پیش‌بینی PCOS از طریق مدلینگ هوش مصنوعی با نشانگرهای زیستی: یک مطالعه اولیه برای تجویز تمرینات ورزشی در زنان ایرانی

نوع مقاله : اصیل پژوهشی

نویسندگان

1 دانشجوی دکتری فیزیولوژی ورزشی، دانشکده علوم ورزشی، دانشگاه مازندران، بابلسر، ایران.

2 استاد فیزیولوژی ورزشی، دانشکده علوم ورزشی، دانشگاه مازندران، بابلسر، ایران. استاد فیزیولوژی ورزشی، مرکز تحقیقات سلامت و عملکرد ورزشی، دانشکده علوم ورزشی، دانشگاه مازندران، بابلسر، ایران.

3 استادیار گروه زنان و مامایی، دانشکده پزشکی، دانشگاه آزاد اسلامی تهران، تهران، ایران.

چکیده

مقدمه: فرزندآوری و جوان‌سازی جامعه، از چالش‌های جدی دنیای امروزی است. سندرم تخمدان پلی‌کیستیک (PCOS) که با چاقی مرتبط می‌باشد، به یک نگرانی رایج برای باروری تبدیل شده است. تشخیص زودهنگام PCOS می‌تواند روند درمانی و کیفیت زندگی خانواده را بهبود بخشد. مطالعه حاضر با هدف اولیه آموزش مدل‌های یادگیری ماشین با داده‌های نشانگرهای هورمونی و سندرم متابولیک برای شناسایی PCOS و سپس ارائه راهکارهای تمرینات ورزشی در زنان نابارور انجام شد.
روش‌کار: داده ­های 1000 زن نابارور 45-20 ساله مبتلا و غیرمبتلا به PCOS تحت پردازش اولیه قرار گرفت و در نهایت داده‌های 500 نفر، به روش ­های مختلف مانند جنگل تصادفی (RF)، حذف بازگشتی ویژگی (RFE) و اطلاعات متقابل (MI)، ویژگی ­های مهم انتخاب و وارد الگوریتم ­های مختلف شد.
یافته­ ها: آموزش مدل درخت تصمیم (DT) با انتخاب ویژگی به روش RF، بالاترین دقت را در تشخیص نسبت به سایرین داشت. همچنین با توجه به نتایج، انتخاب ویژگی به روش RFE، MI و RF نشان داد که علاوه بر هورمون­ های جنسی، قند ناشتا، کلسترول، لیپوپروتئین با چگالی بالا، ویتامین D3 و هورمون ­های مرتبط با تیروئید، عوامل برجسته‌ای هستند که در پیش‌بینی با دقت بالای PCOS نقش دارند.
نتیجه ­گیری: تشخیص PCOS و بررسی اهمیت بیومارکرهای مرتبط با آن با هوش مصنوعی نشان داد، شاخص‌های متابولیکی نیز در کنار هورمون‌های جنسی از اهمیت ویژه‌ای در تشخیص و درمان این بیماری برخوردار می‌باشند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Predicting PCOS through Artificial Intelligence Modeling with Biomarkers: A Preliminary Study for Prescribing Exercise in Iranian Women

نویسندگان [English]

  • Zahra Arab Taherizadeh 1
  • Valiollah Dabidi Roshan 2
  • Marzieh Mirzaei 3
1 PhD Student in Exercise Physiology, School of Sports Sciences, University of Mazandaran, Babolsar, Iran.
2 Professor, Department of Exercise Physiology, School of Sports Sciences, University of Mazandaran, Babolsar, Iran. Professor, Department of Exercise Physiology, Athletic Performance and Health Research Centre, School of Sports Sciences, University of Mazandaran, Babolsar, Iran.
3 Assistant Professor, Department of Obstetrics and Gynecology, Faculty of Medicine, Islamic Azad University of Tehran, Tehran, Iran.
چکیده [English]

Introduction: Childbearing and rejuvenating society are serious challenges in today's world. Polycystic ovary syndrome (PCOS), which is associated with obesity, has become a common concern for fertility. Early diagnosis of PCOS can improve the treatment process and the quality of life of the family. The present study was conducted with aim to train machine learning models with hormonal marker data and metabolic syndrome to identify PCOS and then present exercise strategies for infertile women.
Methods: Data from 1000 infertile women aged 20-45 years with and without PCOS were initially processed, and subsequently, 500 individuals were selected using various methods, including random forests (RF), recurrent feature elimination (RFE), and interaction (MI), to identify important features and incorporate them into different algorithms.
Results: Training Decision Tree (DT) model with feature selection by the RF method had the highest accuracy in diagnosis compared to others. Also, according to the results of feature selection by RFE, MI, and RF methods, it was shown that, in addition to sex hormones, fasting glucose, cholesterol, high-density lipoprotein, vitamin D3, and thyroid-related hormones are prominent factors that play a role in predicting PCOS with high accuracy.
Conclusion: Diagnosis of PCOS and investigation of its related biomarkers with artificial intelligence showed that metabolic indicators, along with sex hormones, are of particular importance in the diagnosis and treatment of this disease.

