30) e-Health Interventions as a Treatment
Modality for Obese Adults:
A Systematic Review
Douglas Sutton, EdD, APRN, and Pamela Stetina, PhD, RN
Northern Arizona University
Background: Technology-based interventions also referred
to as electronic (e-Health) or mobile (m-Health) interventions,
are among the available treatment modalities for managing
weight loss in obese or overweight adults. Due to the
disproportionate incidence and prevalence of obesity, and the
continued weight gain among the general population, there is
a noted lack of sufficient evidence to support the effectiveness
of using e-Health interventions as a method for managing
clinical outcomes. The primary purpose of this systematic
review is to determine the effectiveness of technology-based
or e-Health interventions as a treatment modality for weight
loss and management among the overweight and obese adult
population. This systematic review evaluated the efficacy of
e-Health or technology-based interventions as a weight-loss,
or weight-maintenance treatment modality in adults who are
overweight or obese.
Methods: This review focused on the effectiveness of
Sponsor
e-Health interventions by comparing weight-loss findings
from previously published studies between 2007 to 2017. The
Preferred Reporting Items for Systematic Reviews and Meta-
Analyses (PRISMA) statement was used as a guide during this
review. The articles were retrieved from electronic databases,
using the search terms computer, e-, or m-Health, Internet,
Smart Phone Applications or Apps, technology-based, obesity,
overweight, and weight loss and weight maintenance. Boolean
operators “AND” and “OR” were used in the review. A total
of 2,909 articles were identified, and thirty articles met the
eligibility criteria for inclusion.
Results / Conclusions: These studies demonstrated that
e-Health, m-Health as well as internet technology-based
modalities are clinically meaningful for achieving varying
degrees of weight loss and weight maintenance in adults.
Further, published research findings comparing study
completion date to technology implementation date, reveal a
large time disparity in study results and journal dissemination
dates; which may imply best current practice to either the client
community or their clinicians.
31) Improvements in Clinic Flow Efficiency
and in Enabling Economic Screening for
Diabetic Retinopathy Through AI
Gilberto Zamora, PhD 1 , Jeremy Benson 1 , Sheila Nemeth 1 , John
Maynard 1 , Peter Soltz 1 , Javier Lozano 2
VisionQuest Biomedical LLC, 2 Clinicas del Azucar
1
Background: Countries throughout the world are experiencing
a shortage of trained specialists to address the growing need
for the care and treatment of individuals with diabetes. This
shortage is especially important to eyecare, where early
detection of diabetic retinopathy (DR) can prevent vision
loss. Through periodic screening, progression of advanced,
sight-threatening DR can be prevented or delayed. However,
because of the shortage of eyecare specialists, including the
USA, individuals with diabetes find the challenges of complying
with recommended eye screening overwhelming. In the USA,
less than 50% of individuals receive the recommended annual
retinal exam. This holds true for other countries like Mexico.
Methods: VisionQuest has developed an artificial intelligent
(AI) system, EyeStar, to automatically screen digital retinal
images for signs of DR. The AI method uses deep learning
techniques which have captured the attention of many
researchers in ophthalmology and other medical disciplines.
Deep learning relies on training of the algorithm on large
databases such as one used in this project. The AI screening
software was implemented at 12 diabetes care clinics in
Monterrey Mexico.
Results: EyeStar has been operational at these clinics since
2016, in which time 10,000 individuals have been screened. A
52 | Telemedicine Telehealth Service Provider Summit