Algorithmic Detection of Hormonal Patterns in Women's Health using Artificial Intelligence

References

[1] Yu, J.-L., et al. (2022). Tracking of menstrual cycles and prediction of the fertile window via measurements of basal body temperature and heart rate as well as machine-learning algorithms. Reproductive Biology and Endocrinology, 20(118), 1–11. DOI: 10.1186/s12958-022-00993-4

[2] Ibid., Results (regular vs irregular cycle algorithm performance).

[3] Li, Y., Zeng, H., & Fu, J. (2024). Preovulatory progesterone levels are the top indicator for ovulation prediction based on machine learning model evaluation: a retrospective study. Journal of Ovarian Research, 17(169), 1–11. DOI: 10.1186/s13048-024-01495-0

[4] Ibid., Results (accuracy of P4 vs LH for ovulation within 24 h).

[5] Ibid., Random Forest performance for 24 h, 48 h, 72 h ovulation prediction.

[6] Ibid., Variable importance (P4 top predictor over LH, E2).

[7] Masuda, H., et al. (2025). Machine learning model for menstrual cycle phase classification and ovulation day detection based on sleeping heart rate under free-living conditions. Computers in Biology and Medicine, 187, 109705. DOI: 10.1016/j.compbiomed.2025.109705 (Epub ahead of print).

[8] Kleinschmidt, T. K., et al. (2019). Advantages of determining the fertile window with the individualised Natural Cycles algorithm over calendar-based methods. European Journal of Contraception & Reproductive Health Care, 24(6), 457–463. DOI: 10.1080/13625187.2019.1669057

[9] Leeners, B., et al. (2020). Artificial intelligence in the service of intrauterine insemination and timed intercourse timing. Fertility and Sterility, 114(3S), e371. (Conference Abstract)

[10] Wu, J., et al. (2024). Development of a machine learning-based prediction model for clinical pregnancy of intrauterine insemination in a large Chinese population. Journal of Assisted Reproduction and Genetics, 41(8), 2173–2183. DOI: 10.1007/s10815-024-03153-2

[11] Ibid., Abstract (feature list and model AUC/accuracy).

[12] Yao, Z., et al. (2021). Machine learning algorithms in constructing prediction models for assisted reproductive technology (ART) related live birth outcomes. Scientific Reports, 11(1), 10719. DOI: 10.1038/s41598-021-90102-0

[13] Zhang, Y., et al. (2022). Construction of machine learning tools to predict threatened miscarriage in the first trimester based on AEA, progesterone and β-hCG: a multicentre study. BMC Pregnancy and Childbirth, 22(1), 885. DOI: 10.1186/s12884-022-05025-y

[14] Ibid., Results (median AEA and P4 differences in outcome groups).

[15] Ibid., Results (LR, SVM, MLP performance: AUC 0.75, 0.70, etc.).

[16] Ibid., Text (LR highest accuracy 0.65, precision 0.70; KNN lowest AUC 0.61).

[17] Ibid., Discussion (poor prediction of inevitable miscarriage, all AUC <0.70).

[18] 【38†... (The answer is very long so I'll continue from where it cut off in references.)

[19] Castro, V. M., et al. (2015). Identification of subjects with polycystic ovary syndrome using electronic health records. Reproductive Biology and Endocrinology, 13, 116. DOI: 10.1186/s12958-015-0115-z

[20] Xu, H., et al. (2022). A model for predicting polycystic ovary syndrome using serum AMH, menstrual cycle length, BMI and serum androstenedione in Chinese women. Frontiers in Endocrinology, 13, 821368. DOI: 10.3389/fendo.2022.821368

[21] Vagios, S., et al. (2021). A patient-specific model combining antimüllerian hormone and body mass index as a predictor of polycystic ovary syndrome and other oligo-anovulation disorders. Fertility and Sterility, 115(1), 229–237. DOI: 10.1016/j.fertnstert.2020.07.023

[22] El-Rashidy, N., et al. (2023). Polycystic Ovary Syndrome detection machine learning model based on optimized feature selection and explainable artificial intelligence. Diagnostics, 13(5), 805. DOI: 10.3390/diagnostics13050805

[23] Zad, Z., et al. (2024). Predicting polycystic ovary syndrome with machine learning algorithms from electronic health records. Frontiers in Endocrinology, 15, 1298628. DOI: 10.3389/fendo.2024.1298628

[24] Ibid., Results (Model I AUC 82.3%; key predictors: MLP score, obesity).

[25] Gibson-Helm, M., et al. (2017). Delayed diagnosis and a lack of information associated with dissatisfaction in women with polycystic ovary syndrome. Journal of Clinical Endocrinology & Metabolism, 102(2), 604–612. DOI: 10.1210/jc.2016-2963

[26] Broer, S. L., et al. (2015). Anti-Müllerian hormone for the prediction of age at menopause: a systematic review. Human Reproduction Update, 21(3), 353–363. DOI: 10.1093/humupd/dmu067

[27] Depmann, C., et al. (2018). Can we predict age at natural menopause? Results from the prospective Doetinchem Cohort Study. Journal of Clinical Endocrinology & Metabolism, 103(7), 2498–2507. DOI: 10.1210/jc.2017-02727

@article{1708325,
      author = {Shalvi Singh},
      title = {Algorithmic Detection of Hormonal Patterns in Women's Health using Artificial Intelligence},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {8},
      number = {11},
      pages = {1058-1080},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1708325.pdf},
      abstract = {Women's hormonal patterns underlie critical aspects of health, including menstrual cyclicity, fertility, pregnancy maintenance, and the transition to menopause. Deviations in these patterns can signal conditions like polycystic ovary syndrome (PCOS), infertility, or impending menopause, with significant health implications. In recent years, computational algorithms and machine learning (ML) have been increasingly applied to detect, predict, and classify such hormonal variations. Examples range from predicting menstrual cycle phases via wearable-derived data, to classifying endocrine disorders like PCOS using electronic health records and hormone levels. These methods promise improved accuracy and personalized insights beyond traditional calendar-based or single-threshold approaches.},
      month = {May},
  }