ArticlePDF Available

Abstract

OBJECTIVES/SPECIFIC AIMS: Sexual violence (SV) is a public health crisis. High rates of SV are observed among college-age youth, yet holistic interventions are currently lacking. The purpose of this study was to conduct a pilot feasibility and acceptability test of a WebApp, MKit, which translates a clinical life skills approach to influence the health and well-being of university students. METHODS/STUDY POPULATION: We randomized two residence halls at a public university in the Midwest into a control group (n=139) that received typical university programming around SV and healthy relationships, or an intervention group (n=122) receiving MKit and the usual SV programming. We used online surveys to assess acceptability, feasibility, and usability at 3- and 5-months. Focus groups were conducted with a subsample of participants at 5-months to further investigate safety. RESULTS/ANTICIPATED RESULTS: The mean number of uses of MKit was 2.84 in a 5-month period. The majority of intervention participants endorsed the acceptability and usability of MKit as easy to use, well integrated, accessible, and easy to learn quickly. There were no concerns regarding personal safety. DISCUSSION/SIGNIFICANCE OF IMPACT: MKit provides a promising resource platform to deliver messages regarding healthy relationships and SV within the university context. By delivering SV-related content through a holistic life skills approach, MKit may offer new opportunities to reach and engage a wide range of students on how to foster healthy relationships.
Operation not neededis defined as patients who were safely dis-
charged without an operation or patients who had an operation,
but nothing was found. The distribution of data samples for predic-
tion task 2 is 37 operation not needed cases and 38 operation of ben-
efit cases. An experienced surgical resident from UPMC manually
segmented 3D PI ROIs from the CT scans (5 mm Axial cut) for each
case. The most concerning ~10-15 cm segment of bowel for necrosis
with a 1 cm margin was selected. A total of 7 slices per patient were
segmented for consistency. For both prediction task 1 and prediction
task 2, we independently completed the following procedure for
testing and training: 1.) Extracted radiomic features from the 3D
PI ROIs that resulted in 99 total features. 2.) Used LASSO feature
selection to determine the subset of the original 99 features that
are most significant for performance of the prediction task. 3.)
Used leave-one-out cross-validation for testing and training to
account for the small dataset size in our preliminary analysis. Imple-
mented and trained several machine learning models (AdaBoost,
SVM, and Naive Bayes). 4.) Evaluated the trained models in terms
of AUC and Accuracy and determined the ideal model structure
based on these performance metrics. RESULTS/ANTICIPATED
RESULTS: Prediction Task 1: The top-performing model for this
task was an SVM model trained using 19 features. This model
had an AUC of 0.79 and an accuracy of 75%. Prediction Task 2:
The top-performing model for this task was an SVM model trained
using 28 features. This model had an AUC of 0.74 and an accuracy of
64%. DISCUSSION/SIGNIFICANCE OF IMPACT: To the best of
our knowledge, this is the first study to use radiomic-based machine
learning models for the prediction of tissue ischemia, specifically
intestinal ischemia in the setting of PI. In this preliminary study,
which serves as a proof of concept, the performance of our models
has demonstrated the potential of machine learning based only on
radiomic imaging features to have discriminative power for surgical
decision-making problems. While many non-imaging-related clini-
cal factors play a role in the gestalt of clinical decision making when
PI presents, we have presented radiomic-based models that may aug-
ment this decision-making process, especially for more difficult cases
when clinical features indicating acute abdomen are absent. It should
be noted that prediction task 2, whether or not a patient presenting
with PI would benefit from an operation, has lower performance
than prediction task 1 and is also a more challenging task for physi-
cians in real clinical environments. While our results are promising
and demonstrate potential, we are currently working to increase our
dataset to 300 patients to further train and assess our models.
References DuBose, Joseph J., et al. Pneumatosis Intestinalis Pre-
dictive Evaluation Study (PIPES): a multicenter epidemiologic study
of the Eastern Association for the Surgery of Trauma.Journal of
Trauma and Acute Care Surgery 75.1 (2013): 15-23. Knechtle,
Stuart J., Andrew M. Davidoff, and Reed P. Rice. Pneumatosis intes-
tinalis. Surgical management and clinical outcome.Annals of
Surgery 212.2 (1990): 160.
