bims-rebome 2026-02-01 papers

Curr Oncol. 2026 Jan 22. pii: 65. [Epub ahead of print]33(1):

Artificial Intelligence and Machine Learning in Bone Metastasis Management: A Narrative Review.

Halil Bulut, Serdar Demiröz, Enes Kanay, Korhan Ozkan, Costantino Errani.

BACKGROUND: Artificial intelligence (AI) and machine learning (ML) are increasingly used in the diagnosis and management of bone metastases, spanning lesion detection, segmentation, prognostic modeling, fracture risk assessment, and surgical decision support. However, the literature is heterogeneous and rapidly evolving, making it difficult for clinicians to contextualize these developments.
METHODS: We performed a narrative review of the literature on AI/ML applications in bone metastasis management, focusing on studies that address clinically relevant problems such as detection and segmentation of metastatic lesions, prediction of skeletal-related events and survival, and support for reconstructive decision-making. We prioritized recent, peer-reviewed work that reports model performance and highlights opportunities for clinical translation.
RESULTS: Most published studies center on imaging-based diagnosis and lesion segmentation using radiomics and deep learning, with generally high internal performance but limited external validation. Emerging work explores prognostic models and biomechanically informed fracture risk estimation, yet these remain at an early proof-of-concept stage. Very few frameworks are integrated into routine workflows, and explainability, bias mitigation, and health-economic impacts are rarely evaluated.
CONCLUSIONS: AI and ML tools have substantial potential to standardize imaging assessment, refine risk stratification, and ultimately support personalized management of bone metastases. Future research should focus on externally validated, multimodal models; development of AI-augmented alternatives to the Mirels score; federated multicenter collaboration; and routine incorporation of explainability and cost-effectiveness analyses.

Keywords: artificial intelligence; bone metastasis; machine learning; orthopedic oncology; prognostic modeling

DOI: https://doi.org/10.3390/curroncol33010065

Front Med (Lausanne). 2025 ;12 1655245

Prognostic biomarkers for overall survival in patients undergoing surgery for bone metastases: a pan-cancer study.

Elisa Belluzzi, Assunta Pozzuoli, Pietro Belloni, Maria Grazia Rodà, Andrea Angelini, Pietro Ruggieri.

Prompt diagnosis and prognostic assessment of bone metastases (BMs) remain challenging with most studies and prognostic models focusing on a single primary tumor and neglect host-related biomarkers. Therefore, this pan-cancer study aimed to evaluate bone metabolism, inflammatory, and hematological biomarkers in patients undergoing surgery for BMs, identify risk factors for BM development, and create a prognostic nomogram. A prospective cohort of adult patients with histologically confirmed BMs from various cancers was enrolled between 2020 and 2023. Baseline data included demographics, tumor type, and preoperative biomarkers such as bone turnover markers (P1NP, BAP), calcium, LDH, IGFBP-3, HALP, RDW, and NLR. Outcomes were recurrence, metastasis, and overall survival (OS), analyzed with Kaplan-Meier and Cox regression. Prognostic variables were integrated into a nomogram and validated by ROC curves and calibration. Ninety-one patients underwent surgery for BM. The most frequent primary cancers were breast (28.6%), kidney (23.1%), and lung (16.5%). Significant tumor-type differences were observed in BAP (p = 0.015), IGFBP-3 (p = 0.008), and HALP (p = 0.029). Univariate analysis identified P1NP, BAP, calcium, LDH, and RDW as prognostic markers. Multivariate models found age, kidney cancer, IGFBP-3, RDW, and NLR as independent predictors. The nomogram demonstrated strong predictive performance at 12 months (AUC = 82.3) and 24 months (AUC = 81.0). Tumor-specific and host-related biomarkers (IGFBP-3, NLR, and RDW) improved prognostic stratification beyond tumor type. The proposed nomogram demonstrated good discriminatory performance, supporting its potential use in personalized prognostic assessment and treatment planning.

Keywords: bone markers; bone metastasis; hematological markers; inflammatory markers; nomogram

DOI: https://doi.org/10.3389/fmed.2025.1655245

Int J Radiat Oncol Biol Phys. 2026 Jan 27. pii: S0360-3016(25)06612-X. [Epub ahead of print]

Predictors of Vertebral Compression Fracture Following Stereotactic Body Radiation Therapy in SINS Potentially Unstable Spinal Metastases.

Laura Burgess, Eshetu G Atenafu, Kang Liang Zeng, Hanbo Chen, Deepak Dinakaran, Chia-Lin Tseng, Jay Detsky, Hany Soliman, Joel Mullins, Jeremie Larouche, Christopher Witiw, Pejman Maralani, Cari Whyne, Michael Hardisty, Arjun Sahgal.

