SLIDE 1
Assessing Mental Health Issues
- n College Campuses: Preliminary
1 in 5 adults in the U.S. has mental illness in a year
2
Assessing Mental Health Issues on College Campuses: Preliminary - - PowerPoint PPT Presentation
Assessing Mental Health Issues on College Campuses: Preliminary - - PowerPoint PPT Presentation
Assessing Mental Health Issues on College Campuses: Preliminary Findings from a Pilot Study Vincent W. S. Tseng, Saeed Abdullah, Min Hane Aung, Franziska Wittleder, Michael Merrill, Tanzeem Choudhury 1 in 5 adults in the U.S. has mental
SLIDE 2
SLIDE 3
1 in 5 adults in the U.S. has mental illness in a year 1 in 4 college students in the U.S. has mental illness in a year
3
SLIDE 4
Based on 19,681 students over 40 schools,
- 80% felt overwhelmed by their responsibilities.
4
SLIDE 5
Based on 19,681 students over 40 schools,
- 80% felt overwhelmed by their responsibilities.
- 35% felt difficult to function due to depression.
5
SLIDE 6
Based on 19,681 students over 40 schools,
- 80% felt overwhelmed by their responsibilities.
- 35% felt difficult to function due to depression.
- 10% considered suicide at least once.
6
SLIDE 7
Based on 19,681 students over 40 schools,
- 80% felt overwhelmed by their responsibilities.
- 35% felt difficult to function due to depression.
- 10% considered suicide at least once.
However, 40% of them did not seek help.
7
SLIDE 8
% 10 20 30 40
Reasons
Stigma Busy Schedule Hours of Services Lack Information Long Wait Other
15 16 24 25 34 36
Barriers to Accessing Support
8
SLIDE 9
% 10 20 30 40
Days to wait
≥ 5 Days 2~4 Days 1~2 Days 1 Day
18 23 20 39
Appointment Wait Times
9
SLIDE 10
Ratio of student to psychological counselors is 1900 : 1
10
SLIDE 11
A new tool to monitor students’ behavior and assess their mental well-being continuously and unobtrusively is needed.
SLIDE 12
86% of US college student regularly use a smartphone.
SLIDE 13
- Conducted in an Ubicomp class in the Spring term (4
months) at Cornell University.
- Cornell health center was involved.
- 22 participants (12 females and 10 males) participated.
Pilot Study - Smartphone Based Mental Health Assessment Tool
13
SLIDE 14
- App was run on iOS and Android devices.
- Both self-assessment survey and passive sensing data were
collected.
Pilot Study - Smartphone Based Mental Health Assessment Tool
14
SLIDE 15
Sensor Data Survey Data
Sleep Survey Well-being Survey Photographic Affect Meter (PAM) Survey
10:30 AM 4:30 PM 10:30 AM Beginning,midterm, end of semester
15
SLIDE 16
Sensor Data Survey Data
Photographic Affect Meter (PAM) Survey
16
SLIDE 17
Survey Data
Call Activity Audio Location Charging
17
Sensor Data
SLIDE 18
Survey Data - Sleep Duration Over Weekdays and Weekends
18
SLIDE 19
Survey Data - Sleep Duration During Study and Exam Period
19
SLIDE 20
Survey Data - Average Stress Level Over the Semester
20
SLIDE 21
The low-dimension structures of students’ sensor data might be indicative of the underlying pattern of their daily behavior.
21
SLIDE 22
Robust PCA - Method for Recovering Corrupted Low-Rank Matrices
Given high-dimension data D, decompose D into A and E. where D = A + E.
Low-rank component Sparse component (gross errors)
Zhouchen Lin, Minming Chen, and Yi Ma. 2010. The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. arXiv preprint arXiv:1009.5055 (2010). 22
SLIDE 23
Robust PCA - Method for Recovering Corrupted Low-Rank Matrices
= +
Given high-dimension data D, decompose D into A and E. where D = A + E.
Low-rank component Sparse component (gross errors)
Zhouchen Lin, Minming Chen, and Yi Ma. 2010. The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. arXiv preprint arXiv:1009.5055 (2010).
D Observation A Low-rank E Sparse
23
SLIDE 24
Robust PCA - Finding Underlying Behavioral Pattern
= +
Given high-dimension data D, decompose D into A and E. where D = A + E.
Low-rank component Sparse component (gross errors)
D Raw Sensor Data A Underlying Pattern E Noise
24
SLIDE 25
Example - The Raw Sensor Data from One User
= +
#seconds user being active during an hour
25
Raw Activity Data
SLIDE 26
Example - The Low-rank Matrix from the User’s Sensor Data
= +
Low-rank matrix after decomposition
26
RPCA Raw Activity Data Underlying Activity Pattern
SLIDE 27
Example - The Low-rank Matrix from the User’s Sensor Data
= +
Sleep
27
SLIDE 28
Example - The Low-rank Matrix from the User’s Sensor Data
= +
Class Class
28
SLIDE 29
Example - The Low-rank matrix from the User’s Sensor Data
= +
February Break Spring Break
29
SLIDE 30
Next Step - Identifying the Change of Behavioral Pattern
Mental Well-Being GPA
30
Activity Audio Phone Use Underlying Behavioral Pattern
SLIDE 31
Future Work - Early Intervention
Help students manage their own mental welling and introduce timely mental health service from their caregivers.
31
SLIDE 32