Search Results (424)

Background: Osteoporosis is a prevalent condition characterized by low bone mass and altered microarchitecture, increasing fracture risk. Early detection remains challenging, as conventional methods such as DXA are limited to specialized settings and often detect disease only after a fracture. Radiomics and three-dimensional (3D) imaging techniques, such as CBCT, may provide novel approaches for assessing bone quality. Methods: This pilot study analyzed 68 CBCT scans from adult patients (41 females, 27 males; mean age 57 years). Three-dimensional regions of interest (ROIs) were delineated in seven maxillofacial and mandibular sites (total 309 ROIs). Radiomic texture features were extracted and compared with corresponding T-scores from DXA measurements. Additionally, synthetic 3D reference phantoms with controlled variations in density, trabecular connectivity, and structural anisotropy were generated to evaluate the sensitivity of texture features to microarchitectural changes. Results: Several radiomic features, including GLCM-, ARM-, and Gradient-derived parameters, demonstrated consistent monotonic trends correlating with bone density and microstructural deterioration. Differences in feature values were observed across healthy, osteopenic, osteoporotic, and advanced osteoporotic states. Reference phantoms confirmed that the observed trends were attributable to structural differences rather than imaging variability. Features such as Sum Variance and Correlation exhibited potential as early indicators of microarchitectural degradation. Conclusions: Three-dimensional CBCT texture analysis may provide a non-invasive, supplementary tool for assessing bone quality and detecting early osteopenic changes. Further studies with larger cohorts are warranted to validate radiomic markers and develop predictive indices for osteoporosis screening. Full article

Background: Osteoporosis has a rising global incidence and social burden. Serum uric acid’s dual roles in oxidative stress and inflammation may influence bone health, but findings are inconsistent and require further research. This study aimed to evaluate the relationship between SUA levels and osteoporosis in a multicenter cohort obtained from different regions of Türkiye. Methods: This multi-center retrospective study included 3280 individuals, postmenopausal women and men aged 45 and older, from 16 centers in Türkiye. Individuals were excluded if they recently consumed alcohol, had severe renal dysfunction, certain hormonal or mineral disorders, specific medications, or certain menopausal statuses. Bone mineral density (BMD) at the hip and lumbar spine was measured using dual-energy X-ray absorptiometry (DXA), and participants were classified as normal or having osteopenia or osteoporosis based on T-score thresholds. Results: Overall, 34.8% were male, and 65.2% were female. For the lumbar spine, 36.8% had osteopenia, and 13.5% had osteoporosis; similarly, for the total hip, 40.8% had osteopenia, and 7.9% had osteoporosis. ROC analysis identified a threshold of 3.9 mg/dL serum uric acid (SUA) (AUC 0.374; p < 0.001), which was positively associated with both lumbar and total hip BMD. Osteoporosis rates were higher in patients with SUA < 3.9 mg/dL compared to those with SUA ≥ 3.9 mg/dL at the lumbar spine (29.1% vs. 14.2%, p < 0.001) and total hip sites (23.6% vs. 15.9%, p = 0.003). After adjustment for potential confounders, SUA was a significant independent predictor of osteoporosis in the lumbar spine (OR 0.70; p < 0.001) and the hip (OR 0.80; p < 0.001). Conclusions: Serum uric acid levels are inversely linked to bone mineral density and osteoporosis risk, indicating a potential role in bone health. However, due to study limitations, causal relationships remain unproven, and further research is needed. Full article

