3 6 9
Start 12 weeks3 6 9
![Page 54: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/54.jpg)
![Page 55: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/55.jpg)
![Page 56: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/56.jpg)
![Page 57: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/57.jpg)
![Page 58: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/58.jpg)
![Page 59: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/59.jpg)
![Page 60: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/60.jpg)
![Page 61: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/61.jpg)
![Page 62: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/62.jpg)
Oxygen
diffusion supply
from vessels
consumption
by cells
![Page 63: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/63.jpg)
![Page 64: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/64.jpg)
![Page 65: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/65.jpg)
![Page 66: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/66.jpg)
![Page 67: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/67.jpg)
![Page 68: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/68.jpg)
![Page 69: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/69.jpg)
Patient 3 with two doses of Avastin: less is better
![Page 70: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/70.jpg)
![Page 71: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/71.jpg)
Sampling &
Heterogenity
• Heterogenity
• Genomics (genes)
• Drug mechanisms
Optimisation
Regulatory
approval
![Page 72: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/72.jpg)
2. Data science for medical care
![Page 73: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/73.jpg)
27 nov 2018
![Page 74: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/74.jpg)
Data: 189 clinical interviews with a robot (5-25 minutes)
170 possible questions
‘How are you?’
‘Do you consider yourself to be an introvert?’
dialogic feedback (‘I see’, ‘that sounds great’).
![Page 75: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/75.jpg)
Face
Sound
Text
Results: sensitivity 83.3%
specificity 82.6%
Deep learning
Detected depression using language, voice and facial
expressions.
![Page 76: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/76.jpg)
• Generate digital biomarkers from passively acquired
data from a smartphone
![Page 77: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/77.jpg)
![Page 78: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/78.jpg)
![Page 79: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/79.jpg)
with personalised
calibration, accuracy of
±0.92 g dL−1 wrt blood
count hemoglobin levels
4 December 2018
![Page 80: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/80.jpg)
![Page 81: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/81.jpg)
![Page 82: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/82.jpg)
![Page 83: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/83.jpg)
Babylon is based on a Probabilistic Graphical Model of
primary care medicine, which models the prior probabilities
of diseases and the conditional dependencies between
diseases, symptoms and risk factors via a directed acyclic
graph.
1980-1994-2018
![Page 84: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/84.jpg)
![Page 85: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/85.jpg)
Triage =henvisning
27 june 2018
![Page 86: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/86.jpg)
• The MRCGP final exam to become a GP
• Average pass mark for real-life doctors was 72%
• Babylon scored 81%.
• Accuracy of Babylon was 98% when assessed against
most frequent conditions in primary care.
• In comparison, experienced clinicians: 52%-99%.
• “We're pioneering AI to make healthcare
universally accessible and affordable”
![Page 87: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/87.jpg)
.
![Page 88: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/88.jpg)
Data Science in Health
• All this comes, not tomorrow, but soon
• We have time to build competence
(but better start)
o legeutdanning
o reskilling
• Cross-disciplinarity essential, and
research must reshape
• Enormous advantages
• Understand the purpose
• Responsible use of AI.
Prevent catastrophes.
![Page 89: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/89.jpg)
Data Science in Health
• Medfak: prepare
• Next step for legeutdanning?
• Continuum education of doctors and
researchers?
• Are current «research groups» useful?
Faculties?
• Data Science at UiO
• Data Science centre at LV byggning.
![Page 90: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/90.jpg)
Data Science in Health
• Medfak: OCBE!
![Page 91: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/91.jpg)
• Very costly
• More unequal health system.
• Genetically modified human embryo to prevent cancer in
children from parents with a risky mutation.
• Designer baby
• There is a distinction between preventing disease and
picking traits. (or maybe not?)
• Expensive.
• We risk creating a world, where some people bear more
genetic disease, because of their social, economical,
geographic status.
![Page 92: Data science og big data kan bidra til bedre helse · Data Science in Health •All this comes, not tomorrow, but soon •We have time to build competence (but better start) olegeutdanning](https://reader035.vdocuments.site/reader035/viewer/2022070112/60542dd39abcca66856fb28f/html5/thumbnails/92.jpg)