AMH is Higher Across the Menstrual Cycle in Early Postmenarchal Girls than in Ovulatory Women

Abstract

Context: Adolescents have more small, growing follicles and larger ovaries than normal women and are prone to anovulatory cycles (ANOV). It is unknown if a higher antral follicle count (AFC) per se contributes to ANOV in early postmenarchal girls.

Objective: To determine the relationship between AMH (an AFC biomarker), other reproductive hormones, and ANOV in postmenarchal girls and to compare AMH in girls and regularly cycling adults.

Methods: A total of 23 girls (1.7 ± 0.2 years postmenarche) and 32 historic adult controls (≤34 years) underwent serial hormone measurements during 1 to 2 menstrual cycles. Girls also had pelvic ultrasounds. AMH was measured 5 times/subject using the Ansh ultrasensitive ELISA.

Results: Girls had higher AMH than women (5.2 ± 0.3 vs. 3.3 ± 0.4 ng/mL; P < 0.01) and girls with more ovulatory (OV) cycles tended to have lower AMH than those with ANOV (2 OV 4.5 ± 0.2, 1 OV 5.7 ± 1.1, 0 OV 6.8 ± 1.1 ng/mL; P = 0.1). In girls, AMH correlated with natural-log (ln) transformed LH (r = 0.5, P = 0.01), ln_androstenedione (r = 0.6, P = 0.003), ln_testosterone (r = 0.5, P = 0.02), and ovarian volume (r = 0.7, P < 0.01) but not with FSH, estradiol, P4, or body mass index. In women, AMH correlated with estradiol and P4 (both r = -0.4, P ≤ 0.03) but not with ln_LH or body mass index.

Conclusions: In postmenarchal girls, AMH is higher than in ovulatory women and is associated with LH, androgens, and a propensity for anovulatory cycles. The cause of the transient increase in AMH and AFC during late puberty and the steps underlying the transition to a mature ovary deserve further study.

Trial registration: ClinicalTrials.gov NCT02486757.

Keywords: AMH; adolescent; menstrual cycle.

Figure 1.

Raw mean AMH levels with 95% CI in adolescent subjects (Adol) with either 0, 1, or 2 ovulatory cycles and in ovulatory adult women. AMH tended to decrease with increasing numbers of ovulatory cycles in adolescents. As a group, adolescents had higher AMH levels than adults. See also Table 3. 95% CI, 95% confidence interval.

Figure 2.

Serial AMH measurements in (A) adolescent subjects with 2 ovulatory cycles, with each cycle centered to the mid-cycle LH peak (day 0), and (B) adolescents with either 0, 1, or 2 ovulatory cycles presented by cycle day (where cycle day 1 represents the first day of menses). Adolescent data are presented over a backdrop of normative data from 32 historic adult controls during an ovulatory cycle. Adult data are shown as a solid black line (mean) ± 1 SD (shaded area). “1” in (B) indicates data points from the 1 adolescent outlier.

Figure 3.

Correlations between AMH and (A) LH (black circles and solid line), (B) average ovarian volume, (C) androstenedione, and (D) total testosterone in adolescents. AMH did not correlate with LH in adults (A; open circles and dashed line). Correlation coefficients and P values represent results of analyses performed after natural log(ln)-transformation of LH, androstenedione (AD), and total testosterone (TT) in adolescents and AMH and LH in adults. To convert AD and TT from ng/dL to nmol/L, multiply by 0.0349 and 0.0347, respectively.