EXTENDED BREASTFEEDING AND POSTMENOPAUSAL OSTEOPOROSIS: A RETROSPECTIVE REAPPRAISAL THROUGH ARTIFICIAL INTELLIGENCE

Yıl 2025, Cilt: 15 Sayı: 3, 302 - 308, 15.09.2025

Öznur Uzun , Evren Yaşar

Öz

Objective: This study revisits clinical and demographic data on osteoporosis in postmenopausal women, with a particular emphasis on extended breastfeeding (>12 months) as a modifiable risk factor. Furthermore, we conceptualize how artificial intelligence (AI)—if available in the early 2010s—might have altered the trajectory of our research in terms of design, insight, and clinical decision support.

Methods: We conducted a retrospective analysis of 127 osteoporotic and 53 non-osteoporotic postmenopausal women evaluated between 2010 and 2012. Demographics, reproductive history, lifestyle factors, serum osteocalcin levels, dynamic balance scores, and vertebral fracture prevalence were compared. Additionally, we conceptually simulate an AI-assisted reinterpretation of the same dataset, exploring the hypothetical role of machine learning in risk stratification, outcome prediction, and pattern recognition.

Results: Osteoporotic patients were significantly older (p<0.001), had lower BMI (p<0.001), experienced earlier menopause (p=0.035), and were more likely to have breastfed for ≥12 months (p=0.005). Vertebral fractures were present in 22.8% of osteoporotic women. Balance errors and osteocalcin levels were significantly higher in the osteoporotic group. AI-assisted reanalysis would likely have identified nonlinear risk patterns and interaction effects between breastfeeding duration, early menopause, and BMD reduction.

Conclusion: Our reappraisal confirms extended breastfeeding as a significant osteoporosis risk factor in postmenopausal women. Had AI been available in 2010–2012, predictive algorithms and integrative models may have uncovered deeper associations, offered individualized risk predictions, and reshaped preventive care.

Anahtar Kelimeler

artificial intelligence , body mass index , breastfeeding , machine learning , menopause , osteoporosis

Etik Beyan

This retrospective observational study analyzed data collected from women aged 50 and older who were evaluated at previous Ankara Physical Therapy and Rehabilitation Education and Research Hospital (This hospital currently serves under the roof of Ankara Bilkent City Hospital) between May 2010 and June 2012. At the time, ethics committee approval was formally obtained from the Education Planning Committee (EPK Approval NO: 1152) in accordance with national guidelines. Therefore, we did not need to obtain a new ethics committee approval. All data were anonymized, and no additional patient intervention or data collection was conducted for the current manuscript. The study complies with the ethical standards of the institutional and national research committees and with the 1964 Helsinki declaration and its later amendments

Destekleyen Kurum

None

Uzun Süreli Emzirme ve Postmenopozal Osteoporoz: Yapay Zeka Merceğinden Retrospektif Yeniden Değerlendirme

Öz

Amaç Bu çalışma, değiştirilebilir bir risk faktörü olarak uzun süreli emzirmeye (>12 ay) özellikle vurgu yaparak, postmenopozal kadınlarda osteoporoz ile ilgili klinik ve demografik verileri yeniden gözden geçirmektedir. Ayrıca, 2010'ların başında mevcut olsaydı yapay zekanın (AI) tasarım, içgörü ve klinik karar desteği açısından araştırmamızın yörüngesini nasıl değiştirebileceğini ortaya koymak istedik.
Yöntemler: 2010-2012 yılları arasında değerlendirilen 127 osteoporotik ve 53 osteoporotik olmayan postmenopozal kadının retrospektif bir analizini yaptık. Demografik özellikleri, üreme öyküsünü, yaşam tarzı faktörlerini, serum osteokalsin düzeylerini, dinamik denge skorlarını ve vertebral kırık prevalansını karşılaştırdık. Ek olarak, aynı veri setinin yapay zeka destekli yeniden yorumlanmasını simüle ederek, makine öğreniminin risk tabakalandırması, sonuç tahmini ve örüntü tanımadaki rolü üzerine değerlendirme gerçekleştirdik.
Bulgular: Osteoporotik hastalar önemli ölçüde daha yaşlı (p<0,001), daha düşük beden kitle indeksine sahip (p<0,001),ve daha erken menopoza girmişti (p=0,035). Bu hastaların 12 aydan uzun emzirmiş olma olasılığı daha yüksekti (p=0,005). Osteoporotik kadınların %22,8'inde vertebral kırıklar mevcuttu. Denge hataları ve osteokalsin düzeyleri osteoporotik grupta anlamlı derecede yüksekti. Yapay zeka destekli yeniden analiz muhtemelen doğrusal olmayan risk modellerini ve emzirme süresi, erken menopoz ve KMY azalması arasındaki etkileşim etkilerini tanımlayabilirdi.
Sonuç: Yeniden değerlendirmemiz, postmenopozal kadınlarda uzun süreli emzirmenin önemli bir osteoporoz risk faktörü olduğunu doğrulamaktadır. Yapay zeka 2010-2012 yıllarında mevcut olsaydı, öngörücü algoritmalar ve bütünleştirici modeller daha derin ilişkileri ortaya çıkarabilir, bireyselleştirilmiş risk tahminleri sunabilir ve önleyici bakımı yeniden şekillendirebilirdi.