Postmenopausal osteoporosis is an age-related condition in which estrogen deficiency drives low-grade inflammation and oxidative stress, disrupting the homeostatic balance between bone formation and resorption. Since osteopenia represents a critical intermediate stage, preventive strategies are essential to mitigate its progression. Preclinical studies suggest that hydrogen sulfide (H₂S), a gaseous mediator with antioxidant properties, protects bone metabolism by supporting osteoblast function and suppressing osteoclast activity. Building on this evidence, we conducted the first exploratory clinical trial assessing the effects of inhalation therapy with sulfurous mineral waters on systemic biomarkers in postmenopausal women with osteopenia. Thirty-eight eligible participants underwent a daily inhalation of sulfurous waters (14.6 mg/L sulfide) for 12 consecutive days. Biomarkers of oxidative stress, inflammation, and bone turnover were assessed at baseline, immediately post-treatment, and five days after cessation in the serum of patients. The treatment was well tolerated and did not cause any early adverse effect. Serum H₂S levels, measured in a subset of participants, significantly increased, confirming systemic bioavailability. Sulfurous water inhalation induced a marked change in oxidative stress, with malondialdehyde levels declining by up to 37% from baseline. Pro-inflammatory cytokines, particularly IL-8 and MIP-1α, were significantly decreased (up to 50–70%) at the end of the treatment. Reference bone turnover markers P1NP and CTX-1 did not show significant changes; however, BALP exhibited a significant increase, suggesting the activation of pathways linked to biomineralization. These findings provide preliminary human evidence that inhaled sulfurous waters enhance systemic H₂S bioavailability and modulate redox and inflammatory pathways associated with bone remodeling in osteopenic women, supporting the rationale for further controlled pharmacodynamic investigations evaluating the potential of H₂S in bone health. Full article

Background/Objectives: Osteoporosis and osteoarthritis are age-related musculoskeletal disorders with a high socio-health burden, affecting both healthcare systems and individuals’ quality of life. Both conditions are generally accompanied by a concomitant decline in muscle mass and strength, referred to as sarcopenia. In this context, tensiomyography emerges as a novel, non-invasive potential diagnostic strategy for assessing muscle quality, as this parameter influences the progression of both conditions. Methods: Histomorphometric and immunohistochemical analyses were performed on vastus lateralis muscle tissue obtained from patients undergoing surgery for femoral fracture affected by osteoporosis or osteopenia, patients operated for hip osteoarthritis, and patients undergoing hip arthroplasty for osteoarthritis, concomitantly affected by osteoporosis or osteopenia. In addition, muscle function was assessed in these patients using tensiomyographic analysis. Results: In osteoarthritic, osteoporotic, and osteopenic patients, a reduction in muscle quality and function was observed compared with the other two experimental groups, indicating an unfavorable effect of the coexistence of the two conditions on the muscular component. Furthermore, contraction time (Tc) measured by tensiomyography was negatively correlated with lumbar spine bone mineral density values and positively correlated with the percentage of type II muscle fibers. Conclusions: This study highlights how tensiomyography may represent a valuable non-invasive diagnostic strategy for assessing muscle status in osteoporotic and osteoarthritic patients, as it is able to detect muscle alterations that parallel the worsening of bone status and that cannot be inferred from simple biopsy analysis. Thus, tensiomyography could be considered a practical adjunct tool in the clinical assessment of musculoskeletal frailty. Full article

Prostate cancer (PCa) is a prevalent malignancy in men worldwide, and both androgen deprivation therapy (ADT) and radiotherapy (RT) are key components of its management. However, these treatments significantly affect bone health by inducing bone mineral density (BMD) loss, osteopenia, osteoporosis and increased fracture risk. ADT promotes a high bone turnover state through hormonal suppression and molecular mechanisms involving increased RANKL expression and osteoclast activation. RT generates direct cytotoxic damage and inflammatory changes that compromise bone microarchitecture. Combined ADT + RT exerts synergistic detrimental effects. This narrative review synthesizes the molecular basis, clinical evidence, preventive strategies and emerging technologies related to bone health in men with PCa undergoing ADT and/or RT. Full article

Background/Objectives: Systemic sclerosis (SSc) patients frequently develop osteoporosis; however, vertebral fracture risk factors remain poorly characterized. This study identifies general and SSc-specific predictors of vertebral fractures in SSc patients undergoing osteoporosis evaluation. Methods: This multicenter cross-sectional study enrolled consecutive SSc patients meeting ACR/EULAR 2013 criteria with suspected osteoporosis. Data included demographics, disease characteristics, bone density (DXA), and vertebral imaging. Stepwise logistic regression analyzed fracture associations (p ≤ 0.05 significant). Results: The majority of 103 enrolled patients were female and all were post-menopausal. The prevalence of osteoporosis was 52.4%, that of vertebral fractures was 38.8%, and that of osteopenia was 28.1%. General risk factor analysis identified family history of fragility fractures (OR 11.8, p = 0.008) and vertebral T-scores (OR 0.6, p = 0.049) as significant predictors. When adding SSc-specific factors, only family history (OR 13.8, p = 0.03) and gastrointestinal (GI) involvement (OR 4.8, p = 0.05) remained significant. Conclusions: Vertebral fractures in SSc patients are strongly linked to a family history of fractures. The suggestive association with GI involvement may imply a significant role for malabsorption-related metabolic impairment. Prioritizing bone density screening in SSc patients with GI symptoms may enable earlier intervention and reduce fracture risk. Full article