کلیدواژه‌ها [English]

  • Artificial Intelligence
  • Exercise
  • Infertility
  • Metabolic Syndrome
  • Polycystic Ovary Syndrome

مراجع

  1. Dabidi Roshan V, Noorbakhsh S, Ziatabar Ahmadi SF, Nikseresht M. The physiological impacts of the low‐and moderate‐volume‐HIIT with or without nano‐curcumin supplement in women in menopause with obesity. Advances in Public Health 2024; 2024(1):5243088.
  2. Chen W, Pang Y. Metabolic syndrome and PCOS: pathogenesis and the role of metabolites. Metabolites 2021; 11(12):869.
  3. Gautam D, Purandare N, Maxwell CV, Rosser ML, O'Brien P, Mocanu E, et al. The challenges of obesity for fertility: A FIGO literature review. International Journal of Gynecology & Obstetrics 2023; 160:50-5.
  4. Obeagu EI, Njar VE, Obeagu GU. Infertility: Prevalence and consequences. Int J Curr Res Chem Pharm Sci 2023; 10(7):43-50.
  5. Gnoth C, Godehardt E, Frank-Herrmann P, Friol K, Tigges J, Freundl G. Definition and prevalence of subfertility and infertility. Human reproduction 2005; 20(5):1144-7.
  6. Sajda P. Machine learning for detection and diagnosis of disease. Annu. Rev. Biomed. Eng 2006; 8(1):537-65.
  7. Tahmasbi H, Besharati R, Alishahi M. A Model for Diagnosing Liver Diseases using “Machine Learning” Techniques. Studies in Medical Sciences 2022; 33(11):814-22.
  8. Veisi H, Ghaedsharaf HR, Ebrahimi M. Improving the performance of machine learning algorithms for heart disease diagnosis by optimizing data and features. Soft computing journal 2021; 8(1):70-85.
  9. Lv W, Song Y, Fu R, Lin X, Su Y, Jin X, et al. Deep learning algorithm for automated detection of polycystic ovary syndrome using scleral images. Frontiers in Endocrinology 2022; 12:789878.
  10. Thakre V, Vedpathak S, Thakre K, Sonawani S. PCOcare: PCOS detection and prediction using machine learning algorithms. Biosci Biotechnol Res Commun 2020; 13(14):240-4.
  11. Denny A, Raj A, Ashok A, Ram CM, George R. i-hope: Detection and prediction system for polycystic ovary syndrome (pcos) using machine learning techniques. InTENCON 2019-2019 IEEE Region 10 Conference (TENCON) 2019: 673-678.
  12. Calcaterra V, Magenes VC, Massini G, De Sanctis L, Fabiano V, Zuccotti G. High fat diet and polycystic ovary syndrome (PCOS) in adolescence: an overview of nutritional strategies. Nutrients 2024; 16(7):938.
  13. Ray NM. From Nature To Nurture: A Review of Herbal Approaches to Polycystic Ovary Syndrome (PCOS). InObstetrics & Gynaecology Forum 2024; 34(3).
  14. Ribeiro VB, Kogure GS, Lopes IP, Silva RC, Pedroso DC, de Melo AS, et al. Effects of continuous and intermittent aerobic physical training on hormonal and metabolic profile, and body composition in women with polycystic ovary syndrome: A randomized controlled trial. Clinical endocrinology 2020; 93(2):173-86.
  15. Al-Eisa E, Gabr SA, Alghadir AH. Effects of supervised aerobic training on the levels of anti-Mullerian hormone and adiposity measures in women with normo-ovulatory and polycystic ovary syndrome. JPMA. The Journal of the Pakistan Medical Association 2017; 67(4):499-507.
  16. Khanna VV, Chadaga K, Sampathila N, Prabhu S, Bhandage V, Hegde GK. A distinctive explainable machine learning framework for detection of polycystic ovary syndrome. Applied System Innovation 2023; 6(2):32.
  17. Nandipati SC, Ying CX. Polycystic Ovarian Syndrome (PCOS) classification and feature selection by machine learning techniques. Applied Mathematics and Computational Intelligence (AMCI) 2020; 9:65-74.
  18. Kumari R, Singh J, Gosain A. SmS: SMOTE-stacked hybrid model for diagnosis of polycystic ovary syndrome using feature selection method. Expert Systems with Applications 2023; 225:120102.
  19. Elmannai H, El-Rashidy N, Mashal I, Alohali MA, Farag S, El-Sappagh S, et al. Polycystic ovary syndrome detection machine learning model based on optimized feature selection and explainable artificial intelligence. Diagnostics 2023; 13(8):1506.
  20. Moore AM, Campbell RE. Polycystic ovary syndrome: understanding the role of the brain. Frontiers in neuroendocrinology 2017; 46:1-14.
  21. Shroff R, Syrop CH, Davis W, Van Voorhis BJ, Dokras A. Risk of metabolic complications in the new PCOS phenotypes based on the Rotterdam criteria. Fertility and sterility 2007; 88(5):1389-95.
  22. Parlak B, Uysal AK. A novel filter feature selection method for text classification: Extensive Feature Selector. Journal of Information Science 2023; 49(1):59-78.
