HaloLocus turns the data your wearable already collects into a personal physiological baseline — built for women navigating PCOS, endometriosis, and perimenopause, whose symptoms are too often measured against the wrong reference point.
Most health apps compare you to a population average. We think your own pattern, tracked over time, is the more useful reference point — and we build the model to know the difference.
We connect to a wearable you already own and learn what's typical for you specifically — not a threshold set for the average user.
When your pattern shifts, you see it early — framed as information to bring to a conversation with a doctor, not a diagnosis.
Our models are grounded in large-scale, published cardiovascular and hormonal-health research — not just self-reported symptoms.
The most common hormonal condition in women of reproductive age, and one of the most delayed to diagnose.
Chronic, systemic, and still routinely dismissed as "normal" period pain in its earliest years.
Symptoms often begin over a decade before diagnosis, and are frequently mistaken for something else entirely.
HaloLocus is built to help you notice meaningful change earlier and bring real information into a medical conversation — not to replace one. We don't diagnose, and we don't promise to prevent disease.
PhD candidate in computational biology and human genetics, LMU Klinikum München and the Graduate School of Systemic Neurosciences. Researches personalized health baselines within a lab focused on stroke and dementia epidemiology.
PhD candidate in multimodal machine learning for medical data, DeepVasc Lab, Institute for Stroke and Dementia Research, LMU. Author of a wearable-derived arterial aging biomarker study using UK Biobank data.
We're building in public, grounded in published research at every step. Join the list to hear from us as the first version becomes available.
No spam. We'll only email you about HaloLocus.