JMIR Publications

ABSTRACT

Background:

Identifying subtle changes in the menstrual cycle is crucial for effective fertility tracking and understanding reproductive health.

Objective:

To explore the feasibility of using daily voice recordings to monitor fertility by analyzing fundamental frequency features throughout the menstrual cycle.

Methods:

This study analyzed voice recordings from 16 naturally cycling women, focusing on fundamental frequency features across their menstrual cycles. The analysis included comparisons of these features between the follicular and luteal phases and the application of changepoint detection algorithms to assess shifts in vocal pitch within the fertile window.

Results:

Two voice features were identified that correspond to the transition between the follicular and luteal phases. The fundamental frequency standard deviation was 9.0% lower in the luteal phase compared to the follicular phase (CI: 3.4 - 14.7%, p=0.002), and the 5th percentile of the fundamental frequency was 8.8% higher (CI: 1.7 - 16.0%, p=0.01). No significant differences were found between phases in mean fundamental frequency or the 95th percentile of the fundamental frequency. Additionally, changepoint detection revealed that for a significant majority of the participants (81%, P=0.03), there was a distinct change in the fundamental frequency standard deviation and 5th percentile occurring within the fertile window.

Conclusions:

These findings suggest that subtle variations in vocal pitch could serve as indicators of fertility status, providing a non-invasive and convenient method for monitoring reproductive health.