PURPOSE: The Spinal Instability in Neoplasia Score (SINS) is the gold standard to determine if the metastatically involved spine is stable, potentially unstable, or frankly unstable. In potentially unstable spines, clarity is needed about the risk of post-stereotactic body radiation therapy (SBRT) vertebral compression fracture (VCF) and which patients may benefit from early stabilization. We aimed to identify predictors of VCF following spine SBRT in patients with potentially unstable SINS spinal metastases..
METHODS AND MATERIALS: A retrospective review of a prospectively maintained database of patients treated with SBRT for spinal metastases from January 2008 to December 2022 was performed. This analysis included only spine segments categorized as potentially unstable (SINS 7-12). The primary outcome was the rate of VCF. The cumulative incidence of VCF and the impact of covariates were estimated.
RESULTS: Five hundred twenty-four patients with 976 treated spinal segments were SINS potentially unstable. Out of 976, 168 patients (17.2%) experienced a VCF after SBRT. Out of 168, 107 patients (63.7%) were iatrogenic and 61 (36.3%) concurrent with tumor progression. The 12-month incidence of iatrogenic VCF was 9.3% (95% CI, 7.4%-11.5%) as opposed to 23.4% (95% CI, 17.4%-29.9%) when concurrent with tumor progression (P < .0001). Multivariable analysis confirmed iatrogenic VCF associated with pre-existing VCF (hazard ratios [HR] = 1.83; 95% CI, 1.235-2.714; P = .003), no previous spine surgery (HR = 1.67; 95% CI, 1.024-2.710; P = .040), SINS total ≥10 (HR = 1.68; 95% CI, 1.122-2.512; P = . 012), and an increasing D90 clinical target volume in equivalent dose in 2 Gy (HR = 1.03; 95% CI, 1.010-1.055; P = .004). In the setting of concurrent tumor progression, only an increasing D90 to the clinical target volume in equivalent dose in 2 Gy fractions (HR = 1.04; 95% CI, 1.013-1.076; P = .005) predicted for VCF.
CONCLUSIONS: Tumor control outweighs the risk of VCF associated with spine SBRT in potentially unstable metastases. Prophylactic stabilization could be considered in segments with a total SINS ranging from 10 to 12, a pre-existing VCF, and when treating with high doses.

DOI: https://doi.org/10.1016/j.ijrobp.2025.12.029

Cancer Rep (Hoboken). 2026 Feb;9(2): e70451

Hypofractionated Radiation Therapy for Pain Relief of Patients With Spinal Metastasis: A Real-World Analysis.

Lu Sun, Fan Luo, Yajuan Zhou, Xiyou Liu, Pingping Zhang, Dan Li, Yi Peng.

PURPOSE: Spinal metastases may cause pain, neurological compromise, paraplegia, and limb movement disorders; their management requires a comprehensive approach. Alongside systemic anti-tumor therapies, focal interventions such as radiotherapy, bone-modifying agents, and surgery are crucial for slowing disease progression and managing pain in spinal metastases. However, substantial variations exist in radiotherapy regimens for spinal metastases. In this study, we aimed to investigate the safety and efficacy of hypofractionated radiation therapy (HFRT) regimens at our hospital, specifically to evaluate pain relief and incidence of re-irradiation after HFRT.
METHODS: In this retrospective study, data from 58 patients diagnosed with spinal metastasis who received HFRT (4.5-10Gy * 3-7F) at our center between December 2017 and June 2022 were analyzed. All patients were followed up from the initiation of HFRT to either death or their last follow-up visit. Degree of pain was assessed using the numeric rating scale (NRS) before and after 1 month of HFRT. A multivariate Cox regression model was established to identify the independent risk factors for prognostic analysis of spinal metastasis.
RESULTS: HFRT could effectively manage pain in patients with spinal metastasis. The pain scores were significantly decreased after HFRT (3.43 vs. 1.5, p < 0.001), with 84.5% patients experiencing improved pain relief 1 month after radiotherapy. No cases of radiation myelitis were observed during the follow-up period. Furthermore, the incidence of re-radiotherapy was significantly increased in patients with spinal metastases who received moderate HFRT (< 5 Gy/day) (p = 0.01, HR = 0.43).
CONCLUSION: HFRT significantly reduced pain scores and reirradiation rates without increasing radiation myelitis incidence for spinal metastases.

Keywords: bone metastasis; hypofractionated radiation therapy; pain management; radiotherapy regimen

DOI: https://doi.org/10.1002/cnr2.70451