CHARM: cycle-phase supervision for a wearable foundation model of women's health (Terra API; Research Square 2026)

Inputs (Table 5): one value per night for skin-temperature delta, mean sleep HR, sleep respiratory rate, overnight HRV and lowest sleep HR; four channels are per-user 30-day rolling z-scores; each paired with an observation mask → 10 input channels; 90-day window. Architecture: 1×1 conv to 128 channels, 4 residual dilated causal blocks (dilations 1/2/4/8, receptive field 61 days), 128-d embedding per day. Objective: masked-channel reconstruction (one whole channel hidden with p=0.3; reconstruction weight 0.5) + phase BCE (luteal vs follicular).

• Form factor: ring

The menstrual cycle can be tracked through physiological signals captured by consumer wearables overnight — skin temperature, breathing rate, heart rate and heart rate variability — which act as proxies for the underlying hormonal variations. Other reproductive states, such as pregnancy or menopause, are often studied in isolation rather than as perturbations of the normal menstrual hormone rhythm, even though they are all governed by the same endocrine system. Here, we present CHARM (Cyclic Hormone-Aware Representation of the Menstrual cycle), a framework that learns menstrual cycle representations from wearable data by combining two training objectives: reconstruction of masked sensor channels, and a menstrual cycle phase (luteal or follicular) supervised loss. Phase supervision improves recovery of the underlying hormone dynamics from the learned representation. Without further training, frozen CHARM embeddings also generalise to multiple reproductive states and symptoms not seen during model training. The phase objective substantially improves this generalisation and is highly label-efficient, matching a strong baseline while using around 5-fold fewer labels for perimenopause and outperforming the baseline on menopause across all data regimes.

Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by/4.0/

No row is credited to the paper itself; 1 more belong to models it introduces or evaluates. Ranks apply within each leaderboard only, as reported by the source.

• mcPHASES: A Dataset of Physiological, Hormonal, and Self-reported Events and Symptoms for Menstrual Health Tracking with WearablesEvaluationSpO₂ · Resp · Temp

• CHARMcnncycle-phase-supervised wearable foundation model for women's health (Terra)Foundation modelRespTempHR2026