Skip to content

Combined Use of Machine Learning and Metabolomics to Improve the Diagnosis and Management of Hyperandrogenism

Combined Use of Machine Learning and Metabolomics to Improve the Diagnosis and Management of Hyperandrogenism

Status
Not yet recruiting
Phases
Unknown
Study type
Observational
Source
ClinicalTrials.gov
Registry ID
NCT07253454
Acronym
HYPERMETABO
Enrollment
800
Registered
2025-11-28
Start date
2026-01-31
Completion date
2040-12-31
Last updated
2025-12-04

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Hyperandrogenism

Keywords

fertility

Brief summary

Hyperandrogenism is a common reason for consultation, the causes of which can range from common conditions (PCOS) to rarer conditions with major genetic implications (NC21OHD). It is characterized by elevated levels of circulating androgens, mainly testosterone. This excess of androgens usually manifests clinically as increased male-pattern hair growth and, less specifically, acne and alopecia. Its prevalence is estimated at between 6 and 12% in women of reproductive age, and its incidence is increasing. It is also responsible for infertility. As a reminder, infertility is a major public health issue and affects more and more couples around the world. The investigators therefore wish to develop innovative tools to improve the diagnosis and management of hyperandrogenism

Detailed description

Hyperandrogenism is a common reason for consultation, the causes of which can range from common conditions (PCOS) to rarer conditions with major genetic implications (NC21OHD). It is characterized by elevated levels of circulating androgens, mainly testosterone. This excess of androgens usually manifests clinically as increased male-pattern hair growth and, less specifically, acne and alopecia. Its prevalence is estimated at between 6 and 12% in women of reproductive age, and its incidence is increasing. It is also responsible for infertility. As a reminder, infertility is a major public health issue and affects more and more couples around the world. The investigators therefore wish to develop innovative tools to improve the diagnosis and management of hyperandrogenism

Interventions

OTHERdata collection

collection of data from medical records over a period of 5 years

Sponsors

Assistance Publique - Hôpitaux de Paris
Lead SponsorOTHER

Study design

Observational model
COHORT
Time perspective
CROSS_SECTIONAL

Eligibility

Sex/Gender
FEMALE
Age
16 Years to 45 Years
Healthy volunteers
No

Inclusion criteria

* Patients of childbearing age (16 to 45 years old) * Suffering from hyperandrogenism * Established etiological diagnosis with elimination of differential diagnoses * Informed and not opposed to the collection of their data for the purposes of the study

Exclusion criteria

* Pregnancy * Patients under legal protection measures

Design outcomes

Primary

MeasureTime frame
Use of machine learning models combined with metabolomics to distinguish between different causes of hyperandrogenism5 years

Secondary

MeasureTime frame
Use of metabolomics to improve the management of patients with hyperandrogenism5 years
Use of metabolomics to predict CYP21A2 genotyping results5 years
Study of the impact of anti-androgenic hormone therapy on the predictive capabilities of the model5 years

Contacts

Primary ContactAnne Pr BACHELOT
anne.bachelot@aphp.fr0033 01 42 16 02 46

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026