  23. Liu Z, Yang J, Wang L, Chang Y. A novel relation aware wrapper method for feature selection. Pattern Recognition 2023; 140:109566.
  24. Almenning I, Rieber-Mohn A, Lundgren KM, Shetelig Løvvik T, Garnaes KK, Moholdt T. Effects of high intensity interval training and strength training on metabolic, cardiovascular and hormonal outcomes in women with polycystic ovary syndrome: a pilot study. Plos one 2015; 10(9):e0138793.
  25. Rao M, Khan AA, Adnan QU. Effects of high-intensity interval training and strength training on levels of testosterone and physical activity among women with polycystic ovary syndrome. Obstetrics & gynecology science 2022; 65(4):368-75.
  26. Ribeiro VB, Lopes IP, Dos Reis RM, Silva RC, Mendes MC, Melo AS, et al. Continuous versus intermittent aerobic exercise in the improvement of quality of life for women with polycystic ovary syndrome: A randomized controlled trial. Journal of health psychology 2021; 26(9):1307-17.
  27. Kogure GS, Lopes IP, Ribeiro VB, Mendes MC, Kodato S, Furtado CL, et al. The effects of aerobic physical exercises on body image among women with polycystic ovary syndrome. Journal of affective disorders 2020; 262:350-8.
  28. Lopes IP, Ribeiro VB, Reis RM, Silva RC, Dutra de Souza HC, Kogure GS, et al. Comparison of the effect of intermittent and continuous aerobic physical training on sexual function of women with polycystic ovary syndrome: randomized controlled trial. The journal of sexual medicine 2018; 15(11):1609-19.
  29. Aktaş HŞ, Uzun YE, Kutlu O, Pençe HH, Özçelik F, Çil EÖ, et al. The effects of high intensity-interval training on vaspin, adiponectin and leptin levels in women with polycystic ovary syndrome. Archives of physiology and biochemistry 2022; 128(1):37-42.
  30. Giallauria F, Palomba S, Maresca L, Vuolo L, Tafuri D, Lombardi G, et al. Exercise training improves autonomic function and inflammatory pattern in women with polycystic ovary syndrome (PCOS). Clinical endocrinology 2008; 69(5):792-8.
  31. Vigorito C, Giallauria F, Palomba S, Cascella T, Manguso F, Lucci R, et al. Beneficial effects of a three-month structured exercise training program on cardiopulmonary functional capacity in young women with polycystic ovary syndrome. The Journal of Clinical Endocrinology & Metabolism 2007; 92(4):1379-84.
  32. Joham AE, Naderpoor N, Celik O. Mechanisms involved in the development of obesity with PCOS. Frontiers in Endocrinology 2024; 15:1444299.
  33. Ghafoor S. Impact of Obesity and Weight Management on Women with Polycystic Ovary Syndrome and Coexisting Obesity–A Brief Narrative Review. Actual Gynecology & Obstetrics/Aktuální Gynekologie a Porodnictví 2023; 15.
  34. Aggarwal M, Chakole S. Prevalence of polycystic ovarian syndrome and its link to obesity in adolescent girls. Cureus 2023; 15(9).
  35. Rosenberg SL. The relationship between PCOS and obesity: which comes first?. The Science Journal of the Lander College of Arts and Sciences 2019; 13(1):5.
  36. Krakowsky Y, Conners W, Morgentaler A. Serum concentrations of sex hormone–binding globulin vary widely in younger and older men: Clinical data from a men’s health practice. European Urology Focus 2019; 5(2):273-9.
  37. Ruiz-González D, Cavero-Redondo I, Hernández-Martínez A, Baena-Raya A, Martínez-Forte S, Altmäe S, et al. Comparative efficacy of exercise, diet and/or pharmacological interventions on BMI, ovulation, and hormonal profile in reproductive-aged women with overweight or obesity: a systematic review and network meta-analysis. Human reproduction update 2024; 30(4):472-87.
  38. Borer KT. Advanced exercise endocrinology. Human Kinetics; 2013.
  39. Yu J, Zhou Y, Ding J, Zhang D, Yu C, Huang H. Characteristics and possible mechanisms of metabolic disorder in overweight women with polycystic ovary syndrome. Frontiers in Endocrinology 2023; 13:970733.
  40. O'Donoghue G, Blake C, Cunningham C, Lennon O, Perrotta C. What exercise prescription is optimal to improve body composition and cardiorespiratory fitness in adults living with obesity? A network meta‐analysis. Obesity Reviews 2021; 22(2):e13137.
  41. Higgins JP, Higgins CL. Prescribing exercise to help your patients lose weight. Cleve Clin J Med 2016; 83(2):141-50.
مجله زنان، مامایی و نازایی ایران
دوره 28، شماره 11
بهمن 1404
صفحه 31-45

فایل ها

هم رسانی

ارجاع به این مقاله

آمار