Using social networking and ar1ficial intelligence to collect FHx
Brandon M Welch, MS, PhD Assistant Professor Medical University of South CarolinaUsing social networking and ar1ficial intelligence to collect FHx - - PowerPoint PPT Presentation
Using social networking and ar1ficial intelligence to collect FHx - - PowerPoint PPT Presentation
Using social networking and ar1ficial intelligence to collect FHx Brandon M Welch, MS, PhD Assistant Professor Medical University of South Carolina Family history is important Cancer runs in families Life6me risk for breast cancer 70% 60%
Family history is important
Cancer runs in families
Life6me risk for breast cancer
0% 10% 20% 30% 40% 50% 60% 70% Average risk Smoker Drinker 1 FDR 2 FDR BRCA2 3 FDR BRCA1 Average risk Smoker Drinker 1 FDR 2 FDR BRCA2 3 FDR BRCA1Most people have cancer in the family
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% Smokes Close family (parent, sibling) Extended family (+ grandparents, aunts/uncles)% of US populaPon
Smokes Breast cancer Colon cancer Prostate cancer Lung cancerIt’s in the family, but where’s the gene?
VUS = fly in gene6c tes6ng ointment
VUSs are growing
Use family history to make sense of VUSs
Collec6on of FHx
<4%
Time needed 20-30 minutes Time spent 2.5 minutes
30-90%
accurate
100% 0% Breast cancer Mental healthClinicians don’t have 1me to collect a bad FHx
“painful to use”
- Poor user interface design
- Complicated and illogical quesPons
- System crashes
- High user workload
1 in 10
complete FHx
3 of 4
never finished
Reimagine FHx collec6on
Leverage the family social network Interoperable with EHRs Provide care recommendations Support clinical research
Chatbots
How lik likely ely would you use ItRuns?
PMID: 26958272- MVP complete
- Open beta
- Pilot studies
- HL7 interoperability
Phase 1 Phase 2
FHx risk assessment
Family cancer risk assessment is a me mess
Risk for breast cancer Risk for colon cancer Risk for Lynch syndrome Risk for BRCA gene Risk for- varian cancer
Couch Gail Claus Penn II Myriad Tyrer-Cuzick BRCAPRO BOADICEA BRST Wijnen MMRpro MMRPredict PREMM1,2,6
Risk for skin cancerMELApro Pancpro
Risk for prostate cancer Cancer Guidelines 531 statements 55 guidelines published 11 different organizaPons- varian cancer
Unified Hereditary Cancer Assessment Tool (U-CHAT)
Unify the risk tools
Unified Hereditary Cancer Assessment Tool (U-CHAT)
Under developmentOpportuni6es
Cancer risk
Personalize care
Genome discovery
Research recruitment
Data collecPon and storage
as a pladorm
ApplicaPon & funcPonality
Open collabora6on plaTorm