{
  "abstract": "Polycystic ovary syndrome (PCOS) is among the most prevalent endocrine disorders affecting 12.1% of reproductive-aged women, yet it remains one of the least precisely defined.1 Despite its high global prevalence, PCOS continues to be diagnosed and managed through broad syndromic criteria that fail to capture its underlying biological diversity. This mismatch between clinical heterogeneity and diagnostic uniformity has long constrained mechanistic discovery, therapeutic innovation and individualised care. As artificial intelligence (AI) becomes increasingly integrated into biomedical research, it is now reshaping how complex, multifactorial diseases such as PCOS can be conceptualised and classified.2–4",
  "authors": [
    {
      "affiliations": [
        "State Key Laboratory of Reproductive Medicine and Offspring Health, Center for Reproductive Medicine, Institute of Women, Children and Reproductive Health, Shandong University, Jinan, China"
      ],
      "name": "Han Zhao"
    },
    {
      "affiliations": [
        "State Key Laboratory of Reproductive Medicine and Offspring Health, Center for Reproductive Medicine, Institute of Women, Children and Reproductive Health, Shandong University, Jinan, China"
      ],
      "name": "Shigang Zhao"
    },
    {
      "affiliations": [
        "State Key Laboratory of Reproductive Medicine and Offspring Health, Center for Reproductive Medicine, Institute of Women, Children and Reproductive Health, Shandong University, Jinan, China"
      ],
      "name": "Zi-Jiang Chen"
    }
  ],
  "title": "AI-driven subtyping in polycystic ovary syndrome: from diagnostic heterogeneity to precision management",
  "uid": "77935276-48ae-5a02-ba53-1048619c9bb3"
}