Classifying subtypes of Polycystic Ovary Syndrome using machine learning

An Evidence-Based Novel Subtypes of Polycystic Ovary Syndrome and Their Association With Outcomes: a Large Cohort Study

This study is trying to see if using machine learning can help identify different types of Polycystic Ovary Syndrome (PCOS) in women to better understand their reproductive and metabolic health and how they respond to IVF treatments.

Quick facts

• Study type: Observational
• Enrollment: 50000 (estimated)
• Ages: 18 Years to 45 Years
• Sex: Female
• Sponsor: Shandong University (Academic / other)
• Locations: 11 sites (Hershey, Pennsylvania and 10 other locations)
• Trial ID: NCT06124391 on ClinicalTrials.gov

What this trial studies

This observational study aims to classify patients with Polycystic Ovary Syndrome (PCOS) into four distinct subtypes using a machine-learning model based on nine clinical characteristics. The study will compare the reproductive and metabolic features of these subtypes and assess the outcomes of in vitro fertilization (IVF) across them. Participants will undergo telephone interviews and physical examinations, including laboratory tests and ultrasound scans, over a prospective follow-up period of 6.5 years.

Who should consider this trial

Good fit: Ideal candidates for this study are women diagnosed with PCOS according to the Rotterdam criteria.

Not a fit: Patients with congenital adrenal hyperplasias, androgen-secreting tumors, or Cushing's syndrome may not benefit from this study.

Why it matters

Potential benefit: If successful, this study could lead to more personalized treatment approaches for PCOS, improving reproductive and metabolic outcomes for patients.

How similar studies have performed: Other studies have shown promise in using machine learning for classification in various medical conditions, suggesting potential success for this novel approach in PCOS.

Eligibility criteria

Inclusion Criteria:

* PCOS patients diagnosed using the Rotterdam criteria, which requires the presence of at least two of the following:

  1. Menstrual Irregularities: A menstrual cycle length of fewer than 21 days or more than 35 days, and/or fewer than eight cycles per year.
  2. Hyperandrogenism: Defined either by an elevated total testosterone level (as per local laboratory criteria) or by a modified Ferriman-Gallwey (mFG) score of 5 or higher.
  3. Polycystic Ovaries on Ultrasound: Presence of 12 or more follicles measuring 2-9 mm in diameter in each ovary and/or an ovarian volume exceeding 10 mL.

Exclusion Criteria:

Patients with congenital adrenal hyperplasias, androgen-secreting tumours, or Cushing's syndrome) will be excluded.

Where this trial is running

Hershey, Pennsylvania and 10 other locations

• Penn State College of Medicine — Hershey, Pennsylvania, United States (Recruiting)
• Hospital de Clinicas de Porto Alegre — Porto Alegre, Brazil (Recruiting)
• Chengdu Jinjiang Maternity and Child Health Hospital — Chengdu, China (Recruiting)
• Guangdong Second Provincial General Hospital — Guangzhou, China (Recruiting)
• Shandong University — Jinan, China (Recruiting)
• Ren Ji Hospital, School of Medicine, Shanghai Jiao Tong University — Shanghai, China (Recruiting)
• Tianjin Medical University General Hospital — Tianjin, China (Recruiting)
• General Hospital of Ningxia Medical University — Yinchuan, China (Recruiting)
• National University Hospital, National University of Singapore — Singapore, Singapore (Recruiting)
• Karolinska Institutet — Solna, Sweden (Recruiting)
• Hacettepe University School of Medicine Hacettepe — Ankara, Turkey (Recruiting)

Study contacts

• Study coordinator: Zi-jiang Chen

Conditions Polycystic Ovary Syndrome