Using Hormone Data and Age to Pinpoint Cycle Day within the Menstrual Cycle

Area of Science:

• Reproductive Endocrinology
• Biotechnology
• Data Science in Healthcare

Background:

• Menstrual cycle tracking is crucial for reproductive health but often relies on inaccurate 28-day cycle estimations.
• Variability in cycle and phase lengths makes traditional tracking methods imprecise.

Purpose of the Study:

• To evaluate menstrual cycle hormone levels using daily monitoring to identify follicular and luteal phase nuances across different age groups.
• To establish a precise method for determining an individual's current position within their menstrual cycle.

Main Methods:

• Utilized a remote fertility testing system with AI-powered app to track luteinizing hormone (LH) and pregnanediol-3-glucuronide (PdG) daily.
• Analyzed data from 1233 users, encompassing 4123 menstrual cycles.
• Monitored daily LH and PdG levels across multiple cycles.

Main Results:

• Calculated cycle lengths were generally shorter than user-reported lengths.
• Follicular phase length decreased with age, while luteal phase length increased.
• Age, first cycle day, and current hormone levels predicted cycle phase and day with 95% confidence.

Conclusions:

• At-home hormone monitoring offers superior cycle tracking precision compared to traditional estimations.
• Findings support improved fertility planning, clinical management, and general health monitoring.
• Established a novel standard for pinpointing cycle phase using LH and PdG levels, addressing a gap in reproductive healthcare.