Anahtar Kelimeler

beden kitle indeksi , emzirme , menopoz , osteoporozis , yapay öğrenme , yapay zeka

Kaynakça

• 1. Sözen T, Özışık L, Başaran NÇ. An overview and management of osteoporosis. Eur J Rheu-matol. 2017;4(1):46-56.
• 2. Aibar-Almazán A, Voltes-Martínez A, Castellote-Caballero Y, Afanador-Restrepo DF, Car-celén-Fraile MDC, López-Ruiz E. Current Status of the Diagnosis and Management of Osteopo-rosis. Int J Mol Sci. 2022;23(16):9465.
• 3. Khosla S, Hofbauer LC. Osteoporosis treatment: recent developments and ongoing challenges. Lancet Diabetes Endocrinol. 2017;5(11):898–907.
• 4. Kovacs CS. Calcium and bone metabolism disorders during pregnancy and lactation. Endo-crinol Metab Clin North Am. 2011;40(4):795-826.
• 5. Scioscia MF, Zanchetta MB. Recent Insights into Pregnancy and Lactation-Associated Osteo-porosis (PLO). Int J Womens Health. 2023;15:1227-38.
• 6. O'Sullivan SM, Grey AB, Singh R, Reid IR. Bisphosphonates in pregnancy and lactation-associated osteoporosis. Osteoporos Int. 2006;17(7):1008-12.
• 7. Karlsson MK, Ahlborg HG, Karlsson C. Maternity and bone mineral density. Acta Orthop. 2005;76(1):2–13.
• 8. Uzun Ö, Köklü K, Özel S, Şahin AY, Delialioğlu SÜ, Kulaklı F. Evaluation of gynecological risk factors in osteoporosis. Acta Oncol Turc. 2014;47(1):11-5.
• 9. Bajwa J, Munir U, Nori A, Williams B. Artificial intelligence in healthcare: transforming the practice of medicine. Future Healthc J. 2021;8(2):e188-94.
• 10. Clynes MA, Harvey NC, Curtis EM, Fuggle NR, Dennison EM,Cooper C. The epidemiolo-gy of osteoporosis. Br Med Bull. 2020;133(1):105-17.
• 11. Singh S, Kumar D, Lal AK. Serum Osteocalcin as a Diagnostic Biomarker for Primary Oste-oporosis in Women. J Clin Diagn Res. 2015;9(8):RC04-7.
• 12. Zhang L, Cheng J, Su H, Wang Z, Dai W. Diagnostic value of circulating bone turnover markers osteocalcin, cathepsin K, and osteoprotegerin for osteoporosis in middle-aged and elderly postmenopausal women. Arch Med Sci. 2024;20(5):1727-30.
• 13. Kutsal FY, Ergin Ergani GO. Vertebral compression fractures: Still an unpredictable aspect of osteoporosis. Turk J Med Sci. 2021;51(2):393-9.
• 14. Berk E, Koca TT, Güzelsoy SS, Nacitarhan V, Demirel A. Evaluation of the relationship be-tween osteoporosis, balance, fall risk, and audiological parameters. Clin Rheumatol. 2019;38(11):3261-8.
• 15. Toosizadeh N, Ehsani H, Miramonte M, Mohler J. Proprioceptive impairments in high fall risk older adults: the effect of mechanical calf vibration on postural balance. Biomed Eng Online. 2018;17(1):51.
• 16. Zhang Y, Ma M, Huang X, Liu J, Tian C, Duan Z, et al. Machine learning is changing osteoporosis detection: an integrative review. Osteoporos Int. 2025;36(8):1313-26.
• 17. Mehrabi M, Salek N. Enhancing diagnostic accuracy in breast cancer: integrating novel ma-chine learning approaches with enhanced image preprocessing for improved mammography analysis. Pol J Radiol. 2024;89:e573-83
• 18. Volkmann H, Höglinger GU, Grön G, Bârlescu LA; DESCRIBE-PSP study group; Müller HP, Kassubek J. MRI classification of progressive supranuclear palsy, Parkinson disease and controls using deep learning and machine learning algorithms for the identification of regions and tracts of interest as potential biomarkers. Comput Biol Med. 2025;185:109518.
• 19. Alex JSR, Roshini R, Maneesha G, Aparajeeta J, Priyadarshini B, Lin CY, et al. Enhanced detection of mild cognitive impairment in Alzheimer's disease: a hybrid model integrating dual biomarkers and advanced machine learning. BMC Geriatr. 2025;25(1):54. 2025;19(1):70.
• 20. Baran FDE, Cetin M. AI-driven early diagnosis of specific mental disorders: a comprehensive study. Cogn Neurodyn. 2025;19(1):70.
• 21. Li YC, Chen HH, Horng-Shing Lu H, Hondar Wu HT, Chang MC, Chou PH. Can a Deep-learning Model for the Automated Detection of Vertebral Fractures Approach the Performance Level of Human Subspecialists? Clin Orthop Relat Res. 2021;479(7):1598-612.
• 22. Gudmundsson HT, Hansen KE, Halldorsson BV, Ludviksson BR, Gudbjornsson B. Clinical decision support system for the management of osteoporosis compared to NOGG guidelines and an osteology specialist: a validation pilot study. BMC Med Inform Decis Mak. 2019;19(1):27.