Background: Bone Mineral Density (BMD) plays a crucial role in diagnosing osteoporosis, and early detection is essential to preventing complications such as osteoporotic fractures. However, access to dual-energy X-ray absorptiometry (DXA) screening remains limited in many healthcare settings. Objective: This study presents a fully automated artificial intelligence pipeline for BMD prediction from lumbar spine radiographs to enable opportunistic osteoporosis screening. Methods: The proposed system integrates automatic vertebral segmentation and a machine learning-based regression model for BMD prediction. A YOLO-based instance segmentation model was trained to automatically segment four lumbar vertebrae, achieving a high Intersection over Union (IoU) of 0.9. Radiomic features were extracted from the segmented vertebrae to capture advanced image characteristics and combined with clinical features from 2875 female patients. An eXtreme Gradient Boosting (XGBoost) regressor was trained to provide opportunistic BMD estimation. Results: The model achieved a mean absolute percentage error (MAPE) of 6% for BMD prediction. A classification model built from segmented vertebrae distinguished between osteoporosis, osteopenia, and normal bone with approximately 90% accuracy. Strong agreement between predicted and ground-truth BMD values was confirmed using Pearson correlation coefficient and Bland–Altman analysis. Conclusions: The proposed fully automated system demonstrates strong agreement with DXA measurements and potential for opportunistic osteoporosis screening in settings with limited DXA access. Further validation and refinement are needed to achieve clinical-grade precision for diagnostic applications. Full article

Background: The growing elderly population faces health problems like osteoporosis, but novel exercises like weighted vests (WV) and whole-body vibration (WBV) may help prevent bone loss. Methods: Thirty-one women aged 60–79 years with osteopenia or osteoporosis (T-score −2.15 ± 0.9) were randomly assigned to three groups: a control group performed exercise only; a whole-body vibration group performed the exercise on a 40 Hz, 2 mm vibration platform; and a weighted vest group performed the exercise while wearing a weighted vest. T-score, bone mineral density (BMD), muscle mass, and physical performance were assessed before and after 8 weeks. Results: The WV showed a greater T-score increase than the CT and WBV groups (WV: 0.08 ± 0.03; CT: −0.18 ± 0.04; WBV: −0.11 ± 0.16; p = 0.01, 95%CI). Leg BMD increased in the WV group (1.75 ± 0.13 to 1.79 ± 0.16 g/cm²; p = 0.02). Leg lean mass also increased in the WV (1.28 ± 0.91 kg) compared to WBV (0.17 ± 0.14 kg) and CT (0.06 ± 0.79 kg, p = 0.01, 95%CI). The WV group showed greater physical performance improvements (5TSTS and 6-MWT). The WBV group showed improved total lean mass compared to the CT group (WBV: 0.32 ± 0.17; CT = −1.20 ± 1.86, p = 0.006, 95%CI). Conclusions: WV exercise improved bone density, leg lean mass, and physical performance in older women. WBV exercise increased total lean mass and skeletal muscle index while reducing fat mass. WV exercise provides an additive effect beyond exercise alone or WBV. Full article

Langer–Giedion syndrome (LGS), also known as trichorhinophalangeal syndrome type II (TRPS II; OMIM #150230), is a contiguous-gene deletion disorder caused by haploinsufficiency of TRPS1 and EXT1. Cornelia de Lange syndrome (CdLS) is genetically heterogeneous; heterozygous variants in RAD21 cause the milder CdLS type 4 phenotype (OMIM #614701). Because RAD21 lies between TRPS1 and EXT1, overlapping phenotypes may arise when all three genes are deleted. We report a unique case of a 4-year-old female presenting with a blended phenotype of Langer–Giedion Syndrome (LGS) and Cornelia de Lange Syndrome (CdLS) type 4. This case is distinct from previously reported 8q deletions in three key aspects: (1) Complex Genomic Architecture: Chromosomal microarray revealed a novel complex rearrangement consisting of a 13.01 Mb mosaic interstitial deletion at 8q23.1–q24.12, flanked by two large duplications (21.5 Mb at 8q11.23–q23.1 and 25.78 Mb at 8q24.12–q24.3). (2) Rare Mosaicism: This represents only the second reported case of mosaicism affecting this contiguous gene region. Notably, the patient demonstrates a “mosaic rescue” effect, where the mosaicism appears to have mitigated the neurodevelopmental phenotype (the patient is bilingual and ambulatory) while failing to protect the skeleton. (3) First Bone-Specific Therapy: The patient suffered from severe, recurrent fractures due to a synergistic “double hit” of TRPS1-related osteopenia and EXT1-related exostoses. We report the first successful use of bisphosphonate therapy (pamidronate) in this specific mosaic profile, which resulted in a complete cessation of fractures during a 12-month follow-up. This case underscores the utility of detailed microarray analysis in complex phenotypes and suggests bisphosphonates as a viable rescue therapy for refractory syndromic osteoporosis. Full article

