Trial Outcomes & Findings for Social Media as a Risk Tool for HIV Prevention Needs (NCT NCT06566417)
NCT ID: NCT06566417
Last Updated: 2026-08-31
Results Overview
The investigators will compare the above-noted measure datasets with the Wand risk score as assessed in the study participants at the time of SMS/social media data collection. The Wand risk score is an empirically validated HIV prediction tool designed to estimate the probability of HIV acquisition in women. It calculates a total score (max 50 pts): age \<20 years (11 pts), 20-24 years (10 pts), 25-29 years (6 pts), 30+ years (0 pts); marital status of single/not cohabitating (13 pts), married/cohabitating (0 pts); # sexual partners in last 3 months of 3 or more (5 pts), \<3 (0 pts); age at sexual debut of \<16 years (3 pts), 16+ years (0 pts); parity (# of births) of 0-1 births (10 pts), 2 births (8 pts), 3+ births (0 pts); ever diagnosed with an STI as yes (4 pts), no (0 pts); and use of injectable contraception as yes (4 pts), no (0 pts). A higher score denotes a higher HIV risk. The total possible range is 0-50.
COMPLETED
400 participants
6 months of data given at one time
2026-08-31
Participant Flow
Note: Ineligible participants provided baseline demographic/behavioral information only under verbal consent (according to IRB approval).
Participant milestones
| Measure |
Young Women
young women (ages 18-24) in Kisumu, Kenya who used WhatsApp and were willing to share their messages, and who could understand Swahili, DhoLuo, and/or English (the most spoken languages in the region)
|
|---|---|
|
Overall Study
STARTED
|
400
|
|
Overall Study
COMPLETED
|
400
|
|
Overall Study
NOT COMPLETED
|
0
|
Reasons for withdrawal
Withdrawal data not reported
Baseline Characteristics
Social Media as a Risk Tool for HIV Prevention Needs
Baseline characteristics by cohort
| Measure |
Young Women
n=400 Participants
young women (ages 18-24) in Kisumu, Kenya who used WhatsApp and were willing to share their messages, and who could understand Swahili, DhoLuo, and/or English (the most spoken languages in the region
|
|---|---|
|
Age, Categorical
<=18 years
|
0 Participants
n=14 Participants
|
|
Age, Categorical
Between 18 and 65 years
|
400 Participants
n=14 Participants
|
|
Age, Categorical
>=65 years
|
0 Participants
n=14 Participants
|
|
Age, Continuous
|
22.0 years
STANDARD_DEVIATION 1.6 • n=14 Participants
|
|
Sex: Female, Male
Female
|
400 Participants
n=14 Participants
|
|
Sex: Female, Male
Male
|
0 Participants
n=14 Participants
|
|
Race (NIH/OMB)
American Indian or Alaska Native
|
0 Participants
n=14 Participants
|
|
Race (NIH/OMB)
Asian
|
0 Participants
n=14 Participants
|
|
Race (NIH/OMB)
Native Hawaiian or Other Pacific Islander
|
0 Participants
n=14 Participants
|
|
Race (NIH/OMB)
Black or African American
|
400 Participants
n=14 Participants
|
|
Race (NIH/OMB)
White
|
0 Participants
n=14 Participants
|
|
Race (NIH/OMB)
More than one race
|
0 Participants
n=14 Participants
|
|
Race (NIH/OMB)
Unknown or Not Reported
|
0 Participants
n=14 Participants
|
|
Region of Enrollment
Kenya
|
400 Participants
n=14 Participants
|
PRIMARY outcome
Timeframe: 6 months of data given at one timeThe investigators will compare the above-noted measure datasets with the Wand risk score as assessed in the study participants at the time of SMS/social media data collection. The Wand risk score is an empirically validated HIV prediction tool designed to estimate the probability of HIV acquisition in women. It calculates a total score (max 50 pts): age \<20 years (11 pts), 20-24 years (10 pts), 25-29 years (6 pts), 30+ years (0 pts); marital status of single/not cohabitating (13 pts), married/cohabitating (0 pts); # sexual partners in last 3 months of 3 or more (5 pts), \<3 (0 pts); age at sexual debut of \<16 years (3 pts), 16+ years (0 pts); parity (# of births) of 0-1 births (10 pts), 2 births (8 pts), 3+ births (0 pts); ever diagnosed with an STI as yes (4 pts), no (0 pts); and use of injectable contraception as yes (4 pts), no (0 pts). A higher score denotes a higher HIV risk. The total possible range is 0-50.
Outcome measures
| Measure |
Young Women
n=400 Participants
Young women (ages 18-24) in Kisumu, Kenya who use WhatsApp
|
|---|---|
|
Association of Artificial Intelligence Measure Datasets With the Wand Risk Score
|
32.8 Wand risk score
Standard Deviation 6.4
|
PRIMARY outcome
Timeframe: 6 monthsAnalysts will examine 6 months of SMS/social media message content from each of the 400 study participants using three computational linguistic methods: 1) sentiment, valence, and arousal analysis; 2) topic modeling; 3) simple textual counts. Analysts will also perform network analysis with up to 20 contacts from each participant to understand how often and with which parties the participant communicates most frequently. These networks will be examined temporally to see if any of the connections have grown or weakened over time. The VOICE risk score (modified to not use biological markers) is a measure of behavioral and demographic factors to determine HIV risk: \<25 y/o (2 pts), unmarried or not living with a partner (2 pts), primary partner has other partners (2 pts), partner does not provide financial support (1 pt), alcohol use in the last 3 months (1 pt). A higher score denotes a greater HIV risk. The total possible range is 0-8.
Outcome measures
| Measure |
Young Women
n=400 Participants
Young women (ages 18-24) in Kisumu, Kenya who use WhatsApp
|
|---|---|
|
Association of Artificial Intelligence Measure Datasets With the VOICE Risk Score
|
5.7 VOICE risk score
Standard Deviation 1.4
|
Adverse Events
Young Women
Serious adverse events
Adverse event data not reported
Other adverse events
Adverse event data not reported
Additional Information
Results disclosure agreements
- Principal investigator is a sponsor employee
- Publication restrictions are in place