During the progress of oncological diseases, there is an increased probability that spinal metastases may develop, requiring personalised treatment options. Risk calculator systems aim to provide assistance in the therapeutic decision-making process by estimating survival chances. The predictive ability of such calculators can be improved, thereby optimising the choice of personalised therapy. The aim of this research was to create a new risk assessment system and show a method with which other centres can develop their own local score. We created a database by retrospectively processing 454 patients. The prognostic factors were selected via a network science-based correlation analysis that maximises Uno's C-index, keeping only a small number of predictors. To validate the new system, we calculated the D-statistic, the Integrated Discrimination Index, made a five-fold cross-validation and also calculated the integrated time-dependent Brier score. As a result of multivariate Cox analysis, we found five independent prognostic factors suitable for the design of the risk calculator. This new system has a better predictive ability compared with six other well-known systems with an average C-index of 0.706 at 10 years (95% confidence interval 0.679-0.733). An accurate estimation of the life expectancy of cancer patients is essential for the implementation of personalised medicine. The training performance of our system is encouraging, indicating the benefit of a network science-based visualisation step. We believe that in order to further improve the prediction ability, it is necessary to systematise previously 'unknown' factors (e.g. radiological morphology).

(1) Background: Survival analysis models in clinical research must effectively handle censored data, where complete survival times are unknown for some subjects. While established methodologies exist for validating standard machine learning models, current benchmarking approaches rarely assess model robustness under varying censoring conditions. This limitation creates uncertainty about model reliability in real-world applications where censoring patterns may differ from training data. We address this gap by introducing a systematic benchmarking methodology focused on censoring sensitivity. (2) Methods: We developed a benchmarking framework that assesses survival models through controlled modification of censoring conditions. Five models were evaluated: Cox proportional hazards, survival tree, random survival forest, gradient-boosted survival analysis, and mixture density networks. The framework systematically reduced observation periods and increased censoring rates while measuring performance through multiple metrics following Bayesian hyperparameter optimization. (3) Results: Model performance showed greater sensitivity to increased censoring rates than to reduced observation periods. Non-linear models, especially mixture density networks, exhibited higher vulnerability to data quality degradation. Statistical comparisons became increasingly challenging with higher censoring rates due to widened confidence intervals. (4) Conclusions: Our methodology provides a new standard for evaluating survival analysis models, revealing the critical impact of censoring on model performance. These findings offer practical guidance for model selection and development in clinical applications, emphasizing the importance of robust censoring handling strategies.

Meningiomas are the most common primary tumors in the central nervous system. Surgical resection remains the main treatment option, often resulting in a curative outcome; however, careful preoperative planning is essential. One of the primary concerns for neurosurgeons treating meningiomas is tumor consistency, as this has a significantly impact on the likelihood of complete resection. Predicting the consistency and histology of a meningioma prior to surgery is valuable for selecting the appropriate surgical instruments and planning the approach. We conducted a retrospective study to analyze clinical data and preoperative MRI images of patients who underwent surgery for intracranial meningiomas. T1, T1c, T2, and FLAIR sequences were obtained for all patients. Surgical notes were reviewed to assess tumor consistency. Tumor segmentation was performed using ITK-SNAP software. Fractal analysis and statistical analyses were made, including t-tests, Fisher’s exact tests, logistic regression, and ROC analysis. Forty-eight patients met the selection criteria. For prediction of consistency when only fractal parameters were used, lacunarity index was able to discriminate between soft and hard consistency with an AUC value of 0.745 (95% CI: 0.538–0.958). When tumor homogeneity was added, these values changed to 0.763 (95% CI: 0.518–1.000). For prediction of histological grade, an AUC value of 0.697 (95% CI: 0.490–0.952) was found, using only fractal dimension. When age, tumor homogeneity and volume parameters were added, this value increased to 0.841 (95% CI: 0.625–1.000). Our study suggests that fractal metrics are useful tools for preoperative estimation of tumor consistency and histological grading.

Object The primary treatment option for symptomatic metastatic spinal tumors is surgery. Prognostic systems are designed to assist in the establishment of the indication and the choice of surgical methodology. The best-known prognostic system is the revised Tokuhashi system, which has a predictive ability of about 60%. In our study, we are attempting to find the reason for its poor predictive ability, despite its proper separation ability. Methods We have designed a one-center-based retrospective clinical trial, by which we would like to test the feasibility and the inaccuracy of the revised Tokuhashi system. In our database, there are 329 patients who underwent surgery. Statistical analysis was performed. Results A significant increase in survival time was observed in the ‘conservative’ category. Earlier studies reported OS 0.15 at the 180-day control time, in contrast with our 0.38 OS value. The literature suggested supportive care for this category, but in our population, every patient underwent surgery. Our population passes the 0.15 OS value on day 475. We propose an adjustment of the Tokuhashi category scores. We observed significant success in resolving pain. Motor functions were improved or stabilized compared to changes in vegetative dysfunction. Conclusion According to our results, the Tokuhashi scoring system makes very conservative predictions and prefers non-surgical palliative or supportive care. Surgical treatment increases the life expectancy of patients in poor condition. We propose modifying the therapeutic options of the revised Tokuhashi system, taking into consideration modern spine surgery techniques.