Peak bone mass gained in youth is crucial for preventing osteoporosis. Artistic gymnastics (AG) is highly osteogenic, yet its long-term effects on adults ≥ 45 years are not well documented. This case–control study compared bone mineral density (BMD) and the prevalence of osteopenia/osteoporosis in former gymnasts, age-matched controls, and reference populations from Brazil and Portugal. Participants included 65 former gymnasts (32 males, 33 females; 45–84 years), who trained for 12.6 ± 4.3 years and included 41 international competitors, and 91 controls (37 males; 45–87 years). Whole-body and femoral BMD were assessed by DXA. Physical activity during youth (10–20 years) (PA-Youth) and the past decade (PA-10) was recorded. Reference data were drawn from large cohorts in Brazil (FIBRA, n = 828) and Portugal (CIAFEL, n = 1089). Former gymnasts had substantially higher PA-Youth than controls, while PA-10 was similar. Gymnasts displayed 4–6 times higher femoral Z-scores (neck and total) and a markedly lower prevalence of osteopenia/osteoporosis (males: 3% vs. 16%; females: 36% vs. 52%, p < 0.05). These benefits remained after adjustment for age, PA-10, and hormonal/calcium therapy. Relative to reference populations, gymnasts showed greater whole-body and femoral mineralization, with no osteoporosis cases (vs. 6–12% overall; 9–13% among those ≥60 years). Age-stratified analysis (45–59 and ≥60 years) revealed a consistently lower osteopenia prevalence across age groups, except in females ≥ 60 years. In conclusion, early-life AG participation is associated with enduring skeletal benefits, including higher bone mineralization and reduced osteopenia/osteoporosis in adults ≥ 45 years. The protective effect appears diminished in older females, likely reflecting prolonged postmenopausal bone loss. Full article

Background/Objectives: Type 1 gastric neuroendocrine tumors (gNET) arise in the setting of autoimmune chronic atrophic gastritis and secondary hypergastrinemia. Vitamin D deficiency (VDD) has been associated with bone impairment and adverse outcomes in patients with neuroendocrine tumor (NET); however, data specifically addressing gNET remain limited. This study aimed to evaluate vitamin D status, supplementation requirements, and bone involvement in patients with type 1 gNET compared with those with entero-pancreatic NET (EP-NET). Methods: This retrospective study included patients with type 1 gNET followed at a tertiary referral center between 2010 and 2025 and an age- and sex-matched EP-NET cohort. VDD prevalence, time and dose required for normalization, supplementation formulations, bone status, and dietary habits were analyzed. Results: Twenty-six patients were included (thirteen gNET and thirteen EP-NET). VDD was significantly more prevalent in the gNET group compared with the EP-NET group (92.3% vs. 46.2%, p = 0.03, OR: 14). gNET required significantly higher daily cholecalciferol doses (3198.9 ± 1629 vs. 1580 ± 1121 IU/day, p = 0.008) and more frequently required multiple supplementation formulations (38.5% vs. 0%, p = 0.04). Multivariable linear regression analysis restricted to VDD patients confirmed that gNET was independently associated with higher daily cholecalciferol dose requirements (p = 0.037). Bone impairment, defined as osteoporosis or osteopenia, was significantly more common in the gNET group (61.5% vs. 15.4%, p = 0.04, OR: 8.8). Dietary adherence did not differ between groups. Conclusions: Type 1 gNET show a higher burden of VDD, increased vitamin D supplementation requirements, and a higher prevalence of bone impairment compared with EP-NET, irrespective of dietary habits. These findings suggest disease-specific mechanisms and support the need for tailored management in these patients. Full article

