Performance evaluation of human cough annotators: optimal metrics and sex differences.

INTRODUCTION: Despite its high prevalence and significance, there is still no widely available method to quantify cough. In order to demonstrate agreement with the current gold standard of human annotation, emerging automated techniques require a robust, reproducible approach to annotation. We describe the extent to which a human annotator of cough sounds (a) agrees with herself (intralabeller or intrarater agreement) and (b) agrees with other independent labellers (interlabeller or inter-rater agreement); we go on to describe significant sex differences in cough sound length and epochs size. MATERIALS AND METHODS: 24 participants wore an audiorecording smartwatch to capture 6-24 hours of continuous audio. A randomly selected sample of the whole audio was labelled twice by an expert annotator and a third time by six trained annotators. We collected 400 hours of audio and analysed 40 hours. The cough counts as well as cough seconds (any 1 s of time containing at least one cough) from different annotators were compared and summary statistics from linear and Bland-Altman analyses were used to quantify intraobserver and interobserver agreement. RESULTS: There was excellent intralabeller (less than two disagreements per hour monitored, Pearson's correlation 0.98) and interlabeller agreement (Pearson's correlation 0.96), using cough seconds as the unit of analysis decreased annotator discrepancies by 50% in comparison to coughs. Within this data set, it was observed that the length of cough sounds and epoch size (number of coughs per bout or attach) differed between women and men. CONCLUSION: Given the decreased interobserver variability in annotation when using cough seconds (vs just coughs) we propose their use for manually annotating cough when assessing of the performance of automatic cough monitoring systems. The differences in cough sound length and epochs size may have important implications for equality in the development of cough monitoring tools. TRIAL REGISTRATION NUMBER: NCT05042063.

Intensive Group Learning and On-Site Services to Improve Sexual and Reproductive Health Among Young Adults in Liberia: A Randomized Evaluation of HealthyActions.

INTRODUCTION: Young Liberians, particularly undereducated young adults, face substantial sexual and reproductive health (SRH) challenges, with low uptake of contraceptive methods, high rates of unintended pregnancy, and low levels of knowledge about HIV status. The purpose of this study was to assess the impact of a 6-day intensive group learning intervention combined with on-site SRH services (called HealthyActions) among out-of-school young adults, implemented through an existing alternative education program, on uptake of contraception and HIV testing and counseling (HTC). METHODS: The intervention was implemented among young women and men ages 15-35 who were enrolled in alternative basic education learning sites in 5 counties of Liberia. We conducted a randomized evaluation to assess program impact. Baseline data were collected in January-March 2014, and endline data in June-July 2014. Key outcomes of condom use, contraceptive use, and HTC were estimated with difference-in-difference models using fixed effects. All analyses were conducted in Stata 13. RESULTS: We assessed outcomes for 1,157 learners at baseline and 1,052 learners at endline, across 29 treatment and 26 control sites. After adjusting for potential confounders, learners in the HealthyActions intervention group were 12% less likely to report never using a condom with a regular partner over the last month compared with the control group (P = .02). Female learners who received HealthyActions were 13% more likely to use any form of modern contraception compared with learners in control sites (P<.001), with the greatest increase in the use of contraceptive implants. Learners in HealthyActions sites were 45% more likely to have received HTC (P<.001). CONCLUSION: Providing intensive group learning in a supportive environment coupled with on-site health services improved SRH outcomes among participating learners. The focus of HealthyActions on participatory learning for low-literacy populations presents an adaptable solution for health programming across Liberia and the region.