3032
MKit: Pilot Results of Primary Prevention Sexual
Violence WebApp
Michelle Munro-Kramer1, Lindsay Cannon1, Jose Bauermeister2,
Yasamin Kusunoki1, Quyen Ngo1and Rob Stephenson1
1University of Michigan and 2University of Pennsylvania
OBJECTIVES/SPECIFIC AIMS: Sexual violence (SV) is a public
health crisis. High rates of SV are observed among college-age youth,
yet holistic interventions are currently lacking. The purpose of
this study was to conduct a pilot feasibility and acceptability test
of a WebApp, MKit, which translates a clinical life skills approach
to influence the health and well-being of university students.
METHODS/STUDY POPULATION: We randomized two residence
halls at a public university in the Midwest into a control group
(n=139) that received typical university programming around SV
and healthy relationships, or an intervention group (n=122) receiv-
ing MKit and the usual SV programming. We used online surveys
to assess acceptability, feasibility, and usability at 3- and 5-months.
Focus groups were conducted with a subsample of participants at
5-months to further investigate safety. RESULTS/ANTICIPATED
RESULTS: The mean number of uses of MKit was 2.84 in a 5-month
period. The majority of intervention participants endorsed the
acceptability and usability of MKit as easy to use, well integrated,
accessible, and easy to learn quickly. There were no concerns regard-
ing personal safety. DISCUSSION/SIGNIFICANCE OF IMPACT:
MKit provides a promising resource platform to deliver messages
regarding healthy relationships and SV within the university con-
text. By delivering SV-related content through a holistic life skills
approach, MKit may offer new opportunities to reach and engage
a wide range of students on how to foster healthy relationships.
3086
Virtual World-based Cardiac Rehabilitation to Promote
Healthy Lifestyle Among Cardiac Patients
LaPrincess Brewer1, Brian Kaihoi, Shawn Leth, Ray Squires,
Randal Thomas, Robert Scales, Jorge Trejo-Gutierrez and
Stephen Kopecky
1Mayo Clinic
OBJECTIVES/SPECIFIC AIMS: Our aim was to assess the feasibility
and acceptability of a VW-based cardiac rehabilitation (CR) pro-
gram (Destination Rehab) as an extension of a face-to-face conven-
tional CR program. We hypothesized that a VW-based CR program
could be successfully implemented as an extension of conventional
CR and would have high acceptability among cardiac patients.
METHODS/STUDY POPULATION: We recruited 30 adult cardiac
patients (10/site) hospitalized at Mayo Clinic Hospitals in Rochester,
MN, Jacksonville, FL or Scottsdale, AZ with a diagnosis for CR (eg,
acute coronary syndrome (ACS), heart failure, elective percutaneous
coronary intervention (PCI)). Other inclusion criteria included
at least 1 modifiable, lifestyle risk factor target: sedentary lifestyle
(<3 hours physical activity (PA)/week), unhealthy diet (<5 servings
fruits and vegetables/day) or current smoking (>1 year). Patients
participated in an 8-week, health education program using a VW
platform from a prior proof-of-concept study and provided interven-
tion usability, usefulness and satisfaction feedback. We assessed
cardiovascular (CV) health behaviors (diet, PA) and risk factors
(eg, blood pressure (BP), lipids) at baseline and immediate post-
intervention. RESULTS/ANTICIPATED RESULTS: Among 30
patients enrolled (mean age; 59 years; 50% women; 65% <college
graduate; 32% annual household income <$50,000), 28 (98%) com-
pleted the study. The majority (64%) were enrolled in conventional
CR with a high session completion rate (median 36 sessions, inter-
quartile range 8-36). The most common CR indication was PCI
(68%). There were statistically significant improvements in PA from
baseline to post-intervention: vigorous PA, þ10.7 (SD 11.7) minutes/
day (p =0.05) and flexibility exercises þ0.9 (SD 0.9) days/week for
men (p=0.05). There were favorable trends in risk factors: systolic BP
JCTS 2019 Abstract Supplement 61
https://www.cambridge.org/core/terms. https://doi.org/10.1017/cts.2019.143
Downloaded from https://www.cambridge.org/core. IP address: 178.171.28.17, on 27 Mar 2019 at 12:58:32, subject to the Cambridge Core terms of use, available at
ResearchGate has not been able to resolve any citations for this publication.
ResearchGate has not been able to resolve any references for this publication.