Background and Objectives: The vitamin K epoxide reductase complex subunit 1 (VKORC1) plays a central role in the vitamin K cycle, which is essential for γ-carboxylation of multiple bone-related proteins. Genetic variants in VKORC1 may influence bone mineral density (BMD) and osteoporosis risk. Materials and Methods: A systematic review and meta-analysis were conducted to evaluate the association between VKORC1 polymorphisms and osteopenia and osteoporosis. Relevant studies were identified through PubMed, Scopus, and Web of Science databases. Data on study characteristics, genotypes, BMD measurement, ethnicity, sex, and menopausal status were extracted. Results: Six studies comprising 7335 participants were included. All studies assessed BMD using dual-energy X-ray absorptiometry (DXA). The mean participant age ranged from 41.9 to 63.7 years. The VKORC1 variants most frequently studied, which were included in the meta-analysis, were rs9923231 and rs9934438. The overall effect of VKORC1 risk alleles on osteopenia/osteoporosis was significant with a p = 0.041 (fixed effects OR = 1.16, 95% CI = 1.01–1.35). Heterogeneity among studies was insignificant (I² = 0%, p = 0.893). Conclusions: A modest association was observed for the VKORC1 variants. The current body of evidence requires further studies to elucidate whether VKORC1 polymorphisms have a clinically meaningful role in bone health. Full article

Background and Objectives: People living with HIV (PLWH) have excess osteoporosis and fractures not fully captured by dual-energy X-ray absorptiometry (DXA). We evaluated whether trabecular bone score (TBS), calcaneal quantitative ultrasound (QUS) and bone turnover markers improve vertebral fracture risk assessment beyond areal bone mineral density (BMD) in PLWH. Methods: In this cross-sectional study, 87 antiretroviral-treated adults undergoing DXA had lumbar spine TBS and calcaneal QUS. Morphometric vertebral fractures were identified, correlates of degraded TBS were analyzed using multivariable regression, and sequential logistic models quantified the incremental contribution of TBS and CTX to discriminate for prevalent morphometric vertebral fractures. Results: Low BMD (osteopenia/osteoporosis) was present in 62% of participants, degraded TBS in 37% and morphometric vertebral fractures in 17%. Degraded versus normal TBS was associated with older age (49.1 vs. 39.7 years), longer HIV duration and lower nadir CD4+ count, as well as more frequent tenofovir disoproxil fumarate exposure (66% vs. 52%; all p ≤ 0.04). In multivariable analysis, age (per 10-year increase; adjusted odds ratio [aOR] 1.78; 95% CI 1.13–2.83) and nadir CD4+ < 200 cells/mm³ (aOR 2.29; 95% CI 1.06–4.97) independently predicted degraded TBS. In sequential cross-sectional models for prevalent morphometric vertebral fractures, the area under the curve increased from 0.71 (clinical variables) to 0.79 after adding lumbar spine T-score and to 0.85 after adding TBS; adding CTX yielded 0.87 without a statistically significant incremental gain. Conclusions: In PLWH, TBS captures bone quality deficits and improves vertebral fracture risk discrimination beyond BMD, supporting its integration alongside DXA in routine HIV care. Full article

