Loading presentation...

Present Remotely

Send the link below via email or IM


Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.


Surgery Grand Rounds 10-5-16


Heather Evans

on 15 October 2016

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Surgery Grand Rounds 10-5-16

Post-op PGHD
After discharge, patients are primarily responsible for their post-surgical care
Patients cannot discern when their surgical wound is infected
Using PGHD in post-discharge post-operative care is hard
SSI detection, prediction, risk assessment with photos
Used machine learning to develop prediction model of SSI with serial wound observations and vital signs
sanger et al, JACS 2016
Examined SSI diagnostic accuracy of infection experts: wound photos improved accuracy and increased confidence
sanger et al, JACS (in press)
Thank you
Easily Resize
PSIP: Initial mPOWEr pilot implementation
Patient provider
PGHD for SSI Surveillance
Heather Evans, MD, MS
Associate Professor of Surgery
UW Department of Surgery
Research Grand Rounds 10-5-2016
how do we get there with PGHD?
patient generated health data
Patients, not providers, are primarily responsible for capturing or recording these data.
Patients decide how to share or distribute these data to health care providers and others.
health history
treatment history
biometric data
lifestyle choices
from the Office of the National Coordinator (ONC)
Wound photography is acceptable for wound monitoring
In 2014, 68% of Americans owned a smartphone
Patients are open to using mobile devices for SSI surveillance
Feasibility of a PGHD platform
for monitoring
for prediction
for surveillance
Data Visualizations
Patient-Centered Post-Operative Care
whitby et al 2002
wiseman et al 2016
pew research center 2015
sanger et al 2014
UW Center for Reconstructive Surgery
57 patients, 175 assessments
4 patients recorded >15 assessments
2 surgical site infections documented

CMMI PTN pilot project
refined mPOWEr implementation plan for additional UW Medicine clinics
with QI/Finance Data Analysts, developed metrics to track utilization, cost
clinic and ED visits, readmissions
found and matched mPOWEr users with historical controls by DRG
aligning reporting with existing care pathways in high risk patients
Coulter Foundation Award
Commercialization pilot, first use outside UW Medicine
Rural private practice surgeon-driven implementation
MD in-hospital use, transition to PGHD at discharge
CDC IDIQ Award: Health Information Technology domain
Research Program Summit
Validation of insitutional, state SSI rates
Explore increasing automation in SSI risk assessment with PGHD
Bill Lober, MD, MS
Joie Whitney, RN, PhD
Andrea Hartzler, PhD
Patrick Sanger, MD, PhD
Ross Lordon, MS
Cameron Gaskill, MD
Kristin Helps, RN, MS
Brian Do
Julie Cooper, MPA - SORCE
Gail Dykstra - CoMotion

UW Center for Reconstructive Surgery
NWH Hernia Center & General Surgery Clinic
SCCA Breast Care Clinic
Paul Szotek, MD
Putnam County Hospital

Ross Lordon, Biomedical Health Informatics PhD student
R36 Dissertation Grant submission, fall 2016
Evaluating the Discordance of Patient-Provider Communication Patterns when Utilizing Patient Generated Health Data in a Provider Oriented Healthcare System
In post-implementation interviews
several clinic providers felt unprepared, untrained, frustrated
wanted better ease of use, integration with EMR
Only 4 patient surveys returned, 3/4 were satisfied with platform
Go live:
SCCA Breast Care clinic, NWH Hernia Center & GS clinic, HMC & UWMC ED wound care
Lessons learned
work process mapping, meetings prior to implementation did not adequately prepare team or clinic
engagement level modified by patient preference
prescribe? lack of use may be appropriate for most
caregivers have smartphones too, can be partners
the clinic wasn't built with apps in mind
need to plan how remote engagement happens
multiple engagement pathways need linkage
PGHD datastreams don't fit existing workflow
need local technology champions/partners
Tested crowdsourcing performance in SSI diagnosis using Amazon mTurk
Overall accuracy :
Higher confidence when SSI diagnosis made in absence of SSI
Applying use of mPOWEr to remotely adjudicate SSI, the primary outcome in the CleanCut study in Ethiopia
Building an annotated wound photo library with local startup using a curated crowd
Aim to develop both human and image feature training tools for SSI detection
Collaboration with Stanford global surgery to conduct clinical research in resource poor environments
Year 2
Year 1
HMC inpatient wound care, collaboration with INFORM for SNF wound monitoring
Exploring additional UW Medicine clinics
Refining reporting to include infection metrics
Use in first 3 weeks:
6 patients, average 11 sessions each
abdominal wall reconstruction
necrotizing soft tissue infection
infected hernia mesh excision
Next steps:
Developing use cases, new image annotation features; exploring use with other surgeons in the International Hernia Collaborative
POD 15
Direct patient engagement increased usage
our attempt to minimize disruption to workflow resulted in our failure to train providers
eCare patient portal registration took priority for patient engagement
identified need for more formal implementation planning, partnership with clinic champions
Patient-centered care in a Provider-centered world.
sanger et al 2015
Full transcript