Background: Irisin, a muscle-derived hormone, enhances the energy metabolism by activating the brown adipose tissue and acts as a bone-forming agent across the entire life span. No consistent clinical data in humans have been published so far to highlight if blood irisin as glucose/bone biomarker should be refined based on the vitamin D status (deficient or sufficient). Therefore, we aimed to objectively assess the level of irisin in female adults with abnormal and normal vitamin D status, as reflected by the level of 25-hydroxyvitamin (25OHD) in relationship with glucose and bone metabolic parameters. Methods: This pilot, prospective, exploratory study included eighty-nine menopausal women aged over 50. We excluded subjects with malignancies, bone and metabolic disorders, insulin treatment, and active endocrine disorders. Fasting profile included glycaemia, insulin, and glycated haemoglobin A1c (HbA1c). Then, 75 g oral glucose tolerance test (OGTT) included glycaemia and insulin assay after 60 and 120 min. Bone status involved bone turnover markers and central dual-energy X-ray absorptiometry providing bone mineral density (BMD) and trabecular bone score. Results: Eighty-nine subjects were included in the following two groups depending on 25OHD: vitamin D-deficient (VDD) group (N = 48; 25OHD < 30 ng/mL) and vitamin D-sufficient (VDS) group (N = 41; 25OHD ≥ 30 ng/mL). The two groups had similar age and menopausal period (62.29 ± 10.19 vs. 63.56 ± 8.16 years, respectively; 15.82 ± 9.55 vs. 16.11 ± 9.00 years, p > 0.5 for each). A statistically significant higher body mass index (BMI) was found in VDD vs. VDS group (32.25 ± 5.9 vs. 28.93 ± 4.97 kg/m², p = 0.006). Circulating irisin was similar between the groups as follows: median (IQR) of 91.85 (44.76–121.76) vs. 71.17 (38.76–97.43) ng/mL, p = 0.506. Fasting profile and OGTT assays showed no between-group difference. Median HOMA-IR in VDD group pointed out insulin resistance of 2.67 (1.31–3.29). Lowest mean/median T-scores at DXA for both groups were consistent with osteopenia category, but they were confirmed at different central sites as follows: femoral neck in both groups [VDD versus VDS group: −1.1 (−1.20–−0.90) vs. −1.1 (−1.49–−0.91), p = 0.526, respectively], only at lumbar spine for VDS group (T-score of −1.18 ± 1.13). The correlations between irisin and the mentioned parameters displayed a different profile when the analysis was performed in the groups with different 25OHD levels. In VDD group, irisin levels statistically significantly correlated with serum phosphorus (r = −0.32, p = 0.022), osteocalcin (r = −0.293, p = 0.038), P1NP (r = −0.297, p = 0.04), HbA1c (r = 0.342, p = 0.014), and BMI (r = 0.408, p = 0.003). Conclusions: This pilot study brings awareness in the analysis of irisin in relationship with glucose and bone-related biomarkers correlates, showing a distinct type of association depending on 25OHD level, which might represent an important crossroad in the multitude of irisin-activated signal transduction pathways. Full article

Background: Osteoporosis and osteopenia are prevalent bone diseases characterized by reduced bone mineral density (BMD) and an increased risk of fractures, particularly in postmenopausal women. While dual-energy X-ray absorptiometry (DXA) remains the gold standard for diagnosis, it has limitations regarding accessibility, cost, and predictive capacity for fracture risk. Machine learning (ML) approaches offer an opportunity to develop automated and more accurate diagnostic models by incorporating both BMD values and clinical variables. Method: This study retrospectively analyzed BMD data from 142 postmenopausal women, classified into 3 diagnostic groups: normal, osteopenia, and osteoporosis. Various supervised ML algorithms—including Support Vector Machines (SVM), k-Nearest Neighbors (k-NN), Decision Trees (DT), Naive Bayes (NB), Linear Discriminant Analysis (LDA), and Artificial Neural Networks (ANN)—were applied. Feature selection techniques such as ANOVA, CHI2, MRMR, and Kruskal–Wallis were used to enhance model performance, reduce dimensionality, and improve interpretability. Model performance was evaluated using 10-fold cross-validation based on accuracy, true positive rate (TPR), false negative rate (FNR), and AUC values. Results: Among all models and feature selection combinations, SVM with ANOVA-selected features achieved the highest classification accuracy (94.30%) and 100% TPR for the normal class. Feature sets based on traditional diagnostic regions (L1–L4, femoral neck, total femur) also showed high accuracy (up to 90.70%) but were generally outperformed by statistically selected features. CHI2 and MRMR methods also yielded robust results, particularly when paired with SVM and k-NN classifiers. The results highlight the effectiveness of combining statistical feature selection with ML to enhance diagnostic precision for osteoporosis and osteopenia. Conclusions: Machine learning algorithms, when integrated with data-driven feature selection strategies, provide a promising framework for automated classification of osteoporosis and osteopenia based on BMD data. ANOVA emerged as the most effective feature selection method, yielding superior accuracy across all classifiers. These findings support the integration of ML-based decision support tools into clinical workflows to facilitate early diagnosis and personalized treatment planning. Future studies should explore more diverse and larger datasets, incorporating genetic, lifestyle, and hormonal factors for further model